Articles | Volume 15, issue 15
https://doi.org/10.5194/gmd-15-5967-2022
© Author(s) 2022. 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-15-5967-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
01 Aug 2022
Model description paper |
| 01 Aug 2022
| 01 Aug 2022
Rad-cGAN v1.0: Radar-based precipitation nowcasting model with conditional generative adversarial networks for multiple dam domains
Suyeon Choi
Department of Civil and Environmental Engineering, Yonsei University,
Seoul 03722, Korea
Department of Civil and Environmental Engineering, Yonsei University,
Seoul 03722, Korea
Related authors
No articles found.
Gab Abramowitz, Anna Ukkola, Sanaa Hobeichi, Jon Cranko Page, Mathew Lipson, Martin G. De Kauwe, Samuel Green, Claire Brenner, Jonathan Frame, Grey Nearing, Martyn Clark, Martin Best, Peter Anthoni, Gabriele Arduini, Souhail Boussetta, Silvia Caldararu, Kyeungwoo Cho, Matthias Cuntz, David Fairbairn, Craig R. Ferguson, Hyungjun Kim, Yeonjoo Kim, Jürgen Knauer, David Lawrence, Xiangzhong Luo, Sergey Malyshev, Tomoko Nitta, Jerome Ogee, Keith Oleson, Catherine Ottlé, Phillipe Peylin, Patricia de Rosnay, Heather Rumbold, Bob Su, Nicolas Vuichard, Anthony P. Walker, Xiaoni Wang-Faivre, Yunfei Wang, and Yijian Zeng
Biogeosciences, 21, 5517–5538, https://doi.org/10.5194/bg-21-5517-2024, https://doi.org/10.5194/bg-21-5517-2024, 2024
Short summary
Short summary
This paper evaluates land models – computer-based models that simulate ecosystem dynamics; land carbon, water, and energy cycles; and the role of land in the climate system. It uses machine learning and AI approaches to show that, despite the complexity of land models, they do not perform nearly as well as they could given the amount of information they are provided with about the prediction problem.
Hocheol Seo and Yeonjoo Kim
Geosci. Model Dev., 16, 4699–4713, https://doi.org/10.5194/gmd-16-4699-2023, https://doi.org/10.5194/gmd-16-4699-2023, 2023
Short summary
Short summary
Wildfire is a crucial factor in carbon and water fluxes on the Earth system. About 2.1 Pg of carbon is released into the atmosphere by wildfires annually. Because the fire processes are still limitedly represented in land surface models, we forced the daily GFED4 burned area into the land surface model over Alaska and Siberia. The results with the GFED4 burned area significantly improved the simulated carbon emissions and net ecosystem exchange compared to the default simulation.
Marcos Longo, Ryan G. Knox, David M. Medvigy, Naomi M. Levine, Michael C. Dietze, Yeonjoo Kim, Abigail L. S. Swann, Ke Zhang, Christine R. Rollinson, Rafael L. Bras, Steven C. Wofsy, and Paul R. Moorcroft
Geosci. Model Dev., 12, 4309–4346, https://doi.org/10.5194/gmd-12-4309-2019, https://doi.org/10.5194/gmd-12-4309-2019, 2019
Short summary
Short summary
Our paper describes the Ecosystem Demography model. This computer program calculates how plants and ground exchange heat, water, and carbon with the air, and how plants grow, reproduce and die in different climates. Most models simplify forests to an average big tree. We consider that tall, deep-rooted trees get more light and water than small plants, and that some plants can with shade and drought. This diversity helps us to better explain how plants live and interact with the atmosphere.
Marcos Longo, Ryan G. Knox, Naomi M. Levine, Abigail L. S. Swann, David M. Medvigy, Michael C. Dietze, Yeonjoo Kim, Ke Zhang, Damien Bonal, Benoit Burban, Plínio B. Camargo, Matthew N. Hayek, Scott R. Saleska, Rodrigo da Silva, Rafael L. Bras, Steven C. Wofsy, and Paul R. Moorcroft
Geosci. Model Dev., 12, 4347–4374, https://doi.org/10.5194/gmd-12-4347-2019, https://doi.org/10.5194/gmd-12-4347-2019, 2019
Short summary
Short summary
The Ecosystem Demography model calculates the fluxes of heat, water, and carbon between plants and ground and the air, and the life cycle of plants in different climates. To test if our calculations were reasonable, we compared our results with field and satellite measurements. Our model predicts well the extent of the Amazon forest, how much light forests absorb, and how much water forests release to the air. However, it must improve the tree growth rates and how fast dead plants decompose.
Muhammad Shafqat Mehboob, Yeonjoo Kim, Jaehyeong Lee, Myoung-Jin Um, Amir Erfanian, and Guiling Wang
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2019-319, https://doi.org/10.5194/hess-2019-319, 2019
Manuscript not accepted for further review
Hocheol Seo and Yeonjoo Kim
Geosci. Model Dev., 12, 457–472, https://doi.org/10.5194/gmd-12-457-2019, https://doi.org/10.5194/gmd-12-457-2019, 2019
Myoung-Jin Um, Yeonjoo Kim, Daeryong Park, and Jeongbin Kim
Hydrol. Earth Syst. Sci., 21, 4989–5007, https://doi.org/10.5194/hess-21-4989-2017, https://doi.org/10.5194/hess-21-4989-2017, 2017
Short summary
Short summary
This study aims to understand how different reference periods (i.e., calibration periods) of climate data for estimating the drought index influence regional drought assessments. Specifically, we investigate the influence of different reference periods on historical drought characteristics such as trends, frequency, intensity and spatial extents using the Standard Precipitation Evapotranspiration Index (SPEI) estimated from the two widely used global datasets.
Y. Kim, P. R. Moorcroft, I. Aleinov, M. J. Puma, and N. Y. Kiang
Geosci. Model Dev., 8, 3837–3865, https://doi.org/10.5194/gmd-8-3837-2015, https://doi.org/10.5194/gmd-8-3837-2015, 2015
Short summary
Short summary
The Ent Terrestrial Biosphere Model is a mixed-canopy dynamic global vegetation model developed specifically for coupling with land surface hydrology and general circulation models. This study describes the leaf phenology submodel implemented in the Ent TBM. We evaluate the performance in reproducing observed leaf seasonal growth as well as water and carbon fluxes for four plant functional types at five Fluxnet sites.
