Articles | Volume 18, issue 4
https://doi.org/10.5194/gmd-18-1017-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-18-1017-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Methods for assessment of models
| 
24 Feb 2025
Methods for assessment of models |
| 24 Feb 2025
| 24 Feb 2025
Explaining neural networks for detection of tropical cyclones and atmospheric rivers in gridded atmospheric simulation data
Visual Data Analysis Group, Hub of Computing and Data Science, Universität Hamburg, 20146 Hamburg, Germany
Susanne Fuchs
Visual Data Analysis Group, Hub of Computing and Data Science, Universität Hamburg, 20146 Hamburg, Germany
Christian Wilms
Computer Vision Group, Universität Hamburg, 22527 Hamburg, Germany
Iuliia Polkova
Center for Earth System Research and Sustainability (CEN), Universität Hamburg, 20146 Hamburg, Germany
Institute of Oceanography, Universität Hamburg, 20146 Hamburg, Germany
now at: Deutscher Wetterdienst, 63067 Offenbach am Main, Germany
Marc Rautenhaus
Visual Data Analysis Group, Hub of Computing and Data Science, Universität Hamburg, 20146 Hamburg, Germany
Center for Earth System Research and Sustainability (CEN), Universität Hamburg, 20146 Hamburg, Germany
Related authors
No articles found.
Oriol Tintó Prims, Robert Redl, Marc Rautenhaus, Tobias Selz, Takumi Matsunobu, Kameswar Rao Modali, and George Craig
Geosci. Model Dev., 17, 8909–8925, https://doi.org/10.5194/gmd-17-8909-2024, https://doi.org/10.5194/gmd-17-8909-2024, 2024
Short summary
Short summary
Advanced compression techniques can drastically reduce the size of meteorological datasets (by 5 to 150 times) without compromising the data's scientific value. We developed a user-friendly tool called
enstools-compressionthat makes this compression simple for Earth scientists. This tool works seamlessly with common weather and climate data formats. Our work shows that lossy compression can significantly improve how researchers store and analyze large meteorological datasets.
Christoph Fischer, Andreas H. Fink, Elmar Schömer, Marc Rautenhaus, and Michael Riemer
Geosci. Model Dev., 17, 4213–4228, https://doi.org/10.5194/gmd-17-4213-2024, https://doi.org/10.5194/gmd-17-4213-2024, 2024
Short summary
Short summary
This study presents a method for identifying and tracking 3-D potential vorticity structures within African easterly waves (AEWs). Each identified structure is characterized by descriptors, including its 3-D position and orientation, which have been validated through composite comparisons. A trough-centric perspective on the descriptors reveals the evolution and distinct characteristics of AEWs. These descriptors serve as valuable statistical inputs for the study of AEW-related phenomena.
Christoph Neuhauser, Maicon Hieronymus, Michael Kern, Marc Rautenhaus, Annika Oertel, and Rüdiger Westermann
Geosci. Model Dev., 16, 4617–4638, https://doi.org/10.5194/gmd-16-4617-2023, https://doi.org/10.5194/gmd-16-4617-2023, 2023
Short summary
Short summary
Numerical weather prediction models rely on parameterizations for sub-grid-scale processes, which are a source of uncertainty. We present novel visual analytics solutions to analyze interactively the sensitivities of a selected prognostic variable to multiple model parameters along trajectories regarding similarities in temporal development and spatiotemporal relationships. The proposed workflow is applied to cloud microphysical sensitivities along coherent strongly ascending trajectories.
Andreas A. Beckert, Lea Eisenstein, Annika Oertel, Tim Hewson, George C. Craig, and Marc Rautenhaus
Geosci. Model Dev., 16, 4427–4450, https://doi.org/10.5194/gmd-16-4427-2023, https://doi.org/10.5194/gmd-16-4427-2023, 2023
Short summary
Short summary
We investigate the benefit of objective 3-D front detection with modern interactive visual analysis techniques for case studies of extra-tropical cyclones and comparisons of frontal structures between different numerical weather prediction models. The 3-D frontal structures show agreement with 2-D fronts from surface analysis charts and augment them in the vertical dimension. We see great potential for more complex studies of atmospheric dynamics and for operational weather forecasting.
Andreas Alexander Beckert, Lea Eisenstein, Annika Oertel, Timothy Hewson, George C. Craig, and Marc Rautenhaus
Weather Clim. Dynam. Discuss., https://doi.org/10.5194/wcd-2022-36, https://doi.org/10.5194/wcd-2022-36, 2022
Preprint withdrawn
Short summary
Short summary
This study revises and extends a previously presented 3-D objective front detection method and demonstrates its benefits to analyse weather dynamics in numerical simulation data. Based on two case studies of extratropical cyclones, we demonstrate the evaluation of conceptual models from dynamic meteorology, illustrate the benefits of our interactive analysis approach by comparing fronts in data with different model resolutions, and study the impact of convection on fronts.
Christoph Fischer, Andreas H. Fink, Elmar Schömer, Roderick van der Linden, Michael Maier-Gerber, Marc Rautenhaus, and Michael Riemer
Geosci. Model Dev., 15, 4447–4468, https://doi.org/10.5194/gmd-15-4447-2022, https://doi.org/10.5194/gmd-15-4447-2022, 2022
Short summary
Short summary
Potential vorticity (PV) analysis plays a central role in studying atmospheric dynamics. For example, anomalies in the PV field near the tropopause are linked to extreme weather events. In this study, an objective strategy to identify these anomalies is presented and evaluated. As a novel concept, it can be applied to three-dimensional (3-D) data sets. Supported by 3-D visualizations, we illustrate advantages of this new analysis over existing studies along a case study.
Marcel Meyer, Iuliia Polkova, Kameswar Rao Modali, Laura Schaffer, Johanna Baehr, Stephan Olbrich, and Marc Rautenhaus
Weather Clim. Dynam., 2, 867–891, https://doi.org/10.5194/wcd-2-867-2021, https://doi.org/10.5194/wcd-2-867-2021, 2021
Short summary
Short summary
Novel techniques from computer science are used to study extreme weather events. Inspired by the interactive 3-D visual analysis of the recently released ERA5 reanalysis data, we improve commonly used metrics for measuring polar winter storms and outbreaks of cold air. The software (Met.3D) that we have extended and applied as part of this study is freely available and can be used generically for 3-D visualization of a broad variety of atmospheric processes in weather and climate data.
Hilla Afargan-Gerstman, Iuliia Polkova, Lukas Papritz, Paolo Ruggieri, Martin P. King, Panos J. Athanasiadis, Johanna Baehr, and Daniela I. V. Domeisen
Weather Clim. Dynam., 1, 541–553, https://doi.org/10.5194/wcd-1-541-2020, https://doi.org/10.5194/wcd-1-541-2020, 2020
Short summary
Short summary
We investigate the stratospheric influence on marine cold air outbreaks (MCAOs) in the North Atlantic using ERA-Interim reanalysis data. MCAOs are associated with severe Arctic weather, such as polar lows and strong surface winds. Sudden stratospheric events are found to be associated with more frequent MCAOs in the Barents and the Norwegian seas, affected by the anomalous circulation over Greenland and Scandinavia. Identification of MCAO precursors is crucial for improved long-range prediction.
M. Rautenhaus, M. Kern, A. Schäfler, and R. Westermann
Geosci. Model Dev., 8, 2329–2353, https://doi.org/10.5194/gmd-8-2329-2015, https://doi.org/10.5194/gmd-8-2329-2015, 2015
Short summary
Short summary
This article presents "Met.3D", a new open-source tool for the interactive 3D visualization of numerical ensemble weather predictions. Met.3D builds a bridge from proven 2D visualization methods commonly used in meteorology to 3D visualization and implements approaches to using the ensemble to allow the user to assess forecast uncertainty. The article is the first part of a two-paper study discussing how 3D and ensemble visualization can be used in a meaningful way suited to weather forecasting.
M. Rautenhaus, C. M. Grams, A. Schäfler, and R. Westermann
Geosci. Model Dev., 8, 2355–2377, https://doi.org/10.5194/gmd-8-2355-2015, https://doi.org/10.5194/gmd-8-2355-2015, 2015
Short summary
Short summary
This article presents the application of interactive 3D visualization of ensemble
weather predictions to forecasting warm conveyor belt situations during aircraft-based atmospheric research campaigns. A method to predict 3D probabilities of the spatial occurrence of WCBs is developed and integrated into the 3D visualization tool "Met.3D", introduced in the first part of this two-paper study. A case study demonstrates the use of 3D and uncertainty visualization for weather forecasting.
