Time-series monitoring and prediction of tailings dams through neural network-based deep infusion of InSAR and GNSS data
LYU Linwei1,2(), WANG Rui1,2(), XU Lintao3, HUANG Shiqiao1, HUANG Shuaishuai4, LIN Min5, HE Yibo6, HE Qian7, YAN Huineng1,2, CHEN Shangbo8
1. College of Resources and Civil Engineering，Gannan University of Science and Technology，Ganzhou 341000，China 2. Ganzhou Key Laboratory of Remote Sensing for Resources and Environment，Ganzhou 341000，China 3. CNPC Bohai Oilfield Equipment Manufacturing Co.，Ltd.，Tianjin 300280，China 4. School of Civil and Surveying Engineering，Jiangxi University of Science and Technology，Ganzhou 341000，China 5. Anhui Longqiao Mining Co.，Ltd.，Hefei 230000，China 6. Shanxi Energy Institute，Jinzhong 030600，China 7. Hubei Vocational College of Land and Resources，Wuhan 430090，China 8. Jiangxi Provincial Emergency Management Science Research Institute，Nanchang 330000，China
The time-series monitoring and prediction of tailings dam stability have always been a major concern in China’s mine safety research. Focusing on a tailings dam in Anhui province，this study obtained 26 periods of longitudinal deformation data from six characteristic monitoring points on the dam surface，using InSAR and GNSS technologies. Based on the data，a least-squares adjustment model with restricted parameters was established. Combined with the initial three-dimensional coordinates of the monitoring points as polynomial correction parameters，the InSAR and GNSS data were fused to improve the data accuracy. Then，time-series prediction of deformation data was conducted for the monitoring points using the back propagation （BP） neural network，thus obtaining their future deformation data. Experiments were carried out to compute and compare the deformation data and corresponding root mean square error （RMSE） of each period before and after fusion，wherein the fused GNSS and InSAR data were evaluated with the root mean square error （RMSE） as the accuracy standard. The results showed that the post-fusion RMSE decreased by up to 70.61% and by at least 4.34% （average：25.91%），compared to pre-fusion data. Furthermore，the neural network model was used to repeatedly train the fused InSAR data from periods 1 to 22，with periods 23 to 26 serving as the test set，ultimately outputting the data of each point for periods 23 to 26. Compared to the GNSS data，the RMSE of the outputs were less than 1.5 mm. These results can provide reliable technical support for the time-series monitoring and prediction of tailings dam stability.
吕林伟, 王瑞, 许林涛, 黄诗乔, 黄帅帅, 林敏, 贺一波, 何倩, 晏慧能, 陈尚波. 基于神经网络的InSAR/GNSS深度融合尾矿库坝体时序监测及预测研究[J]. 自然资源遥感, 2025, 37(5): 162-171.
LYU Linwei, WANG Rui, XU Lintao, HUANG Shiqiao, HUANG Shuaishuai, LIN Min, HE Yibo, HE Qian, YAN Huineng, CHEN Shangbo. Time-series monitoring and prediction of tailings dams through neural network-based deep infusion of InSAR and GNSS data. Remote Sensing for Natural Resources, 2025, 37(5): 162-171.
Ma D S. Application of safety online monitoring system of tailings pond based on GNSS deformation monitoring technology in tailings pond in Sijiaying North District[J]. China Metal Bulletin, 2019(11):140-141.
Chen Yanan. Monitoring and disaster identification of tailings dam ( reservoir area ) based on time series InSAR[D]. Kunming: Kunming University of Science and Technology, 2020.
Zhu J J, Yang Z F, Li Z W. Recent progress in retrieving and predicting mining-induced 3D displace-ments using InSAR[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(2):135-144.
doi: 10.11947/j.AGCS.2019.20180188
Xu C J, Wang H, Huang J S. Research prospect of data fusion between GPS and INSAR[J]. Geomatics and Information Science of Wuhan University, 2003, 28(s1):58-61,78.
Liu G L, Zhang L P, Cheng S, et al. Feasibility analysis of monitoring mining surface substance using InSAR/GPS data fusion[J]. Bulletin of Surveying and Mapping, 2005(11):10-13.
Cao H K, Zhao L H, Zhang Q, et al. Ascending and descending orbits InSAR-GPS data fusion method with additional systematic parameters for three-dimensional deformation field[J]. Geomatics and Information Science of Wuhan University, 2018, 43(9):1362-1368.
[8]
王洲. GNSS与InSAR地面形变监测深度融合[D]. 兰州: 兰州交通大学, 2021.
Wang Z. Deep fusion of GNSS and InSAR ground deformation monitoring[D]. Lanzhou: Lanzhou Jiatong University, 2021.
Xiong W, Sun Z J, Zhang B C. Surface subsidence monitoring in Tianjin based on ascending and descending time series InSAR technology[J]. Geospatial Information, 2021, 19(12):45-49.
[10]
Memarian Sorkhabi O, Khajehzadeh M, Keawsawasvong S. Landslides monitoring with SBAS-InSAR and GNSS[J]. Physics and Chemistry Earth,Parts A/B/C, 2023, 132:103486.
[11]
Wang R, Wu K, He Q, et al. A novel method of monitoring surface subsidence law based on probability integral model combined with active and passive remote sensing data[J]. Remote Sensing, 2022, 14(2):299.
Zhao H W, Zhou L, Tan M L, et al. Early identification of potential landslides for the Sichuan-Chongqing power grid based on optical remote sensing and SBAS-InSAR[J]. Remote Sensing for Natural Resources, 2023, 35(4):264-272 doi:10.6046/zrzyyg.2022321.
Zhou D Y, Zuo X Q, Zhao Z F, et al. Prediction of urban land subsidence by SBAS-InSAR and improved BP neural network[J]. Geological Bulletin of China, 2023, 42(10):1774-1783.
Yi B J, Huang C, Fu T, et al. SBAS-InSAR-based detection of geological hazards in alpine gorge areas near the China-Myanmar border[J]. Remote Sensing for Natural Resources, 2023, 35(4):186-191.doi:10.6046/zrzyyg.2022261.
Wei F, Tan Z X, Deng K Z. Application in two-dimensional control network adjustment with additional system parameters adjustment[J]. Coal Technology, 2017, 36(3):139-141.
Chen Y B, Wen Y Y, Dong G X, et al. Speed optimization based on BP artificial neural network and genetic algorithm[J]. Ship Science and Technology, 2024, 46(1):82-87.
[18]
Guo J, Xi W, Yang Z, et al. Study on optimization method for InSAR baseline considering changes in vegetation coverage[J]. Sensors, 2024, 24(15):4783.
Zhang Y F, Li R Z, Wen Y Y, et al. Self-learning artificial neural network model for pre-estimating ship energy consumption for a voyage[J]. Journal of Shanghai Ship and Shipping Research Institute, 2019, 42(2):34-37.
[20]
王瑞. 开采沉陷监测多源数据融合技术及应用研究[D]. 徐州: 中国矿业大学, 2022.
Wang R. Research on multi-source data fusion technology and its application in mining subsidence monitoring[D]. Xuzhou: China University of Mining and Technology, 2022.
2025, Vol. 37 
), 王瑞1,2(