Related subject area
Hydrology
The global water resources and use model WaterGAP v2.2e: description and evaluation of modifications and new features
Generalised drought index: a novel multi-scale daily approach for drought assessment
Development and performance of a high-resolution surface wave and storm surge forecast model: application to a large lake
Deep dive into hydrologic simulations at global scale: harnessing the power of deep learning and physics-informed differentiable models (δHBV-globe1.0-hydroDL)
PyEt v1.3.1: a Python package for the estimation of potential evapotranspiration
Prediction of hysteretic matric potential dynamics using artificial intelligence: application of autoencoder neural networks
Regionalization in global hydrological models and its impact on runoff simulations: a case study using WaterGAP3 (v 1.0.0)
SERGHEI v2.0: introducing a performance-portable, high-performance three-dimensional variably-saturated subsurface flow solver (SERGHEI-RE)
STORM v.2: A simple, stochastic rainfall model for exploring the impacts of climate and climate change at and near the land surface in gauged watersheds
Fluvial flood inundation and socio-economic impact model based on open data
RoGeR v3.0.5 – a process-based hydrological toolbox model in Python
Coupling a large-scale glacier and hydrological model (OGGM v1.5.3 and CWatM V1.08) – towards an improved representation of mountain water resources in global assessments
An open-source refactoring of the Canadian Small Lakes Model for estimates of evaporation from medium-sized reservoirs
EvalHyd v0.1.2: a polyglot tool for the evaluation of deterministic and probabilistic streamflow predictions
Modelling water quantity and quality for integrated water cycle management with the Water Systems Integrated Modelling framework (WSIMOD) software
HGS-PDAF (version 1.0): a modular data assimilation framework for an integrated surface and subsurface hydrological model
Wflow_sbm v0.7.3, a spatially distributed hydrological model: from global data to local applications
Reservoir Assessment Tool version 3.0: a scalable and user-friendly software platform to mobilize the global water management community
HydroFATE (v1): a high-resolution contaminant fate model for the global river system
Validation of a new global irrigation scheme in the land surface model ORCHIDEE v2.2
GPEP v1.0: the Geospatial Probabilistic Estimation Package to support Earth science applications
GEMS v1.0: Generalizable Empirical Model of Snow Accumulation and Melt, based on daily snow mass changes in response to climate and topographic drivers
mesas.py v1.0: a flexible Python package for modeling solute transport and transit times using StorAge Selection functions
rSHUD v2.0: advancing the Simulator for Hydrologic Unstructured Domains and unstructured hydrological modeling in the R environment
GLOBGM v1.0: a parallel implementation of a 30 arcsec PCR-GLOBWB-MODFLOW global-scale groundwater model
Development of inter-grid-cell lateral unsaturated and saturated flow model in the E3SM Land Model (v2.0)
Selecting a conceptual hydrological model using Bayes' factors computed with Replica Exchange Hamiltonian Monte Carlo and Thermodynamic Integration
pyESDv1.0.1: an open-source Python framework for empirical-statistical downscaling of climate information
Representing the impact of Rhizophora mangroves on flow in a hydrodynamic model (COAWST_rh v1.0): the importance of three-dimensional root system structures
Dynamically weighted ensemble of geoscientific models via automated machine-learning-based classification
Enhancing the representation of water management in global hydrological models
NEOPRENE v1.0.1: a Python library for generating spatial rainfall based on the Neyman–Scott process
Uncertainty estimation for a new exponential-filter-based long-term root-zone soil moisture dataset from Copernicus Climate Change Service (C3S) surface observations
Validating the Nernst–Planck transport model under reaction-driven flow conditions using RetroPy v1.0
DynQual v1.0: a high-resolution global surface water quality model
Data space inversion for efficient uncertainty quantification using an integrated surface and sub-surface hydrologic model
Simulation of crop yield using the global hydrological model H08 (crp.v1)
How is a global sensitivity analysis of a catchment-scale, distributed pesticide transfer model performed? Application to the PESHMELBA model
iHydroSlide3D v1.0: an advanced hydrological–geotechnical model for hydrological simulation and three-dimensional landslide prediction
GEB v0.1: a large-scale agent-based socio-hydrological model – simulating 10 million individual farming households in a fully distributed hydrological model
Tracing and visualisation of contributing water sources in the LISFLOOD-FP model of flood inundation (within CAESAR-Lisflood version 1.9j-WS)
Continental-scale evaluation of a fully distributed coupled land surface and groundwater model, ParFlow-CLM (v3.6.0), over Europe
Evaluating a global soil moisture dataset from a multitask model (GSM3 v1.0) with potential applications for crop threats
SERGHEI (SERGHEI-SWE) v1.0: a performance-portable high-performance parallel-computing shallow-water solver for hydrology and environmental hydraulics
A simple, efficient, mass-conservative approach to solving Richards' equation (openRE, v1.0)
Customized deep learning for precipitation bias correction and downscaling
Implementation and sensitivity analysis of the Dam-Reservoir OPeration model (DROP v1.0) over Spain
Regional coupled surface–subsurface hydrological model fitting based on a spatially distributed minimalist reduction of frequency domain discharge data
Operational water forecast ability of the HRRR-iSnobal combination: an evaluation to adapt into production environments
Prediction of algal blooms via data-driven machine learning models: an evaluation using data from a well-monitored mesotrophic lake
Hannes Müller Schmied, Tim Trautmann, Sebastian Ackermann, Denise Cáceres, Martina Flörke, Helena Gerdener, Ellen Kynast, Thedini Asali Peiris, Leonie Schiebener, Maike Schumacher, and Petra Döll
Geosci. Model Dev., 17, 8817–8852, https://doi.org/10.5194/gmd-17-8817-2024, https://doi.org/10.5194/gmd-17-8817-2024, 2024
Short summary
Short summary
Assessing water availability and water use at the global scale is challenging but essential for a range of purposes. We describe the newest version of the global hydrological model WaterGAP, which has been used for numerous water resource assessments since 1996. We show the effects of new model features, as well as model evaluations, against water abstraction statistics and observed streamflow and water storage anomalies. The publicly available model output for several variants is described.
João António Martins Careto, Rita Margarida Cardoso, Ana Russo, Daniela Catarina André Lima, and Pedro Miguel Matos Soares
Geosci. Model Dev., 17, 8115–8139, https://doi.org/10.5194/gmd-17-8115-2024, https://doi.org/10.5194/gmd-17-8115-2024, 2024
Short summary
Short summary
This study proposes a new daily drought index, the generalised drought index (GDI). The GDI not only identifies the same events as established indices but is also capable of improving their results. The index is empirically based and easy to compute, not requiring fitting the data to a probability distribution. The GDI can detect flash droughts and longer-term events, making it a versatile tool for drought monitoring.
Laura L. Swatridge, Ryan P. Mulligan, Leon Boegman, and Shiliang Shan
Geosci. Model Dev., 17, 7751–7766, https://doi.org/10.5194/gmd-17-7751-2024, https://doi.org/10.5194/gmd-17-7751-2024, 2024
Short summary
Short summary
We develop an operational forecast system, Coastlines-LO, that can simulate water levels and surface waves in Lake Ontario driven by forecasts of wind speeds and pressure fields from an atmospheric model. The model has relatively low computational requirements, and results compare well with near-real-time observations, as well as with results from other existing forecast systems. Results show that with shorter forecast lengths, storm surge and wave predictions can improve in accuracy.
Dapeng Feng, Hylke Beck, Jens de Bruijn, Reetik Kumar Sahu, Yusuke Satoh, Yoshihide Wada, Jiangtao Liu, Ming Pan, Kathryn Lawson, and Chaopeng Shen
Geosci. Model Dev., 17, 7181–7198, https://doi.org/10.5194/gmd-17-7181-2024, https://doi.org/10.5194/gmd-17-7181-2024, 2024
Short summary
Short summary
Accurate hydrologic modeling is vital to characterizing water cycle responses to climate change. For the first time at this scale, we use differentiable physics-informed machine learning hydrologic models to simulate rainfall–runoff processes for 3753 basins around the world and compare them with purely data-driven and traditional modeling approaches. This sets a benchmark for hydrologic estimates around the world and builds foundations for improving global hydrologic simulations.