Related subject area
Atmospheric sciences
Accurate space-based NOx emission estimates with the flux divergence approach require fine-scale model information on local oxidation chemistry and profile shapes
Exploring a high-level programming model for the NWP domain using ECMWF microphysics schemes
Quantifying uncertainties in satellite NO2 superobservations for data assimilation and model evaluation
ML-AMPSIT: Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool
Coupling the urban canopy model TEB (SURFEXv9.0) with the radiation model SPARTACUS-Urbanv0.6.1 for more realistic urban radiative exchange calculation
Forecasting contrail climate forcing for flight planning and air traffic management applications: the CocipGrid model in pycontrails 0.51.0
Simulation of the heat mitigation potential of unsealing measures in cities by parameterizing grass grid pavers for urban microclimate modelling with ENVI-met (V5)
AI-NAOS: an AI-based nonspherical aerosol optical scheme for the chemical weather model GRAPES_Meso5.1/CUACE
Orbital-Radar v1.0.0: a tool to transform suborbital radar observations to synthetic EarthCARE cloud radar data
The Modular and Integrated Data Assimilation System at Environment and Climate Change Canada (MIDAS v3.9.1)
Modeling of polycyclic aromatic hydrocarbons (PAHs) from global to regional scales: model development (IAP-AACM_PAH v1.0) and investigation of health risks in 2013 and 2018 in China
LIMA (v2.0): A full two-moment cloud microphysical scheme for the mesoscale non-hydrostatic model Meso-NH v5-6
SLUCM+BEM (v1.0): a simple parameterisation for dynamic anthropogenic heat and electricity consumption in WRF-Urban (v4.3.2)
NAQPMS-PDAF v2.0: a novel hybrid nonlinear data assimilation system for improved simulation of PM2.5 chemical components
Source-specific bias correction of US background and anthropogenic ozone modeled in CMAQ
Observational operator for fair model evaluation with ground NO2 measurements
Valid time shifting ensemble Kalman filter (VTS-EnKF) for dust storm forecasting
An updated parameterization of the unstable atmospheric surface layer in the Weather Research and Forecasting (WRF) modeling system
The impact of cloud microphysics and ice nucleation on Southern Ocean clouds assessed with single-column modeling and instrument simulators
An updated aerosol simulation in the Community Earth System Model (v2.1.3): dust and marine aerosol emissions and secondary organic aerosol formation
Exploring ship track spreading rates with a physics-informed Langevin particle parameterization
Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast
Development of the MPAS-CMAQ coupled system (V1.0) for multiscale global air quality modeling
Assessment of object-based indices to identify convective organization
The Global Forest Fire Emissions Prediction System version 1.0
Sensitivity Studies of Four‐Dimensional Local Ensemble Transform Kalman Filter Coupled With WRF-Chem Version 3.9.1 for Improving Particulate Matter Simulation Accuracy
Development of A Fast Radiative Transfer Model for Ground-based Microwave Radiometers (ARMS-gb v1.0): Validation and Comparison to RTTOV-gb
NEIVAv1.0: Next-generation Emissions InVentory expansion of Akagi et al. (2011) version 1.0
FLEXPART version 11: improved accuracy, efficiency, and flexibility
Challenges of high-fidelity air quality modeling in urban environments – PALM sensitivity study during stable conditions
Knowledge-inspired fusion strategies for the inference of PM2.5 values with a Neural Network
Air quality modeling intercomparison and multiscale ensemble chain for Latin America
Recommended coupling to global meteorological fields for long-term tracer simulations with WRF-GHG
Estimation of aerosol and cloud radiative heating rate in tropical stratosphere using radiative kernel method
Selecting CMIP6 global climate models (GCMs) for Coordinated Regional Climate Downscaling Experiment (CORDEX) dynamical downscaling over Southeast Asia using a standardised benchmarking framework
Improved definition of prior uncertainties in CO2 and CO fossil fuel fluxes and its impact on multi-species inversion with GEOS-Chem (v12.5)
RASCAL v1.0: an open-source tool for climatological time series reconstruction and extension
Introducing graupel density prediction in Weather Research and Forecasting (WRF) double-moment 6-class (WDM6) microphysics and evaluation of the modified scheme during the ICE-POP field campaign
Enabling high-performance cloud computing for the Community Multiscale Air Quality Model (CMAQ) version 5.3.3: performance evaluation and benefits for the user community
Atmospheric-river-induced precipitation in California as simulated by the regionally refined Simple Convective Resolving E3SM Atmosphere Model (SCREAM) Version 0
Sensitivity of predicted ultrafine particle size distributions in Europe to different nucleation rate parameterizations using PMCAMx-UF v2.2
Recent improvements and maximum covariance analysis of aerosol and cloud properties in the EC-Earth3-AerChem model
GPU-HADVPPM4HIP V1.0: using the heterogeneous-compute interface for portability (HIP) to speed up the piecewise parabolic method in the CAMx (v6.10) air quality model on China's domestic GPU-like accelerator
Preliminary evaluation of the effect of electro-coalescence with conducting sphere approximation on the formation of warm cumulus clouds using SCALE-SDM version 0.2.5–2.3.0
Similarity-Based Analysis of Atmospheric Organic Compounds for Machine Learning Applications
Cell tracking -based framework for assessing nowcasting model skill in reproducing growth and decay of convective rainfall
Exploring the footprint representation of microwave radiance observations in an Arctic limited-area data assimilation system
Analysis of model error in forecast errors of extended atmospheric Lorenz 05 systems and the ECMWF system
Description and validation of Vehicular Emissions from Road Traffic (VERT) 1.0, an R-based framework for estimating road transport emissions from traffic flows
Improving the EnSRF in the Community Inversion Framework: a case study with ICON-ART 2024.01
Felipe Cifuentes, Henk Eskes, Enrico Dammers, Charlotte Bryan, and Folkert Boersma
Geosci. Model Dev., 18, 621–649, https://doi.org/10.5194/gmd-18-621-2025, https://doi.org/10.5194/gmd-18-621-2025, 2025
Short summary
Short summary
We tested the capability of the flux divergence approach (FDA) to reproduce known NOx emissions using synthetic NO2 satellite column retrievals from high-resolution model simulations. The FDA accurately reproduced NOx emissions when column observations were limited to the boundary layer and when the variability of the NO2 lifetime, the NOx : NO2 ratio, and NO2 profile shapes were correctly modeled. This introduces strong model dependency, reducing the simplicity of the original FDA formulation.
Stefano Ubbiali, Christian Kühnlein, Christoph Schär, Linda Schlemmer, Thomas C. Schulthess, Michael Staneker, and Heini Wernli
Geosci. Model Dev., 18, 529–546, https://doi.org/10.5194/gmd-18-529-2025, https://doi.org/10.5194/gmd-18-529-2025, 2025
Short summary
Short summary
We explore a high-level programming model for porting numerical weather prediction (NWP) model codes to graphics processing units (GPUs). We present a Python rewrite with the domain-specific library GT4Py (GridTools for Python) of two renowned cloud microphysics schemes and the associated tangent-linear and adjoint algorithms. We find excellent portability, competitive GPU performance, robust execution on diverse computing architectures, and enhanced code maintainability and user productivity.
Pieter Rijsdijk, Henk Eskes, Arlene Dingemans, K. Folkert Boersma, Takashi Sekiya, Kazuyuki Miyazaki, and Sander Houweling
Geosci. Model Dev., 18, 483–509, https://doi.org/10.5194/gmd-18-483-2025, https://doi.org/10.5194/gmd-18-483-2025, 2025
Short summary
Short summary
Clustering high-resolution satellite observations into superobservations improves model validation and data assimilation applications. In our paper, we derive quantitative uncertainties for satellite NO2 column observations based on knowledge of the retrievals, including a detailed analysis of spatial error correlations and representativity errors. The superobservations and uncertainty estimates are tested in a global chemical data assimilation system and are found to improve the forecasts.
Dario Di Santo, Cenlin He, Fei Chen, and Lorenzo Giovannini
Geosci. Model Dev., 18, 433–459, https://doi.org/10.5194/gmd-18-433-2025, https://doi.org/10.5194/gmd-18-433-2025, 2025
Short summary
Short summary
This paper presents the Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool (ML-AMPSIT), a computationally efficient tool that uses machine learning algorithms for sensitivity analysis in atmospheric models. It is tested with the Weather Research and Forecasting (WRF) model coupled with the Noah-Multiparameterization (Noah-MP) land surface model to investigate sea breeze circulation sensitivity to vegetation-related parameters.
Robert Schoetter, Robin James Hogan, Cyril Caliot, and Valéry Masson
Geosci. Model Dev., 18, 405–431, https://doi.org/10.5194/gmd-18-405-2025, https://doi.org/10.5194/gmd-18-405-2025, 2025
Short summary
Short summary
Radiation is relevant to the atmospheric impact on people and infrastructure in cities as it can influence the urban heat island, building energy consumption, and human thermal comfort. A new urban radiation model, assuming a more realistic form of urban morphology, is coupled to the urban climate model Town Energy Balance (TEB). The new TEB is evaluated with a reference radiation model for a variety of urban morphologies, and an improvement in the simulated radiative observables is found.
Zebediah Engberg, Roger Teoh, Tristan Abbott, Thomas Dean, Marc E. J. Stettler, and Marc L. Shapiro
Geosci. Model Dev., 18, 253–286, https://doi.org/10.5194/gmd-18-253-2025, https://doi.org/10.5194/gmd-18-253-2025, 2025
Short summary
Short summary
Contrails forming in some atmospheric conditions may persist and become strongly warming cirrus, while in other conditions may be neutral or cooling. We develop a contrail forecast model to predict contrail climate forcing for any arbitrary point in space and time and explore integration into flight planning and air traffic management. This approach enables contrail interventions to target high-probability high-climate-impact regions and reduce unintended consequences of contrail management.
Nils Eingrüber, Alina Domm, Wolfgang Korres, and Karl Schneider
Geosci. Model Dev., 18, 141–160, https://doi.org/10.5194/gmd-18-141-2025, https://doi.org/10.5194/gmd-18-141-2025, 2025
Short summary
Short summary
Climate change adaptation measures like unsealings can reduce urban heat stress. As grass grid pavers have never been parameterized for microclimate model simulations with ENVI-met, a new parameterization was developed based on field measurements. To analyse the cooling potential, scenario analyses were performed for a densely developed area in Cologne. Statistically significant average cooling effects of up to −11.1 K were found for surface temperature and up to −2.9 K for 1 m air temperature.
