Preprints
https://doi.org/10.5194/egusphere-2024-2081
https://doi.org/10.5194/egusphere-2024-2081
12 Aug 2024
 | 12 Aug 2024

Advances in Land Surface Model-based Forecasting: A Comparison of LSTM, Gradient Boosting, and Feedforward Neural Networks as Prognostic State Emulators in a Case Study with ECLand

Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Bödecker, Carsten F. Dormann, Florian Pappenberger, and Gianpaolo Balsamo

Abstract. Most useful weather prediction for the public is near the surface. The processes that are most relevant for near-surface weather prediction are also those that are most interactive and exhibit positive feedback or have key role in energy partitioning. Land surface models (LSMs) consider these processes together with surface heterogeneity and forecast water, carbon and energy fluxes, and coupled with an atmospheric model provide boundary and initial conditions. This numerical parametrization of atmospheric boundaries being computationally expensive, statistical surrogate models are increasingly used to accelerated progress in experimental research. We evaluated the efficiency of three surrogate models in speeding up experimental research by simulating land surface processes, which are integral to forecasting water, carbon, and energy fluxes in coupled atmospheric models. Specifically, we compared the performance of a Long-Short Term Memory (LSTM) encoder-decoder network, extreme gradient boosting, and a feed-forward neural network within a physics-informed multi-objective framework. This framework emulates key states of the ECMWF's Integrated Forecasting System (IFS) land surface scheme, ECLand, across continental and global scales. Our findings indicate that while all models on average demonstrate high accuracy over the forecast period, the LSTM network excels in continental long-range predictions when carefully tuned, the XGB scores consistently high across tasks and the MLP provides an excellent implementation-time-accuracy trade-off. The runtime reduction achieved by the emulators in comparison to the full numerical models are significant, offering a faster, yet reliable alternative for conducting numerical experiments on land surfaces.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Bödecker, Carsten F. Dormann, Florian Pappenberger, and Gianpaolo Balsamo

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CEC1: 'Comment on egusphere-2024-2081', Astrid Kerkweg, 06 Sep 2024
    • AC1: 'Reply on CEC1', Marieke Wesselkamp, 06 Oct 2024
  • RC1: 'Comment on egusphere-2024-2081', Simon O'Meara, 12 Sep 2024
    • AC2: 'Reply on RC1', Marieke Wesselkamp, 14 Oct 2024
  • RC2: 'Comment on egusphere-2024-2081', Anonymous Referee #2, 28 Sep 2024
    • AC3: 'Reply on RC2', Marieke Wesselkamp, 14 Oct 2024
Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Bödecker, Carsten F. Dormann, Florian Pappenberger, and Gianpaolo Balsamo
Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Bödecker, Carsten F. Dormann, Florian Pappenberger, and Gianpaolo Balsamo

Viewed

Total article views: 538 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
311 89 138 538 57 8 6
  • HTML: 311
  • PDF: 89
  • XML: 138
  • Total: 538
  • Supplement: 57
  • BibTeX: 8
  • EndNote: 6
Views and downloads (calculated since 12 Aug 2024)
Cumulative views and downloads (calculated since 12 Aug 2024)

Viewed (geographical distribution)

Total article views: 534 (including HTML, PDF, and XML) Thereof 534 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Dec 2024
Download
Short summary
We compared spatio-temporal forecast performances of three popular machine learning approaches that learned processes of water and energy exchange on the earth surface from a large physical model. The forecasting models were developed with reanalysis data and simulations on a European scale and transferred to the Globe. We found that all approaches deliver highly accurate predictions until long time horizons, implying their usefulness to advance land surface forecasting when data is available.