Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms
Open Access
Abstract
This study introduces an innovative deep learning model, Residual-EnDecode-Feedforward Attention Mechanism-Long Short-Term Memory (REDF-LSTM), designed to overcome the high uncertainty challenges faced by traditional soil moisture prediction methods. The REDF-LSTM model, by integrating a residual learning encoder–decoder LSTM layer, enhanced LSTM layers, and feedforward attention, not only captures the deep features of time series data but also optimizes the model’s ability to identify key influencing factors, including land surface features, atmospheric conditions, and other static environmental variables. Unlike existing methods, the innovation of this model lies in its first-time combination of the residual learning encoder–decoder and feedforward attention mechanisms in the soil moisture prediction field. It delves into the complex patterns of time series through the encoder–decoder structure and accurately locates key influencing factors through the feedforward attention mechanism, significantly improving predictive performance. The choice to combine the feedforward attention mechanism and encoder–decoder with the LSTM model is to fully leverage their advantages in processing complex data sequences and enhancing the model’s focus on important features, aiming for more accurate soil moisture prediction. After comparison with current advanced models such as EDLSTM, FAMLSTM, and GANBiLSTM, our REDF-LSTM demonstrated the best performance. Compared to traditional LSTM models, it achieved an average improvement of 13.07% in R2, 20.98% in RMSE, 24.86% in BIAS, and 11.1% in KGE key performance indicators, fully proving its superior predictive capability and potential application value in precision agriculture and ecosystem management.Keywords
Funding Information
- National Natural Science Foundation of China (42275155, 42105144, 20230101370JC, JJKH20220840KJ, JJKH20230919KJ)
- Jilin Provincial Science and Technology Development Plan Project (42275155, 42105144, 20230101370JC, JJKH20220840KJ, JJKH20230919KJ)
- Jilin Provincial Department of Education Science and Technology Research Project (42275155, 42105144, 20230101370JC, JJKH20220840KJ, JJKH20230919KJ)
This publication has 48 references indexed in Scilit:
- LandBench 1.0: A benchmark dataset and evaluation metrics for data-driven land surface variables predictionExpert Systems with Applications, 2023
- GAN-BiLSTM network for field-road classification on imbalanced GNSS recordingsComputers and Electronics in Agriculture, 2023
- Multistep ahead prediction of temperature and humidity in solar greenhouse based on FAM-LSTM modelComputers and Electronics in Agriculture, 2023
- A comparison of physical-based and machine learning modeling for soil salt dynamics in crop fieldsAgricultural Water Management, 2022
- Attention mechanisms in computer vision: A surveyComputational Visual Media, 2022
- Improving soil moisture prediction using a novel encoder-decoder model with residual learningComputers and Electronics in Agriculture, 2022
- Influence of persistence and oceanic forcing on global soil moisture predictabilityClimate Dynamics, 2020
- Using data‐driven methods to explore the predictability of surface soil moisture with FLUXNET site dataHydrological Processes, 2019
- Full‐flow‐regime storage‐streamflow correlation patterns provide insights into hydrologic functioning over the continental USWater Resources Research, 2017
- Spatio‐temporal distribution of near‐surface and root zone soil moisture at the catchment scaleHydrological Processes, 2007