Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 5.240 IF 5.240
  • IF 5-year value: 5.768 IF 5-year
  • CiteScore value: 8.9 CiteScore
  • SNIP value: 1.713 SNIP 1.713
  • IPP value: 5.53 IPP 5.53
  • SJR value: 3.18 SJR 3.18
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 71 Scimago H
    index 71
  • h5-index value: 51 h5-index 51
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: model description paper 09 Apr 2020

Submitted as: model description paper | 09 Apr 2020

Review status
A revised version of this preprint was accepted for the journal GMD.

ClimateNet: an expert-labelled open dataset and Deep Learning architecture for enabling high-precision analyses of extreme weather

Prabhat1,2,, Karthik Kashinath1,, Mayur Mudigonda1,10,, Sol Kim2, Lukas Kapp-Schwoerer3, Andre Graubner3, Ege Karaismailoglu3, Leo von Kleist3, Thorsten Kurth4, Annette Greiner1, Kevin Yang2, Colby Lewis2, Jiayi Chen2, Andrew Lou2, Sathyavat Chandran5, Ben Toms6, Will Chapman7, Katherine Dagon8, Christine A. Shields8, Travis O'Brien9,1, Michael Wehner1, and William Collins1,2 Prabhat et al.
  • 1Lawrence Berkeley National Laboratory, Berkeley, CA, USA
  • 2University of California, Berkeley, CA, USA
  • 3ETH Zurich, Switzerland
  • 4NVIDIA, Santa Clara, CA, USA
  • 5Rice University, Houston, TX, USA
  • 6Colorado State University, Fort Collins, CO, USA
  • 7Scripps Institution of Oceanography, University of California, San Diego, La Jolla, CA, USA
  • 8National Center for Atmospheric Research, Boulder, CO, USA
  • 9Indiana University, Bloomington, IN, USA
  • 10Terrafuse, Berkeley, CA,USA
  • These authors contributed equally to this work.

Abstract. Identifying, detecting and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection and segmentation have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of Deep Learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning; when labeled datasets are readily available. Reliable, labeled training data for extreme weather and climate events is scarce.

We create ClimateNet – an open, community-sourced human expert-labeled curated dataset – that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification, i.e. segmentation, of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs or the background at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, hi-fidelity and highly precise analytics of climate data using a curated expert-labelled dataset – ClimateNet.

ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns, and applied to observational and reanalysis data products via transfer learning.

Prabhat et al.

Interactive discussion

Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for Authors/Topical Editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Prabhat et al.

Prabhat et al.


Total article views: 739 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
560 171 8 739 12 9
  • HTML: 560
  • PDF: 171
  • XML: 8
  • Total: 739
  • BibTeX: 12
  • EndNote: 9
Views and downloads (calculated since 09 Apr 2020)
Cumulative views and downloads (calculated since 09 Apr 2020)

Viewed (geographical distribution)

Total article views: 393 (including HTML, PDF, and XML) Thereof 391 with geography defined and 2 with unknown origin.
Country # Views %
  • 1



No saved metrics found.


No discussed metrics found.
Latest update: 08 Jul 2020
Publications Copernicus
Short summary
Detecting extreme weather events is a crucial step in understanding how they change due to climate change. Deep Learning (DL) is remarkable at pattern recognition, however, it works best only when labeled datasets are available. We create ClimateNet – an expert-labeled curated dataset – to train a DL model for detecting weather events and predicting changes in extreme precipitation. This work paves the way for DL-based automated, hi-fidelity and highly precise analytics of climate data.
Detecting extreme weather events is a crucial step in understanding how they change due to...