Matevž Vremec, Raoul A. Collenteur, and Steffen Birk
Geosci. Model Dev., 17, 7083–7103, https://doi.org/10.5194/gmd-17-7083-2024, https://doi.org/10.5194/gmd-17-7083-2024, 2024
Short summary
Short summary
Geoscientists commonly use various potential evapotranpiration (PET) formulas for environmental studies, which can be prone to errors and sensitive to climate change. PyEt, a tested and open-source Python package, simplifies the application of 20 PET methods for both time series and gridded data, ensuring accurate and consistent PET estimations suitable for a wide range of environmental applications.
Nedal Aqel, Lea Reusser, Stephan Margreth, Andrea Carminati, and Peter Lehmann
Geosci. Model Dev., 17, 6949–6966, https://doi.org/10.5194/gmd-17-6949-2024, https://doi.org/10.5194/gmd-17-6949-2024, 2024
Short summary
Short summary
The soil water potential (SWP) determines various soil water processes. Since remote sensing techniques cannot measure it directly, it is often deduced from volumetric water content (VWC) information. However, under dynamic field conditions, the relationship between SWP and VWC is highly ambiguous due to different factors that cannot be modeled with the classical approach. Applying a deep neural network with an autoencoder enables the prediction of the dynamic SWP.
Jenny Kupzig, Nina Kupzig, and Martina Flörke
Geosci. Model Dev., 17, 6819–6846, https://doi.org/10.5194/gmd-17-6819-2024, https://doi.org/10.5194/gmd-17-6819-2024, 2024
Short summary
Short summary
Valid simulation results from global hydrological models (GHMs) are essential, e.g., to studying climate change impacts. Adapting GHMs to ungauged basins requires regionalization, enabling valid simulations. In this study, we highlight the impact of regionalization of GHMs on runoff simulations using an ensemble of regionalization methods for WaterGAP3. We have found that regionalization leads to temporally and spatially varying uncertainty, potentially reaching up to inter-model differences.
Zhi Li, Gregor Rickert, Na Zheng, Zhibo Zhang, Ilhan Özgen-Xian, and Daniel Caviedes-Voullième
EGUsphere, https://doi.org/10.5194/egusphere-2024-2588, https://doi.org/10.5194/egusphere-2024-2588, 2024
Short summary
Short summary
We introduce SERGHEI-RE, a 3D subsurface flow simulator with performance-portable parallel computing capabilities. SERGHEI-RE performs effectively on various computational devices, from personal computers to advanced clusters. It allows users to solve flow equations with multiple numerical schemes, making it adaptable to various hydrological scenarios. Testing results show its accuracy and performance, confirming that SERGHEI-RE is a powerful tool for hydrological research.
Manuel F. Rios Gaona, Katerina Michaelides, and Michael Bliss Singer
Geosci. Model Dev., 17, 5387–5412, https://doi.org/10.5194/gmd-17-5387-2024, https://doi.org/10.5194/gmd-17-5387-2024, 2024
Short summary
Short summary
STORM v.2 (short for STOchastic Rainfall Model version 2.0) is an open-source and user-friendly modelling framework for simulating rainfall fields over a basin. It also allows simulating the impact of plausible climate change either on the total seasonal rainfall or the storm’s maximum intensity.
Lukas Riedel, Thomas Röösli, Thomas Vogt, and David N. Bresch
Geosci. Model Dev., 17, 5291–5308, https://doi.org/10.5194/gmd-17-5291-2024, https://doi.org/10.5194/gmd-17-5291-2024, 2024
Short summary
Short summary
River floods are among the most devastating natural hazards. We propose a flood model with a statistical approach based on openly available data. The model is integrated in a framework for estimating impacts of physical hazards. Although the model only agrees moderately with satellite-detected flood extents, we show that it can be used for forecasting the magnitude of flood events in terms of socio-economic impacts and for comparing these with past events.
Robin Schwemmle, Hannes Leistert, Andreas Steinbrich, and Markus Weiler
Geosci. Model Dev., 17, 5249–5262, https://doi.org/10.5194/gmd-17-5249-2024, https://doi.org/10.5194/gmd-17-5249-2024, 2024
Short summary
Short summary
The new process-based hydrological toolbox model, RoGeR (https://roger.readthedocs.io/), can be used to estimate the components of the hydrological cycle and the related travel times of pollutants through parts of the hydrological cycle. These estimations may contribute to effective water resources management. This paper presents the toolbox concept and provides a simple example of providing estimations to water resources management.
Sarah Hanus, Lilian Schuster, Peter Burek, Fabien Maussion, Yoshihide Wada, and Daniel Viviroli
Geosci. Model Dev., 17, 5123–5144, https://doi.org/10.5194/gmd-17-5123-2024, https://doi.org/10.5194/gmd-17-5123-2024, 2024
Short summary
Short summary
This study presents a coupling of the large-scale glacier model OGGM and the hydrological model CWatM. Projected future increase in discharge is less strong while future decrease in discharge is stronger when glacier runoff is explicitly included in the large-scale hydrological model. This is because glacier runoff is projected to decrease in nearly all basins. We conclude that an improved glacier representation can prevent underestimating future discharge changes in large river basins.
M. Graham Clark and Sean K. Carey
Geosci. Model Dev., 17, 4911–4922, https://doi.org/10.5194/gmd-17-4911-2024, https://doi.org/10.5194/gmd-17-4911-2024, 2024
Short summary
Short summary
This paper provides validation of the Canadian Small Lakes Model (CSLM) for estimating evaporation rates from reservoirs and a refactoring of the original FORTRAN code into MATLAB and Python, which are now stored in GitHub repositories. Here we provide direct observations of the surface energy exchange obtained with an eddy covariance system to validate the CSLM. There was good agreement between observations and estimations except under specific atmospheric conditions when evaporation is low.
Thibault Hallouin, François Bourgin, Charles Perrin, Maria-Helena Ramos, and Vazken Andréassian
Geosci. Model Dev., 17, 4561–4578, https://doi.org/10.5194/gmd-17-4561-2024, https://doi.org/10.5194/gmd-17-4561-2024, 2024
Short summary
Short summary
The evaluation of the quality of hydrological model outputs against streamflow observations is widespread in the hydrological literature. In order to improve on the reproducibility of published studies, a new evaluation tool dedicated to hydrological applications is presented. It is open source and usable in a variety of programming languages to make it as accessible as possible to the community. Thus, authors and readers alike can use the same tool to produce and reproduce the results.
Barnaby Dobson, Leyang Liu, and Ana Mijic
Geosci. Model Dev., 17, 4495–4513, https://doi.org/10.5194/gmd-17-4495-2024, https://doi.org/10.5194/gmd-17-4495-2024, 2024
Short summary
Short summary
Water management is challenging when models don't capture the entire water cycle. We propose that using integrated models facilitates management and improves understanding. We introduce a software tool designed for this task. We discuss its foundation, how it simulates water system components and their interactions, and its customisation. We provide a flexible way to represent water systems, and we hope it will inspire more research and practical applications for sustainable water management.
Qi Tang, Hugo Delottier, Wolfgang Kurtz, Lars Nerger, Oliver S. Schilling, and Philip Brunner
Geosci. Model Dev., 17, 3559–3578, https://doi.org/10.5194/gmd-17-3559-2024, https://doi.org/10.5194/gmd-17-3559-2024, 2024
Short summary
Short summary
We have developed a new data assimilation framework by coupling an integrated hydrological model HydroGeoSphere with the data assimilation software PDAF. Compared to existing hydrological data assimilation systems, the advantage of our newly developed framework lies in its consideration of the physically based model; its large selection of different assimilation algorithms; and its modularity with respect to the combination of different types of observations, states and parameters.
