State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Huainan, China.
School of Geomatics, Anhui University of Science and Technology, Huainan, China.
PLoS One. 2023 Aug 16;18(8):e0289846. doi: 10.1371/journal.pone.0289846. eCollection 2023.
Accurate prediction of surface subsidence is of significance for analyzing the pattern of mining-induced surface subsidence, and for mining under buildings, railways, and water bodies. To address the problem that the existing prediction models ignore the correlation between subsidence points, resulting in large prediction errors, a Multi-point Relationship Fusion prediction model based on Graph Convolutional Networks (MRF-GCN) for mining-induced subsidence was proposed. Taking the surface subsidence in 82/83 mining area of Yuandian No. 2 Mine in Anhui Province in eastern China as an example, the surface deformation data obtained from 250 InSAR images captured by Sentinel-1A satellite from 2018 to 2022, combined with GNSS observation data, were used for modeling. The deformation pattern of each single observation point was obtained by feeding their deformation observation data into the LSTM encoder, after that, the relationship graph was created based on the correlation between points in the observation network and MRF-GCN was established. Then the prediction results came out through a nonlinear activation function of neural network. The research shows that the R2R2 value of MRF-GCN model was 0.865 0, much larger than that of Long-Short Term Memory (LSTM) and other conventional models, while mean square error (MSE) of MRF-GCN model was 1.59 899, much smaller than that of LSTM and other conventional models. Therefore, the MRF-GCN model has better prediction accuracy than other models and can be applied to predicting surface subsidence in large areas.
准确预测地表沉降对于分析采动地表沉降规律以及在建筑物、铁路和水体下采煤具有重要意义。针对现有预测模型忽略沉降点之间相关性，导致预测误差较大的问题，提出了一种基于图卷积网络的多点关系融合预测模型（MRF-GCN）用于采动沉降预测。以中国东部安徽省袁店二矿 82/83 采区的地表沉降为例，利用 2018 年至 2022 年 Sentinel-1A 卫星获取的 250 景 InSAR 图像和 GNSS 观测数据进行建模。将各单点观测数据的变形观测值输入 LSTM 编码器，得到各单点观测值的变形模式，然后根据观测网络中各点之间的相关性建立关系图，建立 MRF-GCN 模型。最后通过神经网络的非线性激活函数得到预测结果。研究表明，MRF-GCN 模型的 R2R2 值为 0.865 0，明显大于长短期记忆（LSTM）等传统模型，而 MRF-GCN 模型的均方根误差（MSE）为 1.59 899，明显小于 LSTM 等传统模型。因此，MRF-GCN 模型的预测精度优于其他模型，可以应用于大面积地表沉降预测。