Xuan Wang, Lei Bi, Hong Wang, Yaqiang Wang, Wei Han, Xueshun Shen, and Xiaoye Zhang
Geosci. Model Dev., 18, 117–139, https://doi.org/10.5194/gmd-18-117-2025, https://doi.org/10.5194/gmd-18-117-2025, 2025
Short summary
Short summary
The Artificial-Intelligence-based Nonspherical Aerosol Optical Scheme (AI-NAOS) was developed to improve the estimation of the aerosol direct radiation effect and was coupled online with a chemical weather model. The AI-NAOS scheme considers black carbon as fractal aggregates and soil dust as super-spheroids, encapsulated with hygroscopic aerosols. Real-case simulations emphasize the necessity of accurately representing nonspherical and inhomogeneous aerosols in chemical weather models.
Lukas Pfitzenmaier, Pavlos Kollias, Nils Risse, Imke Schirmacher, Bernat Puigdomenech Treserras, and Katia Lamer
Geosci. Model Dev., 18, 101–115, https://doi.org/10.5194/gmd-18-101-2025, https://doi.org/10.5194/gmd-18-101-2025, 2025
Short summary
Short summary
The Python tool Orbital-Radar transfers suborbital radar data (ground-based, airborne, and forward-simulated numerical weather prediction model) into synthetic spaceborne cloud profiling radar data, mimicking platform-specific instrument characteristics, e.g. EarthCARE or CloudSat. The tool's novelty lies in simulating characteristic errors and instrument noise. Thus, existing data sets are transferred into synthetic observations and can be used for satellite calibration–validation studies.
Mark Buehner, Jean-Francois Caron, Ervig Lapalme, Alain Caya, Ping Du, Yves Rochon, Sergey Skachko, Maziar Bani Shahabadi, Sylvain Heilliette, Martin Deshaies-Jacques, Weiguang Chang, and Michael Sitwell
Geosci. Model Dev., 18, 1–18, https://doi.org/10.5194/gmd-18-1-2025, https://doi.org/10.5194/gmd-18-1-2025, 2025
Short summary
Short summary
The Modular and Integrated Data Assimilation System (MIDAS) software is described. The flexible design of MIDAS enables both deterministic and ensemble prediction applications for the atmosphere and several other Earth system components. It is currently used for all main operational weather prediction systems in Canada and also for sea ice and sea surface temperature analysis. The use of MIDAS for multiple Earth system components will facilitate future research on coupled data assimilation.
Zichen Wu, Xueshun Chen, Zifa Wang, Huansheng Chen, Zhe Wang, Qing Mu, Lin Wu, Wending Wang, Xiao Tang, Jie Li, Ying Li, Qizhong Wu, Yang Wang, Zhiyin Zou, and Zijian Jiang
Geosci. Model Dev., 17, 8885–8907, https://doi.org/10.5194/gmd-17-8885-2024, https://doi.org/10.5194/gmd-17-8885-2024, 2024
Short summary
Short summary
We developed a model to simulate polycyclic aromatic hydrocarbons (PAHs) from global to regional scales. The model can reproduce PAH distribution well. The concentration of BaP (indicator species for PAHs) could exceed the target values of 1 ng m-3 over some areas (e.g., in central Europe, India, and eastern China). The change in BaP is lower than that in PM2.5 from 2013 to 2018. China still faces significant potential health risks posed by BaP although the Action Plan has been implemented.
Marie Taufour, Jean-Pierre Pinty, Christelle Barthe, Benoît Vié, and Chien Wang
Geosci. Model Dev., 17, 8773–8798, https://doi.org/10.5194/gmd-17-8773-2024, https://doi.org/10.5194/gmd-17-8773-2024, 2024
Short summary
Short summary
We have developed a complete two-moment version of the LIMA (Liquid Ice Multiple Aerosols) microphysics scheme. We have focused on collection processes, where the hydrometeor number transfer is often estimated in proportion to the mass transfer. The impact of these parameterizations on a convective system and the prospects for more realistic estimates of secondary parameters (reflectivity, hydrometeor size) are shown in a first test on an idealized case.
Yuya Takane, Yukihiro Kikegawa, Ko Nakajima, and Hiroyuki Kusaka
Geosci. Model Dev., 17, 8639–8664, https://doi.org/10.5194/gmd-17-8639-2024, https://doi.org/10.5194/gmd-17-8639-2024, 2024
Short summary
Short summary
A new parameterisation for dynamic anthropogenic heat and electricity consumption is described. The model reproduced the temporal variation in and spatial distributions of electricity consumption and temperature well in summer and winter. The partial air conditioning was the most critical factor, significantly affecting the value of anthropogenic heat emission.
Hongyi Li, Ting Yang, Lars Nerger, Dawei Zhang, Di Zhang, Guigang Tang, Haibo Wang, Yele Sun, Pingqing Fu, Hang Su, and Zifa Wang
Geosci. Model Dev., 17, 8495–8519, https://doi.org/10.5194/gmd-17-8495-2024, https://doi.org/10.5194/gmd-17-8495-2024, 2024
Short summary
Short summary
To accurately characterize the spatiotemporal distribution of particulate matter <2.5 µm chemical components, we developed the Nested Air Quality Prediction Model System with the Parallel Data Assimilation Framework (NAQPMS-PDAF) v2.0 for chemical components with non-Gaussian and nonlinear properties. NAQPMS-PDAF v2.0 has better computing efficiency, excels when used with a small ensemble size, and can significantly improve the simulation performance of chemical components.
T. Nash Skipper, Christian Hogrefe, Barron H. Henderson, Rohit Mathur, Kristen M. Foley, and Armistead G. Russell
Geosci. Model Dev., 17, 8373–8397, https://doi.org/10.5194/gmd-17-8373-2024, https://doi.org/10.5194/gmd-17-8373-2024, 2024
Short summary
Short summary
Chemical transport model simulations are combined with ozone observations to estimate the bias in ozone attributable to US anthropogenic sources and individual sources of US background ozone: natural sources, non-US anthropogenic sources, and stratospheric ozone. Results indicate a positive bias correlated with US anthropogenic emissions during summer in the eastern US and a negative bias correlated with stratospheric ozone during spring.
Li Fang, Jianbing Jin, Arjo Segers, Ke Li, Ji Xia, Wei Han, Baojie Li, Hai Xiang Lin, Lei Zhu, Song Liu, and Hong Liao
Geosci. Model Dev., 17, 8267–8282, https://doi.org/10.5194/gmd-17-8267-2024, https://doi.org/10.5194/gmd-17-8267-2024, 2024
Short summary
Short summary
Model evaluations against ground observations are usually unfair. The former simulates mean status over coarse grids and the latter the surrounding atmosphere. To solve this, we proposed the new land-use-based representative (LUBR) operator that considers intra-grid variance. The LUBR operator is validated to provide insights that align with satellite measurements. The results highlight the importance of considering fine-scale urban–rural differences when comparing models and observation.
Mijie Pang, Jianbing Jin, Arjo Segers, Huiya Jiang, Wei Han, Batjargal Buyantogtokh, Ji Xia, Li Fang, Jiandong Li, Hai Xiang Lin, and Hong Liao
Geosci. Model Dev., 17, 8223–8242, https://doi.org/10.5194/gmd-17-8223-2024, https://doi.org/10.5194/gmd-17-8223-2024, 2024
Short summary
Short summary
The ensemble Kalman filter (EnKF) improves dust storm forecasts but faces challenges with position errors. The valid time shifting EnKF (VTS-EnKF) addresses this by adjusting for position errors, enhancing accuracy in forecasting dust storms, as proven in tests on 2021 events, even with smaller ensembles and time intervals.
Prabhakar Namdev, Maithili Sharan, Piyush Srivastava, and Saroj Kanta Mishra
Geosci. Model Dev., 17, 8093–8114, https://doi.org/10.5194/gmd-17-8093-2024, https://doi.org/10.5194/gmd-17-8093-2024, 2024
Short summary
Short summary
Inadequate representation of surface–atmosphere interaction processes is a major source of uncertainty in numerical weather prediction models. Here, an effort has been made to improve the Weather Research and Forecasting (WRF) model version 4.2.2 by introducing a unique theoretical framework under convective conditions. In addition, to enhance the potential applicability of the WRF modeling system, various commonly used similarity functions under convective conditions have also been installed.
Andrew Gettelman, Richard Forbes, Roger Marchand, Chih-Chieh Chen, and Mark Fielding
Geosci. Model Dev., 17, 8069–8092, https://doi.org/10.5194/gmd-17-8069-2024, https://doi.org/10.5194/gmd-17-8069-2024, 2024
Short summary
Short summary
Supercooled liquid clouds (liquid clouds colder than 0°C) are common at higher latitudes (especially over the Southern Ocean) and are critical for constraining climate projections. We compare a single-column version of a weather model to observations with two different cloud schemes and find that both the dynamical environment and atmospheric aerosols are important for reproducing observations.
Yujuan Wang, Peng Zhang, Jie Li, Yaman Liu, Yanxu Zhang, Jiawei Li, and Zhiwei Han
Geosci. Model Dev., 17, 7995–8021, https://doi.org/10.5194/gmd-17-7995-2024, https://doi.org/10.5194/gmd-17-7995-2024, 2024
Short summary
Short summary
This study updates the CESM's aerosol schemes, focusing on dust, marine aerosol emissions, and secondary organic aerosol (SOA) . Dust emission modifications make deflation areas more continuous, improving results in North America and the sub-Arctic. Humidity correction to sea-salt emissions has a minor effect. Introducing marine organic aerosol emissions, coupled with ocean biogeochemical processes, and adding aqueous reactions for SOA formation advance the CESM's aerosol modelling results.