Willem J. van Verseveld, Albrecht H. Weerts, Martijn Visser, Joost Buitink, Ruben O. Imhoff, Hélène Boisgontier, Laurène Bouaziz, Dirk Eilander, Mark Hegnauer, Corine ten Velden, and Bobby Russell
Geosci. Model Dev., 17, 3199–3234, https://doi.org/10.5194/gmd-17-3199-2024, https://doi.org/10.5194/gmd-17-3199-2024, 2024
Short summary
Short summary
We present the wflow_sbm distributed hydrological model, recently released by Deltares, as part of the Wflow.jl open-source modelling framework in the programming language Julia. Wflow_sbm has a fast runtime, making it suitable for large-scale modelling. Wflow_sbm models can be set a priori for any catchment with the Python tool HydroMT-Wflow based on globally available datasets, which results in satisfactory to good performance (without much tuning). We show this for a number of specific cases.
Sanchit Minocha, Faisal Hossain, Pritam Das, Sarath Suresh, Shahzaib Khan, George Darkwah, Hyongki Lee, Stefano Galelli, Konstantinos Andreadis, and Perry Oddo
Geosci. Model Dev., 17, 3137–3156, https://doi.org/10.5194/gmd-17-3137-2024, https://doi.org/10.5194/gmd-17-3137-2024, 2024
Short summary
Short summary
The Reservoir Assessment Tool (RAT) merges satellite data with hydrological models, enabling robust estimation of reservoir parameters like inflow, outflow, surface area, and storage changes around the world. Version 3.0 of RAT lowers the barrier of entry for new users and achieves scalability and computational efficiency. RAT 3.0 also facilitates open-source development of functions for continuous improvement to mobilize and empower the global water management community.
Heloisa Ehalt Macedo, Bernhard Lehner, Jim Nicell, and Günther Grill
Geosci. Model Dev., 17, 2877–2899, https://doi.org/10.5194/gmd-17-2877-2024, https://doi.org/10.5194/gmd-17-2877-2024, 2024
Short summary
Short summary
Treated and untreated wastewaters are sources of contaminants of emerging concern. HydroFATE, a new global model, estimates their concentrations in surface waters, identifying streams that are most at risk and guiding monitoring/mitigation efforts to safeguard aquatic ecosystems and human health. Model predictions were validated against field measurements of the antibiotic sulfamethoxazole, with predicted concentrations exceeding ecological thresholds in more than 400 000 km of rivers worldwide.
Pedro Felipe Arboleda-Obando, Agnès Ducharne, Zun Yin, and Philippe Ciais
Geosci. Model Dev., 17, 2141–2164, https://doi.org/10.5194/gmd-17-2141-2024, https://doi.org/10.5194/gmd-17-2141-2024, 2024
Short summary
Short summary
We show a new irrigation scheme included in the ORCHIDEE land surface model. The new irrigation scheme restrains irrigation due to water shortage, includes water adduction, and represents environmental limits and facilities to access water, due to representing infrastructure in a simple way. Our results show that the new irrigation scheme helps simulate acceptable land surface conditions and fluxes in irrigated areas, even if there are difficulties due to shortcomings and limited information.
Guoqiang Tang, Andrew W. Wood, Andrew J. Newman, Martyn P. Clark, and Simon Michael Papalexiou
Geosci. Model Dev., 17, 1153–1173, https://doi.org/10.5194/gmd-17-1153-2024, https://doi.org/10.5194/gmd-17-1153-2024, 2024
Short summary
Short summary
Ensemble geophysical datasets are crucial for understanding uncertainties and supporting probabilistic estimation/prediction. However, open-access tools for creating these datasets are limited. We have developed the Python-based Geospatial Probabilistic Estimation Package (GPEP). Through several experiments, we demonstrate GPEP's ability to estimate precipitation, temperature, and snow water equivalent. GPEP will be a useful tool to support uncertainty analysis in Earth science applications.
Atabek Umirbekov, Richard Essery, and Daniel Müller
Geosci. Model Dev., 17, 911–929, https://doi.org/10.5194/gmd-17-911-2024, https://doi.org/10.5194/gmd-17-911-2024, 2024
Short summary
Short summary
We present a parsimonious snow model which simulates snow mass without the need for extensive calibration. The model is based on a machine learning algorithm that has been trained on diverse set of daily observations of snow accumulation or melt, along with corresponding climate and topography data. We validated the model using in situ data from numerous new locations. The model provides a promising solution for accurate snow mass estimation across regions where in situ data are limited.
Ciaran J. Harman and Esther Xu Fei
Geosci. Model Dev., 17, 477–495, https://doi.org/10.5194/gmd-17-477-2024, https://doi.org/10.5194/gmd-17-477-2024, 2024
Short summary
Short summary
Over the last 10 years, scientists have developed StorAge Selection: a new way of modeling how material is transported through complex systems. Here, we present some new, easy-to-use, flexible, and very accurate code for implementing this method. We show that, in cases where we know exactly what the answer should be, our code gets the right answer. We also show that our code is closer than some other codes to the right answer in an important way: it conserves mass.
Lele Shu, Paul Ullrich, Xianhong Meng, Christopher Duffy, Hao Chen, and Zhaoguo Li
Geosci. Model Dev., 17, 497–527, https://doi.org/10.5194/gmd-17-497-2024, https://doi.org/10.5194/gmd-17-497-2024, 2024
Short summary
Short summary
Our team developed rSHUD v2.0, a toolkit that simplifies the use of the SHUD, a model simulating water movement in the environment. We demonstrated its effectiveness in two watersheds, one in the USA and one in China. The toolkit also facilitated the creation of the Global Hydrological Data Cloud, a platform for automatic data processing and model deployment, marking a significant advancement in hydrological research.
Jarno Verkaik, Edwin H. Sutanudjaja, Gualbert H. P. Oude Essink, Hai Xiang Lin, and Marc F. P. Bierkens
Geosci. Model Dev., 17, 275–300, https://doi.org/10.5194/gmd-17-275-2024, https://doi.org/10.5194/gmd-17-275-2024, 2024
Short summary
Short summary
This paper presents the parallel PCR-GLOBWB global-scale groundwater model at 30 arcsec resolution (~1 km at the Equator). Named GLOBGM v1.0, this model is a follow-up of the 5 arcmin (~10 km) model, aiming for a higher-resolution simulation of worldwide fresh groundwater reserves under climate change and excessive pumping. For a long transient simulation using a parallel prototype of MODFLOW 6, we show that our implementation is efficient for a relatively low number of processor cores.
Han Qiu, Gautam Bisht, Lingcheng Li, Dalei Hao, and Donghui Xu
Geosci. Model Dev., 17, 143–167, https://doi.org/10.5194/gmd-17-143-2024, https://doi.org/10.5194/gmd-17-143-2024, 2024
Short summary
Short summary
We developed and validated an inter-grid-cell lateral groundwater flow model for both saturated and unsaturated zone in the ELMv2.0 framework. The developed model was benchmarked against PFLOTRAN, a 3D subsurface flow and transport model and showed comparable performance with PFLOTRAN. The developed model was also applied to the Little Washita experimental watershed. The spatial pattern of simulated groundwater table depth agreed well with the global groundwater table benchmark dataset.
