Landslide Susceptibility Prediction Modeling and Interpretability Based on Self-Screening Deep Learning Model
-
摘要: 针对滑坡易发性预测建模中滑坡-非滑坡样本可能存在误差、环境因子间非线性关系较复杂且机器学习可解释性未被关注等重要问题，拟提出一种基于自筛选的双向长短时记忆网络与条件随机场的滑坡易发性预测模型(Self-screening Bi-directional Long Short-Term Memory and Conditional Random Fields，SBiLSTM-CRF).SBiLSTM-CRF模型具有深度学习网络层数深、宽度广及可循环迭代建模的优势，能预测出环境因子间的非线性关系，并通过迭代自动筛选阈值区间外的错误滑坡样本.该模型可用于解释各环境因子之间耦合关系的内部作用机制.将SBiLSTM-CRF模型用于陕西延长县滑坡易发性预测，并与cpLSTM-CRF、随机森林、支持向量机、随机梯度下降和逻辑回归模型比较.结果表明，SBiLSTM-CRF克服了传统机器学习中存在的样本误差以及因子间复杂的非线性关系问题，具有更高的预测性能.通过该模型的可解释性能力揭示了坡度、高程和岩性等因子控制延长县的黄土滑坡发育的机制.Abstract: To address the problems of landslide susceptibility prediction (LSP) modeling including possible errors in landslide and non-landslide samples, complex non-linear relationships between environmental factors and unaddressed machine learning interpretability, a deep learning-based Self-screening Bi-directional Long Short-Term Memory and Conditional Random Fields (SBiLSTM-CRF) model is proposed to reduce the impact of these problems on LSP and improve its confidence. The SBiLSTM-CRF model has the advantages of deep learning network with deep layers, wide width and iterative modeling, which can predict the non-linear relationship between environmental factors and automatically screen out the wrong landslide samples; it can select non-landslide samples from the initial low/very low landslide susceptibility zone through iterative modeling, and finally reveal the internal mechanism of the coupling of environmental factors to predict landslide susceptibility. The SBiLSTM-CRF model is used to predict landslide susceptibility in Yanchang County of China, and compared with cpLSTM-CRF, random forest (RF), support vector machine (SVM), stochastic gradient descent (SGD) and logistic regression (LR) models. The results show that SBiLSTM-CRF overcomes the problems of sample error and complex nonlinear relationship between factors in traditional machine learning, has superior performance in modeling susceptibility than conventional machine learning, and the interpretability of the model reveals that factors such as slope, elevation and lithology control the development of mounded landslides in Yanchang County.
-
图 1 算法流程及Bi-LSTM/LSTM结构示意
a.算法流程. FC. 全连接网络；Bi-LSTM. 双向LSTM；CRF. 条件随机场；b.Bi-LSTM链；c.LSTM单元结构
Fig. 1. Algorithm flow and Bi-LSTM/LSTM structure
图 3 延长县滑坡环境因子
a.高程；b.坡度；c.坡向；d.平面曲率；e.剖面曲率；f.地表起伏度；g.岩性；h.地形湿度指数；i.NDVI；j.NDBI；k.MNDWI；l.地表总辐射
Fig. 3. Environmental factors for landslides
图 4 滑坡易发性图
Fig. 4. Landslide susceptibility maps
a.SBiLSTM-CRF; b.cpLSTM-CRF; c.RF; d. LR; e. SVM; f.SGD
图 5 各滑坡易发性预测模型的ROC曲线
Fig. 5. ROC curves for each landslide susceptibility prediction model
图 7 滑坡易发性预测单因子可解释性结果
a.坡度；b.NDVI
Fig. 7. One-way interpretable results for landslide susceptibility prediction
图 8 滑坡易发性预测的双因子交互可解释性结果
a.高程与坡度；b.地形起伏度与TWI
Fig. 8. Two-factor interactive interpretability results
表 1 实验平台软硬件环境
Table 1. Software and hardware environment of the experimental platform
实验平台配置 参数 实验平台配置 参数 处理器(CPU) Intel(R) Core(TM) i5-7400@3.00 GHz 内存(ROM) Western Digital WDC WD10EZEX-08WN4A0 显卡(GPU) Nvidia GeForce GTX1080 操作系统 Windows10 + Ubuntu18.04 RAM 8.00 GB DDR4 开发环境 Python3.6.5 + TensorFlow1.14.0 +
Keras2.1.4 + Matlab 2018
下载: 导出CSV
表 2 