Quantifying Historical and Future Surface Soil Moisture Drying Using Deep Learning and Remote Sensing

Yong Bo; Xueke Li; Kai Liu; Shudong Wang; Qiuhong Tang; Yelin Jiang; Zhengqiang Li; Shanlong Lu; Litao Wang; Chenglian Feng; Zhan Zhou; Guangsheng Zhou

doi:10.1029/2025EF006261

Quantifying Historical and Future Surface Soil Moisture Drying Using Deep Learning and Remote Sensing

Yong Bo
, Xueke Li
, Kai Liu
, Shudong Wang
, Qiuhong Tang
, Yelin Jiang
, Zhengqiang Li
, Shanlong Lu
, Litao Wang
, Chenglian Feng
, Zhan Zhou
, Guangsheng Zhou

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

1 Citation (Scopus)

1 Downloads (CityUHK Scholars)

Abstract

Understanding historical and future surface soil moisture (SSM) drying is pivotal due to its close links with droughts, heatwaves, and wildfires, yet debates regarding its evolution persist. In this study, we leverage advanced deep learning techniques to fill gaps of remote sensing-based SSM data during 1983–2020 and therefore use these gap-filled observations to constrain SSM estimates from 23 Earth System Models (ESMs) during 1901–2100. Our enhanced observations reveal that approximately half of Earth's landmass experienced SSM drying over the past four decades. However, in contrast to projections from current-generation ESMs, observation-constrained simulations indicate a less pronounced drying trend in dry-wet transitions and monsoon margins during 2021–2100 compared to 1901–1980. Current ESMs may overestimate SSM drying in these regions, likely due to their limited representation of soil moisture-atmosphere feedback. These findings highlight the need to integrate remote sensing and artificial intelligence into ESMs to improve projections of future droughts and their socio-economic consequences. © 2026. The Author(s).

Original language	English
Article number	e2025EF006261
Number of pages	23
Journal	Earth's Future
Volume	14
Issue number	3
Online published	19 Mar 2026
DOIs	https://doi.org/10.1029/2025EF006261
Publication status	Published - Mar 2026
Externally published	Yes

Funding

We are grateful to the providers for all the data sets used in this study. This study has been jointly supported by the National Key R&D Program of China (Grant 2024YFF1308200), Foreign Technical Cooperation and Scientific Research Program (Grant ZE01), and Science and Technology Plan Project of Hohhot (Grant 2022‐Social‐Key 4‐1‐1).

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1029/2025EF006261

492896580.pdfFinal Published version, 4.07 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{46dfb9c4852c44709638e11c44615e13,

title = "Quantifying Historical and Future Surface Soil Moisture Drying Using Deep Learning and Remote Sensing",

abstract = "Understanding historical and future surface soil moisture (SSM) drying is pivotal due to its close links with droughts, heatwaves, and wildfires, yet debates regarding its evolution persist. In this study, we leverage advanced deep learning techniques to fill gaps of remote sensing-based SSM data during 1983–2020 and therefore use these gap-filled observations to constrain SSM estimates from 23 Earth System Models (ESMs) during 1901–2100. Our enhanced observations reveal that approximately half of Earth's landmass experienced SSM drying over the past four decades. However, in contrast to projections from current-generation ESMs, observation-constrained simulations indicate a less pronounced drying trend in dry-wet transitions and monsoon margins during 2021–2100 compared to 1901–1980. Current ESMs may overestimate SSM drying in these regions, likely due to their limited representation of soil moisture-atmosphere feedback. These findings highlight the need to integrate remote sensing and artificial intelligence into ESMs to improve projections of future droughts and their socio-economic consequences. {\textcopyright} 2026. The Author(s).",

author = "Yong Bo and Xueke Li and Kai Liu and Shudong Wang and Qiuhong Tang and Yelin Jiang and Zhengqiang Li and Shanlong Lu and Litao Wang and Chenglian Feng and Zhan Zhou and Guangsheng Zhou",

year = "2026",

month = mar,

doi = "10.1029/2025EF006261",

language = "English",

volume = "14",

number = "3",

}

TY - JOUR

T1 - Quantifying Historical and Future Surface Soil Moisture Drying Using Deep Learning and Remote Sensing

AU - Bo, Yong

AU - Li, Xueke

AU - Liu, Kai

AU - Wang, Shudong

AU - Tang, Qiuhong

AU - Jiang, Yelin

AU - Li, Zhengqiang

AU - Lu, Shanlong

AU - Wang, Litao

AU - Feng, Chenglian

AU - Zhou, Zhan

AU - Zhou, Guangsheng

PY - 2026/3

Y1 - 2026/3

N2 - Understanding historical and future surface soil moisture (SSM) drying is pivotal due to its close links with droughts, heatwaves, and wildfires, yet debates regarding its evolution persist. In this study, we leverage advanced deep learning techniques to fill gaps of remote sensing-based SSM data during 1983–2020 and therefore use these gap-filled observations to constrain SSM estimates from 23 Earth System Models (ESMs) during 1901–2100. Our enhanced observations reveal that approximately half of Earth's landmass experienced SSM drying over the past four decades. However, in contrast to projections from current-generation ESMs, observation-constrained simulations indicate a less pronounced drying trend in dry-wet transitions and monsoon margins during 2021–2100 compared to 1901–1980. Current ESMs may overestimate SSM drying in these regions, likely due to their limited representation of soil moisture-atmosphere feedback. These findings highlight the need to integrate remote sensing and artificial intelligence into ESMs to improve projections of future droughts and their socio-economic consequences. © 2026. The Author(s).

AB - Understanding historical and future surface soil moisture (SSM) drying is pivotal due to its close links with droughts, heatwaves, and wildfires, yet debates regarding its evolution persist. In this study, we leverage advanced deep learning techniques to fill gaps of remote sensing-based SSM data during 1983–2020 and therefore use these gap-filled observations to constrain SSM estimates from 23 Earth System Models (ESMs) during 1901–2100. Our enhanced observations reveal that approximately half of Earth's landmass experienced SSM drying over the past four decades. However, in contrast to projections from current-generation ESMs, observation-constrained simulations indicate a less pronounced drying trend in dry-wet transitions and monsoon margins during 2021–2100 compared to 1901–1980. Current ESMs may overestimate SSM drying in these regions, likely due to their limited representation of soil moisture-atmosphere feedback. These findings highlight the need to integrate remote sensing and artificial intelligence into ESMs to improve projections of future droughts and their socio-economic consequences. © 2026. The Author(s).

UR - http://www.scopus.com/inward/record.url?scp=105033388489&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105033388489&origin=recordpage

U2 - 10.1029/2025EF006261

DO - 10.1029/2025EF006261

M3 - RGC 21 - Publication in refereed journal

SN - 2328-4277

VL - 14

JO - Earth's Future

JF - Earth's Future

IS - 3

M1 - e2025EF006261

ER -

Quantifying Historical and Future Surface Soil Moisture Drying Using Deep Learning and Remote Sensing

Abstract

Funding

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this