Damian N. Mingo, Remko Nijzink, Christophe Ley, and Jack S. Hale
EGUsphere, https://doi.org/10.5194/egusphere-2023-2865, https://doi.org/10.5194/egusphere-2023-2865, 2024
Short summary
Short summary
Hydrologists are often faced with selecting amongst a set of competing models with different numbers of parameters and ability to fit available data. The Bayes’ factor is a tool that can be used to compare models, however it is very difficult to compute the Bayes’ factor numerically. In our paper we explore and develop highly efficient algorithms for computing the Bayes’ factor of hydrological systems, which will bring this useful tool for selecting models to everyday hydrological practice.
Daniel Boateng and Sebastian G. Mutz
Geosci. Model Dev., 16, 6479–6514, https://doi.org/10.5194/gmd-16-6479-2023, https://doi.org/10.5194/gmd-16-6479-2023, 2023
Short summary
Short summary
We present an open-source Python framework for performing empirical-statistical downscaling of climate information, such as precipitation. The user-friendly package comprises all the downscaling cycles including data preparation, model selection, training, and evaluation, designed in an efficient and flexible manner, allowing for quick and reproducible downscaling products. The framework would contribute to climate change impact assessments by generating accurate high-resolution climate data.
Masaya Yoshikai, Takashi Nakamura, Eugene C. Herrera, Rempei Suwa, Rene Rollon, Raghab Ray, Keita Furukawa, and Kazuo Nadaoka
Geosci. Model Dev., 16, 5847–5863, https://doi.org/10.5194/gmd-16-5847-2023, https://doi.org/10.5194/gmd-16-5847-2023, 2023
Short summary
Short summary
Due to complex root system structures, representing the impacts of Rhizophora mangroves on flow in hydrodynamic models has been challenging. This study presents a new drag and turbulence model that leverages an empirical model for root systems. The model can be applied without rigorous measurements of root structures and showed high performance in flow simulations; this may provide a better understanding of hydrodynamics and related transport processes in Rhizophora mangrove forests.
Hao Chen, Tiejun Wang, Yonggen Zhang, Yun Bai, and Xi Chen
Geosci. Model Dev., 16, 5685–5701, https://doi.org/10.5194/gmd-16-5685-2023, https://doi.org/10.5194/gmd-16-5685-2023, 2023
Short summary
Short summary
Effectively assembling multiple models for approaching a benchmark solution remains a long-standing issue for various geoscience domains. We here propose an automated machine learning-assisted ensemble framework (AutoML-Ens) that attempts to resolve this challenge. Results demonstrate the great potential of AutoML-Ens for improving estimations due to its two unique features, i.e., assigning dynamic weights for candidate models and taking full advantage of AutoML-assisted workflow.
Guta Wakbulcho Abeshu, Fuqiang Tian, Thomas Wild, Mengqi Zhao, Sean Turner, A. F. M. Kamal Chowdhury, Chris R. Vernon, Hongchang Hu, Yuan Zhuang, Mohamad Hejazi, and Hong-Yi Li
Geosci. Model Dev., 16, 5449–5472, https://doi.org/10.5194/gmd-16-5449-2023, https://doi.org/10.5194/gmd-16-5449-2023, 2023
Short summary
Short summary
Most existing global hydrologic models do not explicitly represent hydropower reservoirs. We are introducing a new water management module to Xanthos that distinguishes between the operational characteristics of irrigation, hydropower, and flood control reservoirs. We show that this explicit representation of hydropower reservoirs can lead to a significantly more realistic simulation of reservoir storage and releases in over 44 % of the hydropower reservoirs included in this study.
Javier Diez-Sierra, Salvador Navas, and Manuel del Jesus
Geosci. Model Dev., 16, 5035–5048, https://doi.org/10.5194/gmd-16-5035-2023, https://doi.org/10.5194/gmd-16-5035-2023, 2023
Short summary
Short summary
NEOPRENE is an open-source, freely available library allowing scientists and practitioners to generate synthetic time series and maps of rainfall. These outputs will help to explore plausible events that were never observed in the past but may occur in the near future and to generate possible future events under climate change conditions. The paper shows how to use the library to downscale daily precipitation and how to use synthetic generation to improve our characterization of extreme events.
Adam Pasik, Alexander Gruber, Wolfgang Preimesberger, Domenico De Santis, and Wouter Dorigo
Geosci. Model Dev., 16, 4957–4976, https://doi.org/10.5194/gmd-16-4957-2023, https://doi.org/10.5194/gmd-16-4957-2023, 2023
Short summary
Short summary
We apply the exponential filter (EF) method to satellite soil moisture retrievals to estimate the water content in the unobserved root zone globally from 2002–2020. Quality assessment against an independent dataset shows satisfactory results. Error characterization is carried out using the standard uncertainty propagation law and empirically estimated values of EF model structural uncertainty and parameter uncertainty. This is followed by analysis of temporal uncertainty variations.
Po-Wei Huang, Bernd Flemisch, Chao-Zhong Qin, Martin O. Saar, and Anozie Ebigbo
Geosci. Model Dev., 16, 4767–4791, https://doi.org/10.5194/gmd-16-4767-2023, https://doi.org/10.5194/gmd-16-4767-2023, 2023
Short summary
Short summary
Water in natural environments consists of many ions. Ions are electrically charged and exert electric forces on each other. We discuss whether the electric forces are relevant in describing mixing and reaction processes in natural environments. By comparing our computer simulations to lab experiments in literature, we show that the electric interactions between ions can play an essential role in mixing and reaction processes, in which case they should not be neglected in numerical modeling.
Edward R. Jones, Marc F. P. Bierkens, Niko Wanders, Edwin H. Sutanudjaja, Ludovicus P. H. van Beek, and Michelle T. H. van Vliet
Geosci. Model Dev., 16, 4481–4500, https://doi.org/10.5194/gmd-16-4481-2023, https://doi.org/10.5194/gmd-16-4481-2023, 2023
Short summary
Short summary
DynQual is a new high-resolution global water quality model for simulating total dissolved solids, biological oxygen demand and fecal coliform as indicators of salinity, organic pollution and pathogen pollution, respectively. Output data from DynQual can supplement the observational record of water quality data, which is highly fragmented across space and time, and has the potential to inform assessments in a broad range of fields including ecological, human health and water scarcity studies.
Hugo Delottier, John Doherty, and Philip Brunner
Geosci. Model Dev., 16, 4213–4231, https://doi.org/10.5194/gmd-16-4213-2023, https://doi.org/10.5194/gmd-16-4213-2023, 2023
Short summary
Short summary
Long run times are usually a barrier to the quantification and reduction of predictive uncertainty with complex hydrological models. Data space inversion (DSI) provides an alternative and highly model-run-efficient method for uncertainty quantification. This paper demonstrates DSI's ability to robustly quantify predictive uncertainty and extend the methodology to provide practical metrics that can guide data acquisition and analysis to achieve goals of decision-support modelling.
Zhipin Ai and Naota Hanasaki
Geosci. Model Dev., 16, 3275–3290, https://doi.org/10.5194/gmd-16-3275-2023, https://doi.org/10.5194/gmd-16-3275-2023, 2023
Short summary
Short summary
Simultaneously simulating food production and the requirements and availability of water resources in a spatially explicit manner within a single framework remains challenging on a global scale. Here, we successfully enhanced the global hydrological model H08 that considers human water use and management to simulate the yields of four major staple crops: maize, wheat, rice, and soybean. Our improved model will be beneficial for advancing global food–water nexus studies in the future.