Lucas A. McMichael, Michael J. Schmidt, Robert Wood, Peter N. Blossey, and Lekha Patel
Geosci. Model Dev., 17, 7867–7888, https://doi.org/10.5194/gmd-17-7867-2024, https://doi.org/10.5194/gmd-17-7867-2024, 2024
Short summary
Short summary
Marine cloud brightening (MCB) is a climate intervention technique to potentially cool the climate. Climate models used to gauge regional climate impacts associated with MCB often assume large areas of the ocean are uniformly perturbed. However, a more realistic representation of MCB application would require information about how an injected particle plume spreads. This work aims to develop such a plume-spreading model.
Leonardo Olivetti and Gabriele Messori
Geosci. Model Dev., 17, 7915–7962, https://doi.org/10.5194/gmd-17-7915-2024, https://doi.org/10.5194/gmd-17-7915-2024, 2024
Short summary
Short summary
Data-driven models are becoming a viable alternative to physics-based models for weather forecasting up to 15 d into the future. However, it is unclear whether they are as reliable as physics-based models when forecasting weather extremes. We evaluate their performance in forecasting near-surface cold, hot, and windy extremes globally. We find that data-driven models can compete with physics-based models and that the choice of the best model mainly depends on the region and type of extreme.
David C. Wong, Jeff Willison, Jonathan E. Pleim, Golam Sarwar, James Beidler, Russ Bullock, Jerold A. Herwehe, Rob Gilliam, Daiwen Kang, Christian Hogrefe, George Pouliot, and Hosein Foroutan
Geosci. Model Dev., 17, 7855–7866, https://doi.org/10.5194/gmd-17-7855-2024, https://doi.org/10.5194/gmd-17-7855-2024, 2024
Short summary
Short summary
This work describe how we linked the meteorological Model for Prediction Across Scales – Atmosphere (MPAS-A) with the Community Multiscale Air Quality (CMAQ) air quality model to form a coupled modelling system. This could be used to study air quality or climate and air quality interaction at a global scale. This new model scales well in high-performance computing environments and performs well with respect to ground surface networks in terms of ozone and PM2.5.
Giulio Mandorli and Claudia J. Stubenrauch
Geosci. Model Dev., 17, 7795–7813, https://doi.org/10.5194/gmd-17-7795-2024, https://doi.org/10.5194/gmd-17-7795-2024, 2024
Short summary
Short summary
In recent years, several studies focused their attention on the disposition of convection. Lots of methods, called indices, have been developed to quantify the amount of convection clustering. These indices are evaluated in this study by defining criteria that must be satisfied and then evaluating the indices against these standards. None of the indices meet all criteria, with some only partially meeting them.
Kerry Anderson, Jack Chen, Peter Englefield, Debora Griffin, Paul A. Makar, and Dan Thompson
Geosci. Model Dev., 17, 7713–7749, https://doi.org/10.5194/gmd-17-7713-2024, https://doi.org/10.5194/gmd-17-7713-2024, 2024
Short summary
Short summary
The Global Forest Fire Emissions Prediction System (GFFEPS) is a model that predicts smoke and carbon emissions from wildland fires. The model calculates emissions from the ground up based on satellite-detected fires, modelled weather and fire characteristics. Unlike other global models, GFFEPS uses daily weather conditions to capture changing burning conditions on a day-to-day basis. GFFEPS produced lower carbon emissions due to the changing weather not captured by the other models.
Jianyu Lin, Tie Dai, Lifang Sheng, Weihang Zhang, Shangfei Hai, and Yawen Kong
EGUsphere, https://doi.org/10.5194/egusphere-2024-3321, https://doi.org/10.5194/egusphere-2024-3321, 2024
Short summary
Short summary
The effectiveness of assimilation system and its sensitivity to ensemble member size and length of assimilation window have been investigated. This study advances our understanding about the selection of basic parameters in the four-dimension local ensemble transform Kalman filter assimilation system and the performance of ensemble simulation in a particulate matter polluted environment.
Yi-Ning Shi, Jun Yang, Wei Han, Lujie Han, Jiajia Mao, Wanlin Kan, and Fuzhong Weng
EGUsphere, https://doi.org/10.5194/egusphere-2024-2884, https://doi.org/10.5194/egusphere-2024-2884, 2024
Short summary
Short summary
Assimilating Ground-based microwave radiometers' observations into numerical weather prediction models holds significant promise for enhancing forecast accuracy. Radiative transfer models (RTM) are crucial for direct data assimilation. We propose a new RTM capable of simulating brightness temperatures observed by GMRs and their Jacobians. Several improvements are introduced to achieve higher accuracy.The RTM align with RTTOV-gb well and can achieve smaller STD in water vapor absorption channels.
Samiha Binte Shahid, Forrest G. Lacey, Christine Wiedinmyer, Robert J. Yokelson, and Kelley C. Barsanti
Geosci. Model Dev., 17, 7679–7711, https://doi.org/10.5194/gmd-17-7679-2024, https://doi.org/10.5194/gmd-17-7679-2024, 2024
Short summary
Short summary
The Next-generation Emissions InVentory expansion of Akagi (NEIVA) v.1.0 is a comprehensive biomass burning emissions database that allows integration of new data and flexible querying. Data are stored in connected datasets, including recommended averages of ~1500 constituents for 14 globally relevant fire types. Individual compounds were mapped to common model species to allow better attribution of emissions in modeling studies that predict the effects of fires on air quality and climate.
Lucie Bakels, Daria Tatsii, Anne Tipka, Rona Thompson, Marina Dütsch, Michael Blaschek, Petra Seibert, Katharina Baier, Silvia Bucci, Massimo Cassiani, Sabine Eckhardt, Christine Groot Zwaaftink, Stephan Henne, Pirmin Kaufmann, Vincent Lechner, Christian Maurer, Marie D. Mulder, Ignacio Pisso, Andreas Plach, Rakesh Subramanian, Martin Vojta, and Andreas Stohl
Geosci. Model Dev., 17, 7595–7627, https://doi.org/10.5194/gmd-17-7595-2024, https://doi.org/10.5194/gmd-17-7595-2024, 2024
Short summary
Short summary
Computer models are essential for improving our understanding of how gases and particles move in the atmosphere. We present an update of the atmospheric transport model FLEXPART. FLEXPART 11 is more accurate due to a reduced number of interpolations and a new scheme for wet deposition. It can simulate non-spherical aerosols and includes linear chemical reactions. It is parallelised using OpenMP and includes new user options. A new user manual details how to use FLEXPART 11.
Jaroslav Resler, Petra Bauerová, Michal Belda, Martin Bureš, Kryštof Eben, Vladimír Fuka, Jan Geletič, Radek Jareš, Jan Karel, Josef Keder, Pavel Krč, William Patiño, Jelena Radović, Hynek Řezníček, Matthias Sühring, Adriana Šindelářová, and Ondřej Vlček
Geosci. Model Dev., 17, 7513–7537, https://doi.org/10.5194/gmd-17-7513-2024, https://doi.org/10.5194/gmd-17-7513-2024, 2024
Short summary
Short summary
Detailed modeling of urban air quality in stable conditions is a challenge. We show the unprecedented sensitivity of a large eddy simulation (LES) model to meteorological boundary conditions and model parameters in an urban environment under stable conditions. We demonstrate the crucial role of boundary conditions for the comparability of results with observations. The study reveals a strong sensitivity of the results to model parameters and model numerical instabilities during such conditions.
Matthieu Dabrowski, José Mennesson, Jérôme Riedi, Chaabane Djeraba, and Pierre Nabat
EGUsphere, https://doi.org/10.5194/egusphere-2024-2676, https://doi.org/10.5194/egusphere-2024-2676, 2024
Short summary
Short summary
This work focuses on the prediction of aerosol concentration values at ground level, which are a strong indicator of air quality, using Artificial Neural Networks. A study of different variables and their efficiency as inputs for these models is also proposed, and reveals that the best results are obtained when using all of them. Comparison of networks architectures and information fusion methods allows the extraction of knowledge on the most efficient methods in the context of this study.
Jorge E. Pachón, Mariel A. Opazo, Pablo Lichtig, Nicolas Huneeus, Idir Bouarar, Guy Brasseur, Cathy W. Y. Li, Johannes Flemming, Laurent Menut, Camilo Menares, Laura Gallardo, Michael Gauss, Mikhail Sofiev, Rostislav Kouznetsov, Julia Palamarchuk, Andreas Uppstu, Laura Dawidowski, Nestor Y. Rojas, María de Fátima Andrade, Mario E. Gavidia-Calderón, Alejandro H. Delgado Peralta, and Daniel Schuch
Geosci. Model Dev., 17, 7467–7512, https://doi.org/10.5194/gmd-17-7467-2024, https://doi.org/10.5194/gmd-17-7467-2024, 2024
Short summary
Short summary
Latin America (LAC) has some of the most populated urban areas in the world, with high levels of air pollution. Air quality management in LAC has been traditionally focused on surveillance and building emission inventories. This study performed the first intercomparison and model evaluation in LAC, with interesting and insightful findings for the region. A multiscale modeling ensemble chain was assembled as a first step towards an air quality forecasting system.
David Ho, Michał Gałkowski, Friedemann Reum, Santiago Botía, Julia Marshall, Kai Uwe Totsche, and Christoph Gerbig
Geosci. Model Dev., 17, 7401–7422, https://doi.org/10.5194/gmd-17-7401-2024, https://doi.org/10.5194/gmd-17-7401-2024, 2024
Short summary
Short summary
Atmospheric model users often overlook the impact of the land–atmosphere interaction. This study accessed various setups of WRF-GHG simulations that ensure consistency between the model and driving reanalysis fields. We found that a combination of nudging and frequent re-initialization allows certain improvement by constraining the soil moisture fields and, through its impact on atmospheric mixing, improves atmospheric transport.
