Research on Land Subsidence Intelligent Prediction Method Based on LSTM and Transformer

Research on Land Subsidence Intelligent Prediction Method Based on LSTM and Transformer

by

Research on land subsidence intelligent prediction method based on LSTM and Transformer——A case study of Shanghai

PENG Wenxiang1,2,3,4,5，ZHANG Deying1,2,3,4,5

1. Shanghai Institute of Geological Survey, Shanghai 200072; 2. Shanghai Institute of Geological Exploration Technology, Shanghai 200072; 3. Key Laboratory of Land Subsidence Monitoring and Prevention, Ministry of Natural Resources of China, Shanghai 200072; 4. Shanghai Engineering Research Center of Land Subsidence, Shanghai 200072; 5. Shanghai Professional Technical Service Platform of Geological Data Information, Shanghai 200072

Abstract: Land subsidence poses a serious threat to the lives and property of 19% of the world’s population. It is of great practical significance to carry out land subsidence simulation and prediction for disaster prevention and mitigation. Addressing the limitations of the existing land subsidence prediction models, which struggle with parameter acquisition and single-method accuracy, this paper proposes a land subsidence prediction method integrating the core technology of large language models. Firstly, commencing with the top-level design of land subsidence simulation prediction, this paper proposes the overall architecture based on depth learning. This architecture encompasses the computing power layer, data layer, model layer, evaluation layer, and application layer; secondly, it proposes a practical approach to land subsidence prediction based on LSTM and Transformer; finally, Shanghai’s land subsidence data were used for experimental research. The results show that deep learning technology can achieve good results in land subsidence simulation and prediction. The multi-model method proves capable of predicting scenarios with minimal change, rebound, and substantial change in land subsidence. The iTransformer model has a good prediction effect on the situation with small changes in land subsidence. In the era of micro land subsidence, high accuracy can be achieved through the utilization of Transformer, the core technology of large language models.

Keywords: land subsidence; deep learning; time series forecasting; LSTM; Transformer; large language models

Supported by: Fund project of the Shanghai Municipal Science and Technology Commission (19DZ2292000, 20DZ1201200, 21DZ1204200)

Source: Journal of Spatio-Temporal Information, 2024, Issue 1

Leave a Comment