Emilie Rouzies, Claire Lauvernet, Bruno Sudret, and Arthur Vidard
Geosci. Model Dev., 16, 3137–3163, https://doi.org/10.5194/gmd-16-3137-2023, https://doi.org/10.5194/gmd-16-3137-2023, 2023
Short summary
Short summary
Water and pesticide transfer models are complex and should be simplified to be used in decision support. Indeed, these models simulate many spatial processes in interaction, involving a large number of parameters. Sensitivity analysis allows us to select the most influential input parameters, but it has to be adapted to spatial modelling. This study will identify relevant methods that can be transposed to any hydrological and water quality model and improve the fate of pesticide knowledge.
Guoding Chen, Ke Zhang, Sheng Wang, Yi Xia, and Lijun Chao
Geosci. Model Dev., 16, 2915–2937, https://doi.org/10.5194/gmd-16-2915-2023, https://doi.org/10.5194/gmd-16-2915-2023, 2023
Short summary
Short summary
In this study, we developed a novel modeling system called iHydroSlide3D v1.0 by coupling a modified a 3D landslide model with a distributed hydrology model. The model is able to apply flexibly different simulating resolutions for hydrological and slope stability submodules and gain a high computational efficiency through parallel computation. The test results in the Yuehe River basin, China, show a good predicative capability for cascading flood–landslide events.
Jens A. de Bruijn, Mikhail Smilovic, Peter Burek, Luca Guillaumot, Yoshihide Wada, and Jeroen C. J. H. Aerts
Geosci. Model Dev., 16, 2437–2454, https://doi.org/10.5194/gmd-16-2437-2023, https://doi.org/10.5194/gmd-16-2437-2023, 2023
Short summary
Short summary
We present a computer simulation model of the hydrological system and human system, which can simulate the behaviour of individual farmers and their interactions with the water system at basin scale to assess how the systems have evolved and are projected to evolve in the future. For example, we can simulate the effect of subsidies provided on investment in adaptation measures and subsequent effects in the hydrological system, such as a lowering of the groundwater table or reservoir level.
Matthew D. Wilson and Thomas J. Coulthard
Geosci. Model Dev., 16, 2415–2436, https://doi.org/10.5194/gmd-16-2415-2023, https://doi.org/10.5194/gmd-16-2415-2023, 2023
Short summary
Short summary
During flooding, the sources of water that inundate a location can influence impacts such as pollution. However, methods to trace water sources in flood events are currently only available in complex, computationally expensive hydraulic models. We propose a simplified method which can be added to efficient, reduced-complexity model codes, enabling an improved understanding of flood dynamics and its impacts. We demonstrate its application for three sites at a range of spatial and temporal scales.
Bibi S. Naz, Wendy Sharples, Yueling Ma, Klaus Goergen, and Stefan Kollet
Geosci. Model Dev., 16, 1617–1639, https://doi.org/10.5194/gmd-16-1617-2023, https://doi.org/10.5194/gmd-16-1617-2023, 2023
Short summary
Short summary
It is challenging to apply a high-resolution integrated land surface and groundwater model over large spatial scales. In this paper, we demonstrate the application of such a model over a pan-European domain at 3 km resolution and perform an extensive evaluation of simulated water states and fluxes by comparing with in situ and satellite data. This study can serve as a benchmark and baseline for future studies of climate change impact projections and for hydrological forecasting.
Jiangtao Liu, David Hughes, Farshid Rahmani, Kathryn Lawson, and Chaopeng Shen
Geosci. Model Dev., 16, 1553–1567, https://doi.org/10.5194/gmd-16-1553-2023, https://doi.org/10.5194/gmd-16-1553-2023, 2023
Short summary
Short summary
Under-monitored regions like Africa need high-quality soil moisture predictions to help with food production, but it is not clear if soil moisture processes are similar enough around the world for data-driven models to maintain accuracy. We present a deep-learning-based soil moisture model that learns from both in situ data and satellite data and performs better than satellite products at the global scale. These results help us apply our model globally while better understanding its limitations.
Daniel Caviedes-Voullième, Mario Morales-Hernández, Matthew R. Norman, and Ilhan Özgen-Xian
Geosci. Model Dev., 16, 977–1008, https://doi.org/10.5194/gmd-16-977-2023, https://doi.org/10.5194/gmd-16-977-2023, 2023
Short summary
Short summary
This paper introduces the SERGHEI framework and a solver for shallow-water problems. Such models, often used for surface flow and flood modelling, are computationally intense. In recent years the trends to increase computational power have changed, requiring models to adapt to new hardware and new software paradigms. SERGHEI addresses these challenges, allowing surface flow simulation to be enabled on the newest and upcoming consumer hardware and supercomputers very efficiently.
Andrew M. Ireson, Raymond J. Spiteri, Martyn P. Clark, and Simon A. Mathias
Geosci. Model Dev., 16, 659–677, https://doi.org/10.5194/gmd-16-659-2023, https://doi.org/10.5194/gmd-16-659-2023, 2023
Short summary
Short summary
Richards' equation (RE) is used to describe the movement and storage of water in a soil profile and is a component of many hydrological and earth-system models. Solving RE numerically is challenging due to the non-linearities in the properties. Here, we present a simple but effective and mass-conservative solution to solving RE, which is ideal for teaching/learning purposes but also useful in prototype models that are used to explore alternative process representations.
Fang Wang, Di Tian, and Mark Carroll
Geosci. Model Dev., 16, 535–556, https://doi.org/10.5194/gmd-16-535-2023, https://doi.org/10.5194/gmd-16-535-2023, 2023
Short summary
Short summary
Gridded precipitation datasets suffer from biases and coarse resolutions. We developed a customized deep learning (DL) model to bias-correct and downscale gridded precipitation data using radar observations. The results showed that the customized DL model can generate improved precipitation at fine resolutions where regular DL and statistical methods experience challenges. The new model can be used to improve precipitation estimates, especially for capturing extremes at smaller scales.
Malak Sadki, Simon Munier, Aaron Boone, and Sophie Ricci
Geosci. Model Dev., 16, 427–448, https://doi.org/10.5194/gmd-16-427-2023, https://doi.org/10.5194/gmd-16-427-2023, 2023
Short summary
Short summary
Predicting water resource evolution is a key challenge for the coming century.
Anthropogenic impacts on water resources, and particularly the effects of dams and reservoirs on river flows, are still poorly known and generally neglected in global hydrological studies. A parameterized reservoir model is reproduced to compute monthly releases in Spanish anthropized river basins. For global application, an exhaustive sensitivity analysis of the model parameters is performed on flows and volumes.
Nicolas Flipo, Nicolas Gallois, and Jonathan Schuite
Geosci. Model Dev., 16, 353–381, https://doi.org/10.5194/gmd-16-353-2023, https://doi.org/10.5194/gmd-16-353-2023, 2023
Short summary
Short summary
A new approach is proposed to fit hydrological or land surface models, which suffer from large uncertainties in terms of water partitioning between fast runoff and slow infiltration from small watersheds to regional or continental river basins. It is based on the analysis of hydrosystem behavior in the frequency domain, which serves as a basis for estimating water flows in the time domain with a physically based model. It opens the way to significant breakthroughs in hydrological modeling.
