Sub-seasonal soil moisture anomaly forecasting using combinations of deep learning, based on the reanalysis soil moisture records

Wang, X.; Corzo, Gerald; Lü, Haishen; Zhou, Shiliang; Mao, K.; Zhu, Yonghua; Duarte Prieto, F.S.; Liu, Mingwen; Su, Jianbin

doi:10.1016/j.agwat.2024.108772

Sub-seasonal soil moisture anomaly forecasting using combinations of deep learning, based on the reanalysis soil moisture records

Title

Sub-seasonal soil moisture anomaly forecasting using combinations of deep learning, based on the reanalysis soil moisture records

Author

Wang, X. (Chongqing Jiaotong University; Hohai University)
Corzo, Gerald (IHE Delft Institute for Water Education)
Lü, Haishen (Hohai University)
Zhou, Shiliang (Chongqing Jiaotong University)
Mao, K. (TU Delft Physical and Space Geodesy)
Zhu, Yonghua (Hohai University)
Duarte Prieto, F.S. (TU Delft Water Resources; IHE Delft Institute for Water Education)
Liu, Mingwen (Hohai University)
Su, Jianbin (Chinese Academy of Sciences)

Date

2024

Abstract

Sub-seasonal drought forecasting is crucial for early warning in estimating agricultural production and optimizing irrigation management, as forecasting skills are relatively weak during this period. Soil moisture exhibits stronger persistence compared to other climate system quantities, which makes it especially influential in shaping land-atmosphere feedback, thus supplying a unique insight into drought forecasting. Relying on the soil moisture memory, this study investigates the combination of multiple deep-learning modules for sub-seasonal drought indices hindcast in the Huai River basin of China, using long-term ERA5-Land soil moisture records with a noise-assisted data analysis tool. The inter-compared deep-learning models include a hybrid model and a committee machine framework. The results show that the performance of the committee machine framework can be improved with the help of series decomposition and the forecasting skill is not impaired with the lead time increases. Overall, this study highlights the potential of combining deep-learning models with soil moisture memory analysis to improve sub-seasonal drought forecasting.

Subject

Committee model
Deep learning
Drought forecasting
Noise-assisted tool
Reanalysis soil moisture

To reference this document use:

http://resolver.tudelft.nl/uuid:328d3299-e8f0-42d8-9e72-d983e197d95e

DOI

https://doi.org/10.1016/j.agwat.2024.108772

ISSN

0378-3774

Source

Agricultural Water Management, 295

Part of collection

Institutional Repository