Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq

Soil moisture (SM) is a key variable in agricultural ecosystems and is crucial for drought prevention and control management. However, SM is influenced by underlying surface and meteorological conditions, and it changes rapidly in time and space. To capture the changes in SM and improve the accuracy...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiuping Zhang, Xiufeng He, Rencai Lin, Xiaohua Xu, Yanping Shi, Zhenning Hu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849252028422815744
author Xiuping Zhang
Xiufeng He
Rencai Lin
Xiaohua Xu
Yanping Shi
Zhenning Hu
author_facet Xiuping Zhang
Xiufeng He
Rencai Lin
Xiaohua Xu
Yanping Shi
Zhenning Hu
author_sort Xiuping Zhang
collection DOAJ
description Soil moisture (SM) is a key variable in agricultural ecosystems and is crucial for drought prevention and control management. However, SM is influenced by underlying surface and meteorological conditions, and it changes rapidly in time and space. To capture the changes in SM and improve the accuracy of short-term and medium-to-long-term predictions on a daily scale, an LSTMseq2seq model driven by both observational data and mechanism models was constructed. This framework combines historical meteorological elements and SM, as well as the SM change characteristics output by the VIC model, to predict SM over a 90-day period. The model was validated using SMAP SM. The proposed model can accurately predict the spatiotemporal variations in SM in Jiangxi Province. Compared with classical machine learning (ML) models, traditional LSTM models, and advanced transformer models, the LSTMseq2seq model achieved R<sup>2</sup> values of 0.949, 0.9322, 0.8839, 0.8042, and 0.7451 for the prediction of surface SM over 3 days, 7 days, 30 days, 60 days, and 90 days, respectively. The mean absolute error (MAE) ranged from 0.0118 m<sup>3</sup>/m<sup>3</sup> to 0.0285 m<sup>3</sup>/m<sup>3</sup>. This study also analyzed the contributions of meteorological features and simulated future SM state changes to SM prediction from two perspectives: time importance and feature importance. The results indicated that meteorological and SM changes within a certain time range prior to the prediction have an impact on SM prediction. The dual-driven LSTMseq2seq model has unique advantages in predicting SM and is conducive to the integration of physical mechanism models with data-driven models for handling input features of different lengths, providing support for daily-scale SM time series prediction and drought dynamics prediction.
format Article
id doaj-art-c9d2fd4e4b3144a39d78d4bf125f83fd
institution Kabale University
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-c9d2fd4e4b3144a39d78d4bf125f83fd2025-08-20T03:56:45ZengMDPI AGRemote Sensing2072-42922025-07-011714245310.3390/rs17142453Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seqXiuping Zhang0Xiufeng He1Rencai Lin2Xiaohua Xu3Yanping Shi4Zhenning Hu5School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaJiangxi Academy of Water Science and Engineering, Nanchang 330029, ChinaJiangxi Academy of Water Science and Engineering, Nanchang 330029, ChinaJiangxi Academy of Water Science and Engineering, Nanchang 330029, ChinaJiangxi Academy of Water Science and Engineering, Nanchang 330029, ChinaSoil moisture (SM) is a key variable in agricultural ecosystems and is crucial for drought prevention and control management. However, SM is influenced by underlying surface and meteorological conditions, and it changes rapidly in time and space. To capture the changes in SM and improve the accuracy of short-term and medium-to-long-term predictions on a daily scale, an LSTMseq2seq model driven by both observational data and mechanism models was constructed. This framework combines historical meteorological elements and SM, as well as the SM change characteristics output by the VIC model, to predict SM over a 90-day period. The model was validated using SMAP SM. The proposed model can accurately predict the spatiotemporal variations in SM in Jiangxi Province. Compared with classical machine learning (ML) models, traditional LSTM models, and advanced transformer models, the LSTMseq2seq model achieved R<sup>2</sup> values of 0.949, 0.9322, 0.8839, 0.8042, and 0.7451 for the prediction of surface SM over 3 days, 7 days, 30 days, 60 days, and 90 days, respectively. The mean absolute error (MAE) ranged from 0.0118 m<sup>3</sup>/m<sup>3</sup> to 0.0285 m<sup>3</sup>/m<sup>3</sup>. This study also analyzed the contributions of meteorological features and simulated future SM state changes to SM prediction from two perspectives: time importance and feature importance. The results indicated that meteorological and SM changes within a certain time range prior to the prediction have an impact on SM prediction. The dual-driven LSTMseq2seq model has unique advantages in predicting SM and is conducive to the integration of physical mechanism models with data-driven models for handling input features of different lengths, providing support for daily-scale SM time series prediction and drought dynamics prediction.https://www.mdpi.com/2072-4292/17/14/2453soil moistureVIC-LSTMseq2seq modeldeep learningprediction
spellingShingle Xiuping Zhang
Xiufeng He
Rencai Lin
Xiaohua Xu
Yanping Shi
Zhenning Hu
Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
Remote Sensing
soil moisture
VIC-LSTMseq2seq model
deep learning
prediction
title Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
title_full Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
title_fullStr Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
title_full_unstemmed Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
title_short Soil Moisture Prediction Using the VIC Model Coupled with LSTMseq2seq
title_sort soil moisture prediction using the vic model coupled with lstmseq2seq
topic soil moisture
VIC-LSTMseq2seq model
deep learning
prediction
url https://www.mdpi.com/2072-4292/17/14/2453
work_keys_str_mv AT xiupingzhang soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq
AT xiufenghe soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq
AT rencailin soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq
AT xiaohuaxu soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq
AT yanpingshi soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq
AT zhenninghu soilmoisturepredictionusingthevicmodelcoupledwithlstmseq2seq