An attention-aware LSTM model for soil moisture and soil temperature prediction

Accurate prediction of soil moisture (SM) and soil temperature (ST) plays an important role in Earth system science, helping to forecast and understand ecosystem changes. They present great challenges because land atmospheric interactions are complex and diverse in space and time. Although deep learning methods have excellent performance for land surface variables' prediction such as SM and ST, they are often questioned due to their over-parameterized black-box nature and neglect of physical knowledge and interpretability. From this, we propose an attention-aware LSTM Model (ILSTM_Soil) by taking multi-feature attention, predictor attention and temporal attention into account. We first used LSTM to generate multi-feature vectors of all predictors, and then the three attention mechanisms were designed to summarize these feature vectors for SM and ST prediction. Experiment results for SM and ST prediction at the lead time of 1 and 7 days on ten FLUXNET sites suggest that the proposed ILSTM_Soil model outperforms Random Forest (RF), Support Vector Regression (SVR), Elastic-Net (ENET), original Long Short-Term Memory (LSTM), and attention LSTM (A-LSTM) models in most cases. The interpretation of attention weights verifies that the proposed model can capture physical knowledge over SM and ST. The code of ILSTM_Soil is made publicly available and we hope it can encourage researchers to develop effective DL models in land surface variables' prediction conveniently.

Automated summary

Accurate prediction of soil moisture and soil temperature is important in Earth system science, but faces challenges due to the complex land-atmosphere interactions. A deep learning model with attention mechanisms is proposed to improve prediction performance. Experimental results show that the proposed model outperforms other models in most cases, and the interpretation of attention weights verifies its ability to capture physical knowledge.