Kelu He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Kelu He has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xuesong Zhang
State Key Laboratory of Loess Science Chang'an University Xi'an China
3 shared publications - Zhenhong Li
State Key Laboratory of Loess Science, Chang’an University, Xi’an 710054, China
3 shared publications Jiawei Zhou
College of Geological Engineering and Geomatics, Changan University, Xian, China
2 shared publicationsBingquan Han
College of Geological Engineering and Geomatics, Changan University, Xian, China
1 shared publication- Chenglong Zhang
State Key Laboratory of Loess Science, Changan University, Xian, China
1 shared publication - Chuang Song
College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China
1 shared publication
Latest Publications
- Open Access
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 1641-1659
Earthformer_MSTSP: A Dynamic Simulation-Based Model for Mining Subsidence Prediction Using InSAR Observations
Mining-induced subsidence is a complex deformation process influenced by both human activities and natural factors, making accurate prediction essential. Conventional methods face challenges in spatial modeling, deformation interpretation, and computational efficiency. Although deep learning (DL) offers strong nonlinear modeling capabilities and avoids complex physical parameter constraints, its application to mining subsidence prediction remains limited. This study introduces a new prediction framework, Earthformer_MSTSP, and a Gaussian-based dynamic simulation method (MSDS_G) for generating training data. The synthesized dataset is trained using a Cuboid Attention.based hierarchical codec architecture. Using SBASInSAR displacement time series from the Datong mine as input, Earthformer_MSTSP achieves an MSE of 0.45 m and a 3.7% relative error in maximum subsidence, improving prediction accuracy by 74% over the Weibull model and 82% over LSTM. A transferability test in the Changwu mine shows that the model trained with MSDS_G effectively preserves the spatial deformation patterns, as verified by Moran.s I. Additionally, subsidence-rate-based early warning analysis and the impact of mining speed are explored, providing multiple indicators for hazard mitigation.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 1641-1659
Open AccessEarthformer_MSTSP: A Dynamic Simulation-Based Model for Mining Subsidence Prediction Using InSAR Observations
Mining-induced subsidence is a complex deformation process influenced by both human activities and natural factors, making accurate prediction essential. Conventional methods face challenges in spatial modeling, deformation interpretation, and computational efficiency. Although deep learning (DL) offers strong nonlinear modeling capabilities and avoids complex physical parameter constraints, its application to mining subsidence prediction remains limited. This study introduces a new prediction framework, Earthformer_MSTSP, and a Gaussian-based dynamic simulation method (MSDS_G) for generating training data. The synthesized dataset is trained using a Cuboid Attention.based hierarchical codec architecture. Using SBASInSAR displacement time series from the Datong mine as input, Earthformer_MSTSP achieves an MSE of 0.45 m and a 3.7% relative error in maximum subsidence, improving prediction accuracy by 74% over the Weibull model and 82% over LSTM. A transferability test in the Changwu mine shows that the model trained with MSDS_G effectively preserves the spatial deformation patterns, as verified by Moran.s I. Additionally, subsidence-rate-based early warning analysis and the impact of mining speed are explored, providing multiple indicators for hazard mitigation.
- Open Access
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 17368-17385
Asymmetric Deformation Induced by Underground Mining: A Case Study of a Mine in Shaanxi, China
Geohazards resulting from mining activities must be effectively monitored to mitigate their impact on the environment and human activities. Geohazards such as landslides and collapses caused by open-pit mining are relatively easier to monitor because they are primarily surface-based. In contrast, underground mining disrupts the stress balance in the overlying rock layers, leading to complex settlement patterns, including subsidence basins, cracks, and groundwater depletion. This complexity makes monitoring geohazards caused by underground mining particularly challenging, as it depends on subsurface stress conditions and structural complexity. Previous studies have shown that land subsidence caused by horizontal/near-horizontal longwall mining methods is typically symmetrical. However, asymmetry can occur under complex conditions. In this paper, asymmetric land subsidence caused by coal mining activities in Shaanxi, China, over the past decade is investigated using Interferometric Synthetic Aperture Radar (InSAR) supplemented by field investigations and geophysical experiments. The results indicate that the mining across multiple working faces over the years has led to the formation of a large subsidence funnel above the working faces with a cumulative subsidence of more than 900 mm in the centre area, in addition to the formation of a new subsidence centre. Moreover, asymmetric surface deformation has also occurred, with both the extent and magnitude of deformation being greater on the southwest side of the working faces than on the northeast side. Through further analysis, we proposed potential driving mechanisms of asymmetric subsidence, providing valuable insights into the prediction and monitoring of land subsidence due to underground mining.
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 17368-17385
Open AccessAsymmetric Deformation Induced by Underground Mining: A Case Study of a Mine in Shaanxi, China
Geohazards resulting from mining activities must be effectively monitored to mitigate their impact on the environment and human activities. Geohazards such as landslides and collapses caused by open-pit mining are relatively easier to monitor because they are primarily surface-based. In contrast, underground mining disrupts the stress balance in the overlying rock layers, leading to complex settlement patterns, including subsidence basins, cracks, and groundwater depletion. This complexity makes monitoring geohazards caused by underground mining particularly challenging, as it depends on subsurface stress conditions and structural complexity. Previous studies have shown that land subsidence caused by horizontal/near-horizontal longwall mining methods is typically symmetrical. However, asymmetry can occur under complex conditions. In this paper, asymmetric land subsidence caused by coal mining activities in Shaanxi, China, over the past decade is investigated using Interferometric Synthetic Aperture Radar (InSAR) supplemented by field investigations and geophysical experiments. The results indicate that the mining across multiple working faces over the years has led to the formation of a large subsidence funnel above the working faces with a cumulative subsidence of more than 900 mm in the centre area, in addition to the formation of a new subsidence centre. Moreover, asymmetric surface deformation has also occurred, with both the extent and magnitude of deformation being greater on the southwest side of the working faces than on the northeast side. Through further analysis, we proposed potential driving mechanisms of asymmetric subsidence, providing valuable insights into the prediction and monitoring of land subsidence due to underground mining.
- Open Access
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
A Mask R-CNN Network for Wide-Area Mining Subsidence Automatic Detection With InSAR Observations
Land subsidence caused by mining activity is one of the most serious anthropogenic geohazards. The rapid detection and continuous monitoring of mining subsidence facilitate the swift detection of geohazards. Traditional methods of monitoring mining subsidence have shortcomings, such as offering only a limited coverage and being time consuming. Interferometric Synthetic Aperture Radar (InSAR) has been proven to be a powerful tool to identify mining subsidence hazards from unwrapped interferograms but this method can be complex and inefficient, particularly for wide areas. In this paper, a Mask R-CNN model is presented to automatically detect mining subsidence and monitor the surface activity over wide areas using original SAR interferograms to avoid the time-consuming and error-prone phase unwrapping procedure. Using Sentinel-1 wrapped interferograms as the real dataset and simulated wrapped interferograms generated with the Gaussian surface function combined with Generic Atmospheric Correction Online Service for InSAR (GACOS) as the simulated dataset, the Mask R-CNN deep neural network was used to train the mining subsidence detection model. It turned out that the accuracy of the detection model was 91.48%, while the precision was 96.44%, the recall rate was 93.88% and the F1 index was 0.949. The detection model was then utilized to detect mining subsidence in south-western Shanxi Province, China between 2016 and 2022. A total of 152 land subsidence points were detected and long-term monitoring results were also obtained. An analysis of the state of land subsidence in the mining areas was carried out to obtain land subsidence activity during the monitoring period.
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
Open AccessA Mask R-CNN Network for Wide-Area Mining Subsidence Automatic Detection With InSAR Observations
Land subsidence caused by mining activity is one of the most serious anthropogenic geohazards. The rapid detection and continuous monitoring of mining subsidence facilitate the swift detection of geohazards. Traditional methods of monitoring mining subsidence have shortcomings, such as offering only a limited coverage and being time consuming. Interferometric Synthetic Aperture Radar (InSAR) has been proven to be a powerful tool to identify mining subsidence hazards from unwrapped interferograms but this method can be complex and inefficient, particularly for wide areas. In this paper, a Mask R-CNN model is presented to automatically detect mining subsidence and monitor the surface activity over wide areas using original SAR interferograms to avoid the time-consuming and error-prone phase unwrapping procedure. Using Sentinel-1 wrapped interferograms as the real dataset and simulated wrapped interferograms generated with the Gaussian surface function combined with Generic Atmospheric Correction Online Service for InSAR (GACOS) as the simulated dataset, the Mask R-CNN deep neural network was used to train the mining subsidence detection model. It turned out that the accuracy of the detection model was 91.48%, while the precision was 96.44%, the recall rate was 93.88% and the F1 index was 0.949. The detection model was then utilized to detect mining subsidence in south-western Shanxi Province, China between 2016 and 2022. A total of 152 land subsidence points were detected and long-term monitoring results were also obtained. An analysis of the state of land subsidence in the mining areas was carried out to obtain land subsidence activity during the monitoring period.