Ground subsidence is a significant safety concern in mining regions, making large-scale subsidence forecasting vital for mine site environmental management. This study proposes a deep learning-based prediction approach to address the challenges posed by the existing prediction methods, such as complicated model parameters or large data requirements. Small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technology was utilized to collect spatiotemporal ground subsidence data at the Pingshuo mining area from 2019 to 2022, which was then analyzed using the long-short term memory (LSTM) neural network algorithm. Additionally, an attention mechanism was introduced to incorporate temporal dependencies and improve prediction accuracy, leading to the development of the AT-LSTM model. The results demonstrate that the Pingshuo mine area had subsidence rates ranging from −205.89 to −59.70 mm/yr from 2019 to 2022, with subsidence areas mainly located around Jinggong-1 (JG-1) and the three open-pit mines, strongly linked to mining activities, and the subsidence range continuously expanding. The spatial distribution of the AT-LSTM prediction results is basically consistent with the real situation, and the correlation coefficient is more than 0.97. Compared with the LSTM, the AT-LSTM method better captured the fluctuation changes of the time series for fitting, while the model was more sensitive to the mining method of the mine, and had different expressiveness in open-pit and shaft mines. Furthermore, in comparison to existing time-series forecasting methods, the AT-LSTM is effective and practical.

Geo-hazard emergency response is a disaster prevention and reduction action that multi-factorial, time-critical, task-intensive and socially significant. In order to improve the rationalization and standardization of space-air-ground remote sensing collaborative observation in geo-hazard emergency response, this paper comprehensively analyzes the technical resources of remote sensing sensors and the emergency service system, and establishes a database of technical and service evaluation indexes using MySQL. A method is proposed to evaluate and calculate the cooperative observation effectiveness in a specific remote sensing cooperative environment by combining TOPSIS and RSR. For the evaluation of remote sensing cooperative service capability in geo-hazard emergency response, taking earthquake as an example, establishing a remote sensing cooperative earthquake emergency response service chain, and designing a Bayesian network evaluation model. Through the evaluation of observation efficiency and service capability, the operation and task completion of remote sensing collaborative technology in geo-hazard emergency response can be effectively grasped and a basis for decision making can be provided for space-air-ground remote sensing collaborative work.