Landslide susceptibility prediction has always been an important and
challenging content. However, there are some uncertain problems to be solved in
susceptibility modeling, such as the error of landslide samples and the complex
nonlinear relationship between environmental factors. A self-screening graph
convolutional network and long short-term memory network (SGCN-LSTM) is
proposed int this paper to overcome the above problems in landslide
susceptibility prediction. The SGCN-LSTM model has the advantages of wide width
and good learning ability. The landslide samples with large errors outside the
set threshold interval are eliminated by self-screening network, and the
nonlinear relationship between environmental factors can be extracted from both
spatial nodes and time series, so as to better simulate the nonlinear
relationship between environmental factors. The SGCN-LSTM model was applied to
landslide susceptibility prediction in Anyuan County, Jiangxi Province, China,
and compared with Cascade-parallel Long Short-Term Memory and Conditional
Random Fields (CPLSTM-CRF), Random Forest (RF), Support Vector Machine (SVM),
Stochastic Gradient Descent (SGD) and Logistic Regression (LR) models.The
landslide prediction experiment in Anyuan County showed that the total accuracy
and AUC of SGCN-LSTM model were the highest among the six models, and the total
accuracy reached 92.38 %, which was 5.88%, 12.44%, 19.65%, 19.92% and 20.34%
higher than those of CPLSTM-CRF, RF, SVM, SGD and LR models, respectively. The
AUC value reached 0.9782, which was 0.0305,0.0532,0.1875,0.1909 and 0.1829
higher than the other five models, respectively. In conclusion, compared with
some existing traditional machine learning, the SGCN-LSTM model proposed in
this paper has higher landslide prediction accuracy and better robustness, and
has a good application prospect in the LSP field.

本文提出了一种使用自筛选图卷积和长短期记忆网络的山体滑坡易损性预测模型来解决传统机器学习模型在样本误差和环境因素等方面存在的不确定性问题，并与几种常规机器学习方法进行了比较，实验结果显示，SGCN-LSTM 模型具有更高的预测精度和更好的鲁棒性，具有很好的应用前景。