EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A deep learning bias-correction layer for land surface models: application to soil moisture during drought and hurricane events

Mahmoud Mbarak, Manmeet Singh, Naveen Sudharsan, Zong-Liang Yang

Machine Learning: Earth · 01.06.2026 · 2 (1) · 01LT02

DOI: 10.1088/3049-4753/ae7115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Earth, online erschienen am 10.06.2026. Verfasst von Mahmoud Mbarak und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Energy Advanced Scientific Computing Research Program, Texas Water Development Board, Jackson School of Geosciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate soil moisture prediction during extreme events remains a challenge for Earth system modeling, with significant implications for drought monitoring, flood forecasting, and climate adaptation strategies. Although land surface models (LSMs) provide physics-based predictions, their parameterizations struggle to represent the non-linear feedbacks and threshold behaviors that emerge during hydrometeorological extremes, producing systematic biases. Here we present a deep learning bias-correction layer for Noah-MP soil moisture. A 3D U-Net architecture for Noah-MP outputs (soil moisture, latent heat flux, and sensible heat flux) is trained against SMAP L4 soil moisture across two contrasting extreme events: a drought (March–September 2022) and a hurricane (July 2024) over Texas. The bias correction layer achieves substantial improvements over standalone Noah-MP, increasing R2 from below the climatological mean to 0.5 during drought while reducing prediction errors by 40%–60% for both events, all while preserving spatial coherence. The framework operates as a post-processing layer on LSM output, addressing forecast windows where direct observational correction is unavailable. This provides a deployable pathway for integrating LSMs with deep learning in Earth system forecasting.

Förderung

  • U.S. Department of Energy Advanced Scientific Computing Research Program
  • Texas Water Development Board
  • Jackson School of Geosciences
  • NASA

Zitieren

APA

Mbarak, M., Singh, M., Sudharsan, N., & Yang, Z. (2026). A deep learning bias-correction layer for land surface models: application to soil moisture during drought and hurricane events. Machine Learning: Earth, 2(1), 01LT02. https://doi.org/10.1088/3049-4753/ae7115

Vancouver

Mbarak M, Singh M, Sudharsan N, Yang Z. A deep learning bias-correction layer for land surface models: application to soil moisture during drought and hurricane events. Machine Learning: Earth. 2026;2(1):01LT02. doi:10.1088/3049-4753/ae7115

BibTeX
@article{Mbarak2026,
  author = {Mbarak, Mahmoud and Singh, Manmeet and Sudharsan, Naveen and Yang, Zong-Liang},
  title = {A deep learning bias-correction layer for land surface models: application to soil moisture during drought and hurricane events},
  journal = {Machine Learning: Earth},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {01LT02},
  doi = {10.1088/3049-4753/ae7115}
}
Kostenlos starten →