Soil temperature prediction based on explainable artificial intelligence and LSTM
Authors:
Open Access
- 31 July 2024
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Environmental Science
- Vol. 12, 1426942
Abstract
Soil temperature is a key parameter in many disciplines, and its research has important practical significance. In recent years, the prediction of soil temperature by deep learning has achieved good results. However, deep learning is difficult to popularize in practical use because of its opacity. This study aims to interpret and analyze the Long Short Term Memory Network (LSTM) model for global soil temperature prediction using SHapley Additive exPlanation (SHAP), Permutation Importance (PI) and Partial Dependence Plot (PDP). The results show that Temperature of air at 2 m above the surface of land has the greatest influence on the prediction of soil temperature, and its SHAP and PI characteristic values have significant seasonality. Meanwhile, radiation also has a certain influence on the prediction results. There was a significant positive correlation between the temperature of 2 m and the soil temperature. The explanatory insights provided in this paper enhance the transparency and confidence of the model, which promotes the applicability of soil temperature prediction models in relevant fields.Keywords
This publication has 38 references indexed in Scilit:
- A decision-aid system for subway microenvironment health risk intervention based on backpropagation neural network and permutation feature importance methodBuilding and Environment, 2024
- LandBench 1.0: A benchmark dataset and evaluation metrics for data-driven land surface variables predictionExpert Systems with Applications, 2023
- Exploring explainable machine learning and Shapley additive exPlanations (SHAP) technique to uncover key factors of HNSC cancer: An analysis of the best practicesBiomedical Signal Processing and Control, 2023
- Explainable Methods for Image-Based Deep Learning: A ReviewArchives of Computational Methods in Engineering, 2023
- Transparency and accountability in AI decision support: Explaining and visualizing convolutional neural networks for text informationDecision Support Systems, 2020
- A review on the long short-term memory modelArtificial Intelligence Review, 2020
- Modeling daily soil temperature over diverse climate conditions in Iran—a comparison of multiple linear regression and support vector regression techniquesTheoretical and Applied Climatology, 2018
- The dropout learning algorithmArtificial Intelligence, 2014
- Prediction of soil temperature using regression and artificial neural network modelsMeteorology and Atmospheric Physics, 2010
- Soil temperature under forests: a simple model for predicting soil temperature under a range of forest typesAgricultural and Forest Meteorology, 2004