Jie Gao, Yi Huang, Jonathon S. Wright, Ke Li, Tao Geng, and Qiurun Yu
EGUsphere, https://doi.org/10.5194/egusphere-2024-2815, https://doi.org/10.5194/egusphere-2024-2815, 2024
Short summary
Short summary
The aerosol in the upper troposphere and stratosphere is highly variable, and its radiative effect is poorly understood. To estimate that effect, the radiative kernel is constructed and applied. The results show that the kernels can reproduce aerosol radiative effects and are expected to simulate stratospheric aerosol radiative effects. This approach reduces computational expense and consists well with radiative model calculations and can be applied to atmospheric models with speed requirements.
Phuong Loan Nguyen, Lisa V. Alexander, Marcus J. Thatcher, Son C. H. Truong, Rachael N. Isphording, and John L. McGregor
Geosci. Model Dev., 17, 7285–7315, https://doi.org/10.5194/gmd-17-7285-2024, https://doi.org/10.5194/gmd-17-7285-2024, 2024
Short summary
Short summary
We use a comprehensive approach to select a subset of CMIP6 models for dynamical downscaling over Southeast Asia, taking into account model performance, model independence, data availability and the range of future climate projections. The standardised benchmarking framework is applied to assess model performance through both statistical and process-based metrics. Ultimately, we identify two independent model groups that are suitable for dynamical downscaling in the Southeast Asian region.
Ingrid Super, Tia Scarpelli, Arjan Droste, and Paul I. Palmer
Geosci. Model Dev., 17, 7263–7284, https://doi.org/10.5194/gmd-17-7263-2024, https://doi.org/10.5194/gmd-17-7263-2024, 2024
Short summary
Short summary
Monitoring greenhouse gas emission reductions requires a combination of models and observations, as well as an initial emission estimate. Each component provides information with a certain level of certainty and is weighted to yield the most reliable estimate of actual emissions. We describe efforts for estimating the uncertainty in the initial emission estimate, which significantly impacts the outcome. Hence, a good uncertainty estimate is key for obtaining reliable information on emissions.
Álvaro González-Cervera and Luis Durán
Geosci. Model Dev., 17, 7245–7261, https://doi.org/10.5194/gmd-17-7245-2024, https://doi.org/10.5194/gmd-17-7245-2024, 2024
Short summary
Short summary
RASCAL is an open-source Python tool designed for reconstructing daily climate observations, especially in regions with complex local phenomena. It merges large-scale weather patterns with local weather using the analog method. Evaluations in central Spain show that RASCAL outperforms ERA20C reanalysis in reconstructing precipitation and temperature. RASCAL offers opportunities for broad scientific applications, from short-term forecasts to local-scale climate change scenarios.
Sun-Young Park, Kyo-Sun Sunny Lim, Kwonil Kim, Gyuwon Lee, and Jason A. Milbrandt
Geosci. Model Dev., 17, 7199–7218, https://doi.org/10.5194/gmd-17-7199-2024, https://doi.org/10.5194/gmd-17-7199-2024, 2024
Short summary
Short summary
We enhance the WDM6 scheme by incorporating predicted graupel density. The modification affects graupel characteristics, including fall velocity–diameter and mass–diameter relationships. Simulations highlight changes in graupel distribution and precipitation patterns, potentially influencing surface snow amounts. The study underscores the significance of integrating predicted graupel density for a more realistic portrayal of microphysical properties in weather models.
Christos I. Efstathiou, Elizabeth Adams, Carlie J. Coats, Robert Zelt, Mark Reed, John McGee, Kristen M. Foley, Fahim I. Sidi, David C. Wong, Steven Fine, and Saravanan Arunachalam
Geosci. Model Dev., 17, 7001–7027, https://doi.org/10.5194/gmd-17-7001-2024, https://doi.org/10.5194/gmd-17-7001-2024, 2024
Short summary
Short summary
We present a summary of enabling high-performance computing of the Community Multiscale Air Quality Model (CMAQ) – a state-of-the-science community multiscale air quality model – on two cloud computing platforms through documenting the technologies, model performance, scaling and relative merits. This may be a new paradigm for computationally intense future model applications. We initiated this work due to a need to leverage cloud computing advances and to ease the learning curve for new users.
Peter A. Bogenschutz, Jishi Zhang, Qi Tang, and Philip Cameron-Smith
Geosci. Model Dev., 17, 7029–7050, https://doi.org/10.5194/gmd-17-7029-2024, https://doi.org/10.5194/gmd-17-7029-2024, 2024
Short summary
Short summary
Using high-resolution and state-of-the-art modeling techniques we simulate five atmospheric river events for California to test the capability to represent precipitation for these events. We find that our model is able to capture the distribution of precipitation very well but suffers from overestimating the precipitation amounts over high elevation. Increasing the resolution further has no impact on reducing this bias, while increasing the domain size does have modest impacts.
David Patoulias, Kalliopi Florou, and Spyros N. Pandis
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-145, https://doi.org/10.5194/gmd-2024-145, 2024
Revised manuscript accepted for GMD
Short summary
Short summary
The effect of the assumed atmospheric nucleation mechanism on particle number concentrations and size distribution was investigated. Two quite different mechanisms involving sulfuric acid and ammonia or a biogenic organic vapor gave quite similar results which were consistent with measurements in 26 measurement stations across Europe. The number of larger particles that serve as cloud condensation nuclei showed little sensitivity to the assumed nucleation mechanism.
Manu Anna Thomas, Klaus Wyser, Shiyu Wang, Marios Chatziparaschos, Paraskevi Georgakaki, Montserrat Costa-Surós, Maria Gonçalves Ageitos, Maria Kanakidou, Carlos Pérez García-Pando, Athanasios Nenes, Twan van Noije, Philippe Le Sager, and Abhay Devasthale
Geosci. Model Dev., 17, 6903–6927, https://doi.org/10.5194/gmd-17-6903-2024, https://doi.org/10.5194/gmd-17-6903-2024, 2024
Short summary
Short summary
Aerosol–cloud interactions occur at a range of spatio-temporal scales. While evaluating recent developments in EC-Earth3-AerChem, this study aims to understand the extent to which the Twomey effect manifests itself at larger scales. We find a reduction in the warm bias over the Southern Ocean due to model improvements. While we see footprints of the Twomey effect at larger scales, the negative relationship between cloud droplet number and liquid water drives the shortwave radiative effect.
Kai Cao, Qizhong Wu, Lingling Wang, Hengliang Guo, Nan Wang, Huaqiong Cheng, Xiao Tang, Dongxing Li, Lina Liu, Dongqing Li, Hao Wu, and Lanning Wang
Geosci. Model Dev., 17, 6887–6901, https://doi.org/10.5194/gmd-17-6887-2024, https://doi.org/10.5194/gmd-17-6887-2024, 2024
Short summary
Short summary
AMD’s heterogeneous-compute interface for portability was implemented to port the piecewise parabolic method solver from NVIDIA GPUs to China's GPU-like accelerators. The results show that the larger the model scale, the more acceleration effect on the GPU-like accelerator, up to 28.9 times. The multi-level parallelism achieves a speedup of 32.7 times on the heterogeneous cluster. By comparing the results, the GPU-like accelerators have more accuracy for the geoscience numerical models.
Ruyi Zhang, Limin Zhou, Shin-ichiro Shima, and Huawei Yang
Geosci. Model Dev., 17, 6761–6774, https://doi.org/10.5194/gmd-17-6761-2024, https://doi.org/10.5194/gmd-17-6761-2024, 2024
Short summary
Short summary
Solar activity weakly ionises Earth's atmosphere, charging cloud droplets. Electro-coalescence is when oppositely charged droplets stick together. We introduce an analytical expression of electro-coalescence probability and use it in a warm-cumulus-cloud simulation. Results show that charge cases increase rain and droplet size, with the new method outperforming older ones. The new method requires longer computation time, but its impact on rain justifies inclusion in meteorology models.
Hilda Sandström and Patrick Rinke
EGUsphere, https://doi.org/10.48550/arXiv.2406.18171, https://doi.org/10.48550/arXiv.2406.18171, 2024
Short summary
Short summary
Machine learning has the potential to aid the identification organic molecules involved in aerosol formation. Yet, progress is stalled by a lack of curated atmospheric molecular datasets. Here, we compared atmospheric compounds with large molecular datasets used in machine learning and found minimal overlap with similarity algorithms. Our result underlines the need for collaborative efforts to curate atmospheric molecular data to facilitate machine learning model in atmospheric sciences.
Jenna Ritvanen, Seppo Pulkkinen, Dmitri Moisseev, and Daniele Nerini
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-99, https://doi.org/10.5194/gmd-2024-99, 2024
Revised manuscript accepted for GMD
Short summary
Short summary
Nowcasting models struggle with the rapid evolution of heavy rain, and common verification methods are unable to describe how accurately the models predict the growth and decay of heavy rainfall. We propose a framework to assess model performance. In the framework, convective cells are identified and tracked in the forecasts and observations, and then the model skill is evaluated by comparing differences between forecast and observed cells. We demonstrate the framework with 4 open-source models.
Máté Mile, Stephanie Guedj, and Roger Randriamampianina
Geosci. Model Dev., 17, 6571–6587, https://doi.org/10.5194/gmd-17-6571-2024, https://doi.org/10.5194/gmd-17-6571-2024, 2024
Short summary
Short summary
Satellite observations provide crucial information about atmospheric constituents in a global distribution that helps to better predict the weather over sparsely observed regions like the Arctic. However, the use of satellite data is usually conservative and imperfect. In this study, a better spatial representation of satellite observations is discussed and explored by a so-called footprint function or operator, highlighting its added value through a case study and diagnostics.
Hynek Bednář and Holger Kantz
Geosci. Model Dev., 17, 6489–6511, https://doi.org/10.5194/gmd-17-6489-2024, https://doi.org/10.5194/gmd-17-6489-2024, 2024
Short summary
Short summary
The forecast error growth of atmospheric phenomena is caused by initial and model errors. When studying the initial error growth, it may turn out that small-scale phenomena, which contribute little to the forecast product, significantly affect the ability to predict this product. With a negative result, we investigate in the extended Lorenz (2005) system whether omitting these phenomena will improve predictability. A theory explaining and describing this behavior is developed.
Giorgio Veratti, Alessandro Bigi, Sergio Teggi, and Grazia Ghermandi
Geosci. Model Dev., 17, 6465–6487, https://doi.org/10.5194/gmd-17-6465-2024, https://doi.org/10.5194/gmd-17-6465-2024, 2024
Short summary
Short summary
In this study, we present VERT (Vehicular Emissions from Road Traffic), an R package designed to estimate transport emissions using traffic estimates and vehicle fleet composition data. Compared to other tools available in the literature, VERT stands out for its user-friendly configuration and flexibility of user input. Case studies demonstrate its accuracy in both urban and regional contexts, making it a valuable tool for air quality management and transport scenario planning.
Joël Thanwerdas, Antoine Berchet, Lionel Constantin, Aki Tsuruta, Michael Steiner, Friedemann Reum, Stephan Henne, and Dominik Brunner
EGUsphere, https://doi.org/10.5194/egusphere-2024-2197, https://doi.org/10.5194/egusphere-2024-2197, 2024
Short summary
Short summary
The Community Inversion Framework (CIF) brings together methods for estimating greenhouse gas fluxes from atmospheric observations. The initial ensemble method implemented in CIF was found to be incomplete and could hardly be compared to other ensemble methods employed in the inversion community. In this paper, we present and evaluate a more efficient implementation of the serial and batch versions of the Ensemble Square Root Filter (EnSRF) algorithm in CIF.
Cited articles
Abu Alhaija, H., Mustikovela, S. K., Mescheder, L., Geiger, A., and Rother, C.: Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes, Int. J. Comput. Vis., 126, 961–972, https://doi.org/10.1007/s11263-018-1070-x, 2018.
Achtibat, R., Dreyer, M., Eisenbraun, I., Bosse, S., Wiegand, T., Samek, W., and Lapuschkin, S.: From attribution maps to human-understandable explanations through Concept Relevance Propagation, Nat. Mach. Intell., 5, 1006–1019, https://doi.org/10.1038/s42256-023-00711-8, 2023.
Ahmed, A. M. A. and Ali, L.: Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagation, Nordic Machine Intelligence, 1, 20–22, https://doi.org/10.5617/nmi.9126, 2021.
Ahrens, C. D., Jackson, P. L., and Jackson, C. E. O.: Meteorology Today: An Introduction to Weather, Climate, and the Environment, Nelson Education, 710 pp., ISBN-10 0357452070, ISBN-13 978-0357452073, 2012.
Alves, D. B. M., Sapucci, L. F., Marques, H. A., and Souza, E. M.: Using a regional numerical weather prediction model for GNSS positioning over Brazil, GPS Solut., 20, 677–685, https://doi.org/10.1007/s10291-015-0477-x, 2016.
Arras, L., Montavon, G., Müller, K.-R., and Samek, W.: Explaining Recurrent Neural Network Predictions in Sentiment Analysis, in: Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2017, Copenhagen, Denmark, 159–168, https://doi.org/10.18653/v1/W17-5221, 2017.
Avberšek, L. K. and Repovš, G.: Deep learning in neuroimaging data analysis: Applications, challenges, and solutions, Front. Neuroimaging, 1, 981642, https://doi.org/10.3389/fnimg.2022.981642, 2022.
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., and Samek, W.: On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation, PLOS ONE, 10, e0130140, https://doi.org/10.1371/journal.pone.0130140, 2015.
Beckert, A. A., Eisenstein, L., Oertel, A., Hewson, T., Craig, G. C., and Rautenhaus, M.: The three-dimensional structure of fronts in mid-latitude weather systems in numerical weather prediction models, Geosci. Model Dev., 16, 4427–4450, https://doi.org/10.5194/gmd-16-4427-2023, 2023.
Beobide-Arsuaga, G., Düsterhus, A., Müller, W. A., Barnes, E. A., and Baehr, J.: Spring Regional Sea Surface Temperatures as a Precursor of European Summer Heatwaves, Geophys. Res. Lett., 50, e2022GL100727, https://doi.org/10.1029/2022GL100727, 2023.
Biard, J. C. and Kunkel, K. E.: Automated detection of weather fronts using a deep learning neural network, Adv. Stat. Clim. Meteorol. Oceanogr., 5, 147–160, https://doi.org/10.5194/ascmo-5-147-2019, 2019.
Bishop, C. M.: Neural Networks for Pattern Recognition, Clarendon Press, 501 pp., https://doi.org/10.1093/oso/9780198538493.001.0001, 1995.
Bishop, C. M.: Pattern recognition and machine learning, 5. (corr. print.), Springer, New York, XX, 738 pp., ISBN 978-1-4939-3843-8, 2007.
Bösiger, L., Sprenger, M., Boettcher, M., Joos, H., and Günther, T.: Integration-based extraction and visualization of jet stream cores, Geosci. Model Dev., 15, 1079–1096, https://doi.org/10.5194/gmd-15-1079-2022, 2022.
Boukabara, S.-A., Krasnopolsky, V., Penny, S. G., Stewart, J. Q., McGovern, A., Hall, D., Hoeve, J. E. T., Hickey, J., Huang, H.-L. A., Williams, J. K., Ide, K., Tissot, P., Haupt, S. E., Casey, K. S., Oza, N., Geer, A. J., Maddy, E. S., and Hoffman, R. N.: Outlook for Exploiting Artificial Intelligence in the Earth and Environmental Sciences, B. Am. Meteorol. Soc., 102, E1016–E1032, https://doi.org/10.1175/BAMS-D-20-0031.1, 2021.
Bourdin, S., Fromang, S., Dulac, W., Cattiaux, J., and Chauvin, F.: Intercomparison of four algorithms for detecting tropical cyclones using ERA5, Geosci. Model Dev., 15, 6759–6786, https://doi.org/10.5194/gmd-15-6759-2022, 2022.
Captum: Semantic Segmentation with Captum, https://captum.ai/tutorials/Segmentation_Interpret, last access: 17 November 2023.
Chase, R. J., Harrison, D. R., Burke, A., Lackmann, G. M., and McGovern, A.: A Machine Learning Tutorial for Operational Meteorology. Part I: Traditional Machine Learning, Weather Forecast., 37, 1509–1529, https://doi.org/10.1175/WAF-D-22-0070.1, 2022.
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H.: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, in: Computer Vision – ECCV 2018, edited by: Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y., Springer International Publishing, Cham, vol. 11211, 833–851, https://doi.org/10.1007/978-3-030-01234-2_49, 2018.
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B.: The Cityscapes Dataset for Semantic Urban Scene Understanding, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 3213–3223, https://doi.org/10.1109/CVPR.2016.350, 2016.
Dardouillet, P., Benoit, A., Amri, E., Bolon, P., Dubucq, D., and Credoz, A.: Explainability of Image Semantic Segmentation Through SHAP Values, in: Pattern Recognition, Computer Vision, and Image Processing, ICPR 2022 International Workshops and Challenges, Cham, 188–202, https://doi.org/10.1007/978-3-031-37731-0_19, 2023.
Davenport, F. V. and Diffenbaugh, N. S.: Using Machine Learning to Analyze Physical Causes of Climate Change: A Case Study of U.S. Midwest Extreme Precipitation, Geophys. Res. Lett., 48, e2021GL093787, https://doi.org/10.1029/2021GL093787, 2021.
Dawe, J. T. and Austin, P. H.: Statistical analysis of an LES shallow cumulus cloud ensemble using a cloud tracking algorithm, Atmos. Chem. Phys., 12, 1101–1119, https://doi.org/10.5194/acp-12-1101-2012, 2012.
Dong, J., Liu, B., Zhang, Z., Wang, W., Mehra, A., Hazelton, A. T., Winterbottom, H. R., Zhu, L., Wu, K., Zhang, C., Tallapragada, V., Zhang, X., Gopalakrishnan, S., and Marks, F.: The Evaluation of Real-Time Hurricane Analysis and Forecast System (HAFS) Stand-Alone Regional (SAR) Model Performance for the 2019 Atlantic Hurricane Season, Atmosphere, 11, 617, https://doi.org/10.3390/atmos11060617, 2020.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A.: The Pascal Visual Object Classes (VOC) Challenge, Int. J. Comput. Vis., 88, 303–338, https://doi.org/10.1007/s11263-009-0275-4, 2010.
Farokhmanesh, F., Höhlein, K., and Westermann, R.: Deep Learning–Based Parameter Transfer in Meteorological Data, Artif. Intell. Earth Syst., 2, e220024, https://doi.org/10.1175/AIES-D-22-0024.1, 2023.
García, S., Luengo, J., and Herrera, F.: Data Preprocessing in Data Mining, Springer, 327 pp., ISBN 978-3-319-37731-5, 2014.
Gimeno, L., Nieto, R., Vázquez, M., and Lavers, D.: Atmospheric rivers: a mini-review, Front. Earth Sci., 2, 2, https://doi.org/10.3389/feart.2014.00002, 2014.
Guan, B. and Waliser, D.: Detection of Atmospheric Rivers: Evaluation and Application of an Algorithm for Global Studies, J. Geophys. Res.-Atmos., 120, 12514–12535, https://doi.org/10.1002/2015JD024257, 2015.
Guillemot, M., Heusele, C., Korichi, R., Schnebert, S., and Chen, L.: Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation, ArXiv [preprint], https://doi.org/10.48550/arXiv.2002.11018, 2020.
Hengstebeck, T., Wapler, K., Heizenreder, D., and Joe, P.: Radar Network–Based Detection of Mesocyclones at the German Weather Service, J. Atmos. Ocean. Tech., 35, 299–321, https://doi.org/10.1175/JTECH-D-16-0230.1, 2018.
Hewson, T. D. and Titley, H. A.: Objective identification, typing and tracking of the complete life-cycles of cyclonic features at high spatial resolution, Meteorol. Appl., 17, 355–381, https://doi.org/10.1002/met.204, 2010.
Higgins, T. B., Subramanian, A. C., Graubner, A., Kapp-Schwoerer, L., Watson, P. A. G., Sparrow, S., Kashinath, K., Kim, S., Delle Monache, L., and Chapman, W.: Using Deep Learning for an Analysis of Atmospheric Rivers in a High-Resolution Large Ensemble Climate Data Set, J. Adv. Model. Earth Sy., 15, e2022MS003495, https://doi.org/10.1029/2022MS003495, 2023.
Hintze, J. L. and Nelson, R. D.: Violin Plots: A Box Plot-Density Trace Synergism, Am. Stat., 52, 181, https://doi.org/10.2307/2685478, 1998.
Holzinger, A., Saranti, A., Molnar, C., Biecek, P., and Samek, W.: Explainable AI Methods – A Brief Overview, in: xxAI – Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, 18 July 2020, Vienna, Austria, Revised and Extended Papers, edited by: Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.-R., and Samek, W., Springer International Publishing, Cham, 13–38, https://doi.org/10.1007/978-3-031-04083-2_2, 2022.
Hui, L. Y. W. and Binder, A.: BatchNorm Decomposition for Deep Neural Network Interpretation, Cham, Book Title: Advances in Computational Intelligence, 280–291, https://doi.org/10.1007/978-3-030-20518-8_24, 2019.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: Proceedings of the 32nd International Conference on Machine Learning, International Conference on Machine Learning, 448–456, 2015.
Jenkner, J., Sprenger, M., Schwenk, I., Schwierz, C., Dierer, S., and Leuenberger, D.: Detection and climatology of fronts in a high-resolution model reanalysis over the Alps, Met. Apps, 17, 1–18, https://doi.org/10.1002/met.142, 2010.
Justin, A. D., Willingham, C., McGovern, A., and Allen, J. T.: Toward Operational Real-Time Identification of Frontal Boundaries Using Machine Learning, Artif. Intell. Earth Syst., 2, e220052, https://doi.org/10.1175/AIES-D-22-0052.1, 2023.
Kapp-Schwoerer, L., Graubner, A., Kim, S., and Kashinath, K.: Spatio-temporal segmentation and tracking of weather patterns with light-weight Neural Networks, 34th Conf. on Neural Information Processing Systems, NeurIPS, Online, https://ai4earthscience.github.io/neurips-2020-workshop/papers/ai4earth_neurips_2020_55.pdf (last access: 13 February 2025), 2020.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, in 3rd International Conference on Learning Representations, edited by: Bengio, Y. and LeCun, Y., ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings, https://doi.org/10.48550/arXiv.1412.6980, 2015.
Kokhlikyan, N., Miglani, V., Martin, M., Wang, E., Alsallakh, B., Reynolds, J., Melnikov, A., Kliushkina, N., Araya, C., Yan, S., and Reblitz-Richardson, O.: Captum: A unified and generic model interpretability library for PyTorch, arXiv [preprint], https://doi.org/10.48550/arXiv.2009.07896, 2020.
Labe, Z. M. and Barnes, E. A.: Predicting Slowdowns in Decadal Climate Warming Trends With Explainable Neural Networks, Geophys. Res. Lett., 49, e2022GL098173, https://doi.org/10.1029/2022GL098173, 2022.
Lagerquist, R., McGovern, A., and Ii, D. J. G.: Deep Learning for Spatially Explicit Prediction of Synoptic-Scale Fronts, Weather Forecast., 34, 1137–1160, https://doi.org/10.1175/WAF-D-18-0183.1, 2019.
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., and Müller, K.-R.: Unmasking Clever Hans predictors and assessing what machines really learn, Nat. Commun., 10, 1096, https://doi.org/10.1038/s41467-019-08987-4, 2019.
Lawrence, Z. D. and Manney, G. L.: Characterizing Stratospheric Polar Vortex Variability With Computer Vision Techniques, J. Geophys. Res.-Atmos., 123, 1510–1535, https://doi.org/10.1002/2017JD027556, 2018.
LeCun, Y. A., Bottou, L., Orr, G. B., and Müller, K.-R.: Efficient BackProp, in: Neural Networks: Tricks of the Trade: Second Edition, edited by: Montavon, G., Orr, G. B., and Müller, K.-R., Springer, Berlin, Heidelberg, 9–48, https://doi.org/10.1007/978-3-642-35289-8_3, 2012.
Linardatos, P., Papastefanopoulos, V., and Kotsiantis, S.: Explainable AI: A Review of Machine Learning Interpretability Methods, Entropy, 23, 18, https://doi.org/10.3390/e23010018, 2021.
Liu, X., Deng, Z., and Yang, Y.: Recent progress in semantic image segmentation, Artif. Intell. Rev., 52, 1089–1106, https://doi.org/10.1007/s10462-018-9641-3, 2019.
Long, J., Shelhamer, E., and Darrell, T.: Fully convolutional networks for semantic segmentation, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440, https://doi.org/10.1109/CVPR.2015.7298965, 2015.
Lundberg, S. M. and Lee, S.-I.: A Unified Approach to Interpreting Model Predictions, in: Advances in Neural Information Processing Systems, 28, 4765–4774, 2017.
Mamalakis, A., Barnes, E. A., and Ebert-Uphoff, I.: Investigating the Fidelity of Explainable Artificial Intelligence Methods for Applications of Convolutional Neural Networks in Geoscience, Artif. Intell. Earth Syst., 1, e220012, https://doi.org/10.1175/AIES-D-22-0012.1, 2022.
Manakitsa, N., Maraslidis, G. S., Moysis, L., and Fragulis, G. F.: A Review of Machine Learning and Deep Learning for Object Detection, Semantic Segmentation, and Human Action Recognition in Machine and Robotic Vision, Technologies, 12, 15, https://doi.org/10.3390/technologies12020015, 2024.
MathWorks: Explore Semantic Segmentation Network Using Grad-CAM, https://de.mathworks.com/help/deeplearning/ug/explore-semantic-segmentation-network-using-gradcam.html, last access: 17 November 2023.
Mersha, M., Lam, K., Wood, J., AlShami, A. K., and Kalita, J.: Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction, Neurocomputing, 599, 128111, https://doi.org/10.1016/j.neucom.2024.128111, 2024.
Mittermaier, M., North, R., Semple, A., and Bullock, R.: Feature-Based Diagnostic Evaluation of Global NWP Forecasts, Mon. Weather Rev., 144, 3871–3893, https://doi.org/10.1175/MWR-D-15-0167.1, 2016.
Montavon, G., Binder, A., Lapuschkin, S., Samek, W., and Müller, K.-R.: Layer-Wise Relevance Propagation: An Overview, in: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, edited by: Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., and Müller, K.-R., Springer International Publishing, Cham, 193–209, https://doi.org/10.1007/978-3-030-28954-6_10, 2019.
Mulovhedzi, P. T., Rambuwani, G. T., Bopape, M.-J., Maisha, R., and Monama, N.: Model inter-comparison for short-range forecasts over the southern African domain, South Afr. J. Sci., 117, 1–12, https://doi.org/10.17159/sajs.2021/8581, 2021.
Narkhede, M. V., Bartakke, P. P., and Sutaone, M. S.: A review on weight initialization strategies for neural networks, Artif. Intell. Rev., 55, 291–322, https://doi.org/10.1007/s10462-021-10033-z, 2022.
Nellikkattil, A. B., O’Brien, T. A., Lemmon, D., Lee, J.-Y., and Chu, J.-E.: Scalable Feature Extraction and Tracking (SCAFET): A general framework for feature extraction from large climate datasets, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2023-592, 2023.
Neu, U., Akperov, M. G., Bellenbaum, N., Benestad, R., Blender, R., Caballero, R., Cocozza, A., Dacre, H. F., Feng, Y., Fraedrich, K., Grieger, J., Gulev, S., Hanley, J., Hewson, T., Inatsu, M., Keay, K., Kew, S. F., Kindem, I., Leckebusch, G. C., Liberato, M. L. R., Lionello, P., Mokhov, I. I., Pinto, J. G., Raible, C. C., Reale, M., Rudeva, I., Schuster, M., Simmonds, I., Sinclair, M., Sprenger, M., Tilinina, N. D., Trigo, I. F., Ulbrich, S., Ulbrich, U., Wang, X. L., and Wernli, H.: IMILAST: A Community Effort to Intercompare Extratropical Cyclone Detection and Tracking Algorithms, B. Am. Meteorol. Soc., 94, 529–547, https://doi.org/10.1175/BAMS-D-11-00154.1, 2013.
Niebler, S., Miltenberger, A., Schmidt, B., and Spichtinger, P.: Automated detection and classification of synoptic-scale fronts from atmospheric data grids, Weather Clim. Dynam., 3, 113–137, https://doi.org/10.5194/wcd-3-113-2022, 2022.
Pena-Ortiz, C., Gallego, D., Ribera, P., Ordonez, P., and Alvarez-Castro, M. D. C.: Observed trends in the global jet stream characteristics during the second half of the 20th century, J. Geophys. Res.-Atmos., 118, 2702–2713, https://doi.org/10.1002/jgrd.50305, 2013.
Prabhat, Kashinath, K., Mudigonda, M., Kim, S., Kapp-Schwoerer, L., Graubner, A., Karaismailoglu, E., von Kleist, L., Kurth, T., Greiner, A., Mahesh, A., Yang, K., Lewis, C., Chen, J., Lou, A., Chandran, S., Toms, B., Chapman, W., Dagon, K., Shields, C. A., O'Brien, T., Wehner, M., and Collins, W.: ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather, Geosci. Model Dev., 14, 107–124, https://doi.org/10.5194/gmd-14-107-2021, 2021.
Puri, K., Dietachmayer, G., Steinle, P., Dix, M., Rikus, L., Logan, L., Naughton, M., Tingwell, C., Xiao, Y., Barras, V., Bermous, I., Bowen, R., Deschamps, L., Franklin, C., Fraser, J., Glowacki, T., Harris, B., Lee, J., Le, T., and Engel, C.: Operational Implementation of the ACCESS Numerical Weather prediction Systems, Aust. Meteorol. Ocean., 63, 265–284, 2013.
Radke, T.: ClimateNet Dataset as used in “Explaining neural networks for detection of tropical cyclones and atmospheric rivers in gridded atmospheric simulation data”, Zenodo [data set], https://doi.org/10.5281/zenodo.14046402, 2024.
Radke, T., Fuchs, S., Wilms, C., Polkova, I., and Rautenhaus, M.: Code for the paper: “Explaining neural networks for detection of tropical cyclones and atmospheric rivers in gridded atmospheric simulation data”, Zenodo [code], https://doi.org/10.5281/zenodo.10892412, 2024.
Rahman, M. A. and Wang, Y.: Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation, in: Advances in Visual Computing, Cham, 234–244, https://doi.org/10.1007/978-3-319-50835-1_22, 2016.
Rautenhaus, M., Böttinger, M., Siemen, S., Hoffman, R., Kirby, R. M., Mirzargar, M., Röber, N., and Westermann, R.: Visualization in Meteorology – A Survey of Techniques and Tools for Data Analysis Tasks, IEEE Trans. Vis. Comput. Graph., 24, 3268–3296, https://doi.org/10.1109/TVCG.2017.2779501, 2018.
Ribeiro, M. T., Singh, S., and Guestrin, C.: “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 1135–1144, https://doi.org/10.1145/2939672.2939778, 2016.
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Rueckert, D. and Schnabel, J. A.: Model-Based and Data-Driven Strategies in Medical Image Computing, P. IEEE, 108, 110–124, https://doi.org/10.1109/JPROC.2019.2943836, 2020.
Russell, S. and Norvig, P.: Artificial Intelligence, Global Edition, 4th Edn., Pearson, Harlow, 1168 pp., ISBN-10 0134610997, ISBN-13 978-0134610993, 2021.
Saitoh, K.: Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation, Packt Publishing Ltd, 317 pp., ISBN 978-1-80020-613-7, 2021.
Saito, K., Fujita, T., Yamada, Y., Ishida, J., Kumagai, Y., Aranami, K., Ohmori, S., Nagasawa, R., Kumagai, S., Muroi, C., Kato, T., Eito, H., and Yamazaki, Y.: The Operational JMA Nonhydrostatic Mesoscale Model, Mon. Weather Rev., 134, 1266–1298, https://doi.org/10.1175/MWR3120.1, 2006.
Schemm, S., Rudeva, I., and Simmonds, I.: Extratropical fronts in the lower troposphere–global perspectives obtained from two automated methods, Q. J. Roy. Meteor. Soc., 141, 1686–1698, https://doi.org/10.1002/qj.2471, 2015.
Schittenkopf, C., Deco, G., and Brauer, W.: Two Strategies to Avoid Overfitting in Feedforward Networks, Neural Networks, 10, 505–516, https://doi.org/10.1016/S0893-6080(96)00086-X, 1997.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D.: Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization, in: 2017 IEEE International Conference on Computer Vision (ICCV), 618–626, https://doi.org/10.1109/ICCV.2017.74, 2017.
Shields, C. A., Rutz, J. J., Leung, L.-Y., Ralph, F. M., Wehner, M., Kawzenuk, B., Lora, J. M., McClenny, E., Osborne, T., Payne, A. E., Ullrich, P., Gershunov, A., Goldenson, N., Guan, B., Qian, Y., Ramos, A. M., Sarangi, C., Sellars, S., Gorodetskaya, I., Kashinath, K., Kurlin, V., Mahoney, K., Muszynski, G., Pierce, R., Subramanian, A. C., Tome, R., Waliser, D., Walton, D., Wick, G., Wilson, A., Lavers, D., Prabhat, Collow, A., Krishnan, H., Magnusdottir, G., and Nguyen, P.: Atmospheric River Tracking Method Intercomparison Project (ARTMIP): project goals and experimental design, Geosci. Model Dev., 11, 2455–2474, https://doi.org/10.5194/gmd-11-2455-2018, 2018.
Simonyan, K. and Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition, in: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings, https://doi.org/10.48550/arXiv.1409.1556, 2015.
Sprenger, M., Fragkoulidis, G., Binder, H., Croci-Maspoli, M., Graf, P., Grams, C. M., Knippertz, P., Madonna, E., Schemm, S., Škerlak, B., and Wernli, H.: Global Climatologies of Eulerian and Lagrangian Flow Features based on ERA-Interim, B. Am. Meteorol. Soc., 98, 1739–1748, https://doi.org/10.1175/BAMS-D-15-00299.1, 2017.
Stull, R.: Practical Meteorology: An Algebra-based Survey of Atmospheric Science, Univ. of British Columbia, 940 pp., ISBN-10 0888651767, ISBN-13 978-0888651761, 2017.
Tian, Y., Zhao, Y., Son, S.-W., Luo, J.-J., Oh, S.-G., and Wang, Y.: A Deep-Learning Ensemble Method to Detect Atmospheric Rivers and Its Application to Projected Changes in Precipitation Regime, J. Geophys. Res.-Atmos, 128, e2022JD037041, https://doi.org/10.1029/2022JD037041, 2023.
Tjoa, E., Guo, H., Lu, Y., and Guan, C.: Enhancing the Extraction of Interpretable Information for Ischemic Stroke Imaging from Deep Neural Networks, ArXiv [preprint], https://doi.org/10.48550/arXiv.1911.08136, 2019.
Toms, B. A., Barnes, E. A., and Ebert-Uphoff, I.: Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability, J. Adv. Model. Earth Sy., 12, e2019MS002002, https://doi.org/10.1029/2019MS002002, 2020.
Tory, K. J., Chand, S. S., Dare, R. A., and McBride, J. L.: The Development and Assessment of a Model-, Grid-, and Basin-Independent Tropical Cyclone Detection Scheme, J. Climate, 26, 5493–5507, https://doi.org/10.1175/JCLI-D-12-00510.1, 2013.
Wang, S., Zhou, T., and Bilmes, J.: Bias Also Matters: Bias Attribution for Deep Neural Network Explanation, in: Proceedings of the 36th International Conference on Machine Learning, International Conference on Machine Learning, 6659–6667, 2019.
Wehner, M. F., Reed, K. A., Li, F., Prabhat, Bacmeister, J., Chen, C.-T., Paciorek, C., Gleckler, P. J., Sperber, K. R., Collins, W. D., Gettelman, A., and Jablonowski, C.: The effect of horizontal resolution on simulation quality in the Community Atmospheric Model, CAM5.1, J. Adv. Model. Earth Sy., 6, 980–997, https://doi.org/10.1002/2013MS000276, 2014.
Wick, G. A., Neiman, P. J., and Ralph, F. M.: Description and Validation of an Automated Objective Technique for Identification and Characterization of the Integrated Water Vapor Signature of Atmospheric Rivers, IEEE T. Geosci. Remote, 51, 2166–2176, https://doi.org/10.1109/TGRS.2012.2211024, 2013.
Wu, T., Tang, S., Zhang, R., Cao, J., and Zhang, Y.: CGNet: A Light-Weight Context Guided Network for Semantic Segmentation, IEEE T. Image Process., 30, 1169–1179, https://doi.org/10.1109/TIP.2020.3042065, 2021.
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., and Luo, P.: SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Adv. Neur. In., 12077–12090, 2021.
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., and Torralba, A.: Scene Parsing through ADE20K Dataset, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 5122–5130, https://doi.org/10.1109/CVPR.2017.544, 2017.
Short summary
In our study, we built upon previous work to investigate the patterns artificial intelligence (AI) learns to detect atmospheric features like tropical cyclones (TCs) and atmospheric rivers (ARs). As primary objective, we adopt a method to explain the AI used and investigate the plausibility of learned patterns. We find that plausible patterns are learned for both TCs and ARs. Hence, the chosen method is very useful for gaining confidence in the AI-based detection of atmospheric features.
In our study, we built upon previous work to investigate the patterns artificial intelligence...