Joachim Meyer, John Horel, Patrick Kormos, Andrew Hedrick, Ernesto Trujillo, and S. McKenzie Skiles
Geosci. Model Dev., 16, 233–250, https://doi.org/10.5194/gmd-16-233-2023, https://doi.org/10.5194/gmd-16-233-2023, 2023
Short summary
Short summary
Freshwater resupply from seasonal snow in the mountains is changing. Current water prediction methods from snow rely on historical data excluding the change and can lead to errors. This work presented and evaluated an alternative snow-physics-based approach. The results in a test watershed were promising, and future improvements were identified. Adaptation to current forecast environments would improve resilience to the seasonal snow changes and helps ensure the accuracy of resupply forecasts.
Shuqi Lin, Donald C. Pierson, and Jorrit P. Mesman
Geosci. Model Dev., 16, 35–46, https://doi.org/10.5194/gmd-16-35-2023, https://doi.org/10.5194/gmd-16-35-2023, 2023
Short summary
Short summary
The risks brought by the proliferation of algal blooms motivate the improvement of bloom forecasting tools, but algal blooms are complexly controlled and difficult to predict. Given rapid growth of monitoring data and advances in computation, machine learning offers an alternative prediction methodology. This study tested various machine learning workflows in a dimictic mesotrophic lake and gave promising predictions of the seasonal variations and the timing of algal blooms.
Cited articles
Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey,
J.: Machine learning for precipitation nowcasting from radar images, arXiv
[preprint], https://doi.org/10.48550/arXiv.1912.12132, 2019.
Ayzel, G., Heistermann, M., and Winterrath, T.: Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1), Geosci. Model Dev., 12, 1387–1402, https://doi.org/10.5194/gmd-12-1387-2019, 2019.
Ayzel, G., Scheffer, T., and Heistermann, M.: RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting, Geosci. Model Dev., 13, 2631–2644, https://doi.org/10.5194/gmd-13-2631-2020, 2020.
Basist, A., Bell, G. D., and Meentemeyer, V.: Statistical relationships between topography and precipitation patterns, J. climate, 7, 1305–1315, https://doi.org/10.1175/1520-0442(1994)007<1305:SRBTAP>2.0.CO;2, 1994.
Berenguer, M., Surcel, M., Zawadzki, I., Xue, M., and Kong, F.: The Diurnal Cycle of Precipitation from Continental Radar Mosaics and Numerical Weather Prediction Models. Part II: Intercomparison among Numerical Models and with Nowcasting, Mon. Weather Rev., 140, 2689–2705, https://doi.org/10.1175/MWR-D-11-00181.1, 2012.
Choi, S. and Kim, Y.: Rad-cGAN v1.0: Radar-based precipitation nowcasting
model with conditional Generative Adversarial Networks for multiple dam
domains, Zenodo [code], https://doi.org/10.5281/zenodo.6650722, 2021a.
Choi, S. and Kim, Y.: SuyeonC/Rad-cGAN: (v1.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.6880997, 2021b.
Clark, A., Donahue, J., and Simonyan, K.: Adversarial video generation on
complex datasets, arXiv [preprint], https://doi.org/10.48550/arXiv.1907.06571, 2019.
Fang, K., Kifer, D., Lawson, K., Feng, D., and Shen, C.: The data synergy
effects of time-series deep learning models in hydrology, Water Resour.
Res., 58, e2021WR029583, https://doi.org/10.1029/2021WR029583, 2022.
Foresti, L. and Seed, A.: The effect of flow and orography on the spatial distribution of the very short-term predictability of rainfall from composite radar images, Hydrol. Earth Syst. Sci., 18, 4671–4686, https://doi.org/10.5194/hess-18-4671-2014, 2014.
Germann, U. and Zawadzki, I.: Scale-Dependence of the Predictability of Precipitation from Continental Radar Images. Part I: Description of the Methodology, Mon. Weather Rev., 130, 2859–2873, https://doi.org/10.1175/1520-0493(2002)130<2859:SDOTPO>2.0.CO;2, 2002.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y.: Generative adversarial networks, in: Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 8–13 December 2014, The MIT Press, 2672–2680, available at: https://arxiv.org/pdf/1406.2661.pdf (last access: 20 July 2022), 2014.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, in: CVPR 2016: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 27–30 June 2016, IEEE, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural
Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Hwang, S., Yoon, J., Kang, N., and Lee, D.-R.: Development of flood
forecasting system on city ⋅ mountains ⋅ small river area
in Korea and assessment of forecast accuracy, Journal of Korea Water
Resources Association, 53, 225–236, https://doi.org/10.3741/JKWRA.2020.53.3.225, 2020.
Imhoff, R. O., Brauer, C. C., Overeem, A., Weerts, A. H., and Uijlenhoet,
R.: Spatial and Temporal Evaluation of Radar Rainfall Nowcasting Techniques
on 1,533 Events, Water Resour. Res., 56, e2019WR026723,
https://doi.org/10.1029/2019WR026723, 2020.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning, Lille, France, 6–11 July 2015, JMLR.org, 37, 448–456, available at: http://proceedings.mlr.press/v37/ioffe15.pdf (last access: 20 July 2022), 2015.
Isola, P., Zhu, J., Zhou, T., and Efros, A. A.: Image-to-Image Translation with Conditional Adversarial Networks, in: CVPR 2017: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, 21–26 July 2017, IEEE, 1125–1134, https://doi.org/10.1109/CVPR.2017.632, 2017.
Jeong, C. H., Kim, W., Joo, W., Jang, D., and Yi, M. Y.: Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step, Atmosphere, 12, 261, https://doi.org/10.3390/atmos12020261, 2021.
Kim, S., Hong, S., Joh, M., and Song, S.-K.: Deeprain: Convlstm network for precipitation prediction using multichannel radar data, in: Proceedings of the 7th International Workshop on Climate Informatics: CI 2017, Boulder, Colorado, USA, 20–22 September 2017, UCAR/NCAR – Library, 89–92, https://arxiv.org/pdf/1711.02316.pdf (last access: 20 July 2022), 2017.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, in: Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, California, USA, 7–9 May 2015, Conference Track Proceedings, https://arxiv.org/pdf/1412.6980.pdf (last access: 21 July 2022), 2015.
KMA (Korea Meteorological Administration): Quality-controlled 1.5 km Constant Altitude Plan-Position Indicator (CAPPI) Radar Reflectiviy Composite map, KMA [data set], https://data.kma.go.kr/cmmn/main.do, last access: 22 July 2022.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet classification with deep convolutional neural networks, in: Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, USA, 3–8 December 2012, NeurIPS, 1097–1105, https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf (last access: 21 July 2022), 2012.
Kumar, A., Islam, T., Sekimoto, Y., Mattmann, C., and Wilson, B.: Convcast:
An embedded convolutional LSTM based architecture for precipitation
nowcasting using satellite data, Plos One, 15, e0230114,
https://doi.org/10.1371/journal.pone.0230114, 2020.
Long, J., Shelhamer, E., and Darrell, T.: Fully convolutional networks for semantic segmentation, in: CVPR 2015: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 7–12 June 2015, IEEE, 3431–3440, https://doi.org/10.1109/CVPR.2015.7298965, 2015.
Marshall, J. S. and Palmer, W. M. K.: THE DISTRIBUTION OF RAINDROPS WITH
SIZE, J. Atmos. Sci., 5, 165–166, https://doi.org/10.1175/1520-0469(1948)005<0165:Tdorws>2.0.Co;2, 1948.
McCuen, R. H., Knight, Z., and Cutter, A. G.: Evaluation of the
Nash-Sutcliffe Efficiency Index, J. Hydrol. Eng., 11,
597–602, https://doi.org/10.1061/(ASCE)1084-0699(2006)11:6(597), 2006.
Mirza, M. and Osindero, S.: Conditional generative adversarial nets, arXiv
[preprint], https://doi.org/10.48550/arXiv.1411.1784, 2014.
Mo, S., Cho, M., and Shin, J.: Freeze the discriminator: a simple baseline for fine-tuning gans, in: Proceedings of the Conference on Computer Vision and Pattern Recognition: AI for Content Creation Workshop, Online, 15 June 2020, AICCW, https://arxiv.org/pdf/2002.10964.pdf (last access: 21 July 2022), 2020.
Moishin, M., Deo, R. C., Prasad, R., Raj, N., and Abdulla, S.: Designing
Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm,
IEEE Access, 9, 50982–50993, https://doi.org/10.1109/ACCESS.2021.3065939, 2021.
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L.: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations, T. ASABE, 50, 885–900, https://doi.org/10.13031/2013.23153, 2007.
Pan, S. J. and Yang, Q.: A Survey on Transfer Learning, IEEE T.
Knowl. Data En., 22, 1345–1359, https://doi.org/10.1109/TKDE.2009.191, 2010.
Pierce, C., Seed, A., Ballard, S., Simonin, D., and Li, Z.: Nowcasting, in: Doppler Radar Observations – Weather Radar, Wind Profiler, Ionospheric Radar, and Other Advanced Applications, edited by: Bech, J. and Chau, J. L., InTechOpen., 97–142, https://doi.org/10.5772/39054, 2012.
Poletti, M. L., Silvestro, F., Davolio, S., Pignone, F., and Rebora, N.: Using nowcasting technique and data assimilation in a meteorological model to improve very short range hydrological forecasts, Hydrol. Earth Syst. Sci., 23, 3823–3841, https://doi.org/10.5194/hess-23-3823-2019, 2019.
Prudhomme, C. and Reed, D. W.: Relationships between extreme daily precipitation and topography in a mountainous region: a case study in Scotland. Int. J. Climatol., 18, 1439–1453, https://doi.org/10.1002/(SICI)1097-0088(19981115)18:13<1439::AID-JOC320>3.0.CO;2-7, 1998.
Pulkkinen, S., Nerini, D., Pérez Hortal, A. A., Velasco-Forero, C., Seed, A., Germann, U., and Foresti, L.: Pysteps: an open-source Python library for probabilistic precipitation nowcasting (v1.0), Geosci. Model Dev., 12, 4185–4219, https://doi.org/10.5194/gmd-12-4185-2019, 2019.
Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P.,
Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R.,
Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N.,
Clancy, E., Arribas, A., and Mohamed, S.: Skilful precipitation nowcasting
using deep generative models of radar, Nature, 597, 672–677,
https://doi.org/10.1038/s41586-021-03854-z, 2021.
Renzullo, L., Velasco-Forero, C., and Seed, A.: Blending radar, NWP and satellite data for real-time ensemble rainfall analysis: a scale-dependent method, Tech. Rep. EP174236, CSIRO, https://doi.org/10.4225/08/594eb78c96025, 2017.
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, edited by: Navab, N.,
Hornegger, J., Wells, W. M., and Frangi, A. F., Springer International
Publishing, Cham, 234–241,
https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Rüttgers, M., Lee, S., Jeon, S., and You, D.: Prediction of a typhoon
track using a generative adversarial network and satellite images,
Sci. Rep.-UK, 9, 6057, https://doi.org/10.1038/s41598-019-42339-y, 2019.
Seed, A. W.: A dynamic and spatial scaling approach to advection
forecasting, J. Appl. Meteorol., 42, 381–388,
https://doi.org/10.1175/1520-0450(2003)042<0381:ADASSA>2.0.CO;2, 2003.
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-C.: Convolutional LSTM Network: a machine learning approach for precipitation nowcasting, in: Proceedings of the 29th International Conference on Neural Information Processing Systems, Montreal, Canada, 7–12 December 2015, NeurIPS, 802–810, https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf (last access: 21 July 2022), 2015.
Simonyan, K. and Zisserman, A.: Very deep convolutional networks for large-scale image recognition, in: Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, California, USA, 7–9 May 2015, Conference Track Proceedings, https://arxiv.org/pdf/1409.1556.pdf (last access: 21 July 2022), 2015.
Sønderby, C. K., Espeholt, L., Heek, J., Dehghani, M., Oliver, A.,
Salimans, T., Agrawal, S., Hickey, J., and Kalchbrenner, N.: Metnet: A
neural weather model for precipitation forecasting, arXiv [preprint], https://doi.org/10.48550/arXiv.2003.12140, 2020.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and
Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from
overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014.
Sutskever, I., Vinyals, O., and Le, Q. V.: Sequence to sequence learning with neural networks, , in: Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 8–13 December 2014, NeurIPS, 3014–3112, https://proceedings.neurips.cc/paper/2014/file/a14ac55a4f27472c5d894ec1c3c743d2-Paper.pdf (last access: 20 July 2022), 2014.
Trebing, K., Staǹczyk, T., and Mehrkanoon, S.: SmaAt-UNet: Precipitation
nowcasting using a small attention-UNet architecture, Pattern Recogn.
Lett., 145, 178–186, https://doi.org/10.1016/j.patrec.2021.01.036, 2021.
Wang, S., Liu, W., Wu, J., Cao, L., Meng, Q., and Kennedy, P. J.: Training
deep neural networks on imbalanced data sets, in: 2016 International Joint
Conference on Neural Networks (IJCNN), 24–29 July 2016, 4368–4374,
https://doi.org/10.1109/IJCNN.2016.7727770, 2016.
Wang, Y., Coning, E., Harou, A., Jacobs, W., Joe, P., Nikitina, L., Roberts,
R., Wang, J., and Wilson, J.: Guidelines for nowcasting techniques, WMO
publication, https://library.wmo.int/opac/doc_num.php?explnum_id=3795 (last access: 19 July 2022), 2017.
Wang, Y., Wu, C., Herranz, L., van de Weijer, J., Gonzalez-Garcia, A., and Raducanu, B.: Transferring gans: generating images from limited data, in: Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018, Springer, Cham, 220–236, https://doi.org/10.1007/978-3-030-01231-1_14, 2018.
Wang, Y., Gonzalez-Garcia, A., Berga, D., Herranz, L., Khan, F. S., and Weijer, J. v. d.: MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images, in: CVPR 2020: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Online, 14–19 June 2020, IEEE, 9332–9341, https://doi.org/10.1109/CVPR42600.2020.00935, 2020.
Short summary
Here we present the cGAN-based precipitation nowcasting model, named Rad-cGAN, trained to predict a radar reflectivity map with a lead time of 10 min. Rad-cGAN showed superior performance at a lead time of up to 90 min compared with the reference models. Furthermore, we demonstrate the successful implementation of the transfer learning strategies using pre-trained Rad-cGAN to develop the models for different dam domains.
Here we present the cGAN-based precipitation nowcasting model, named Rad-cGAN, trained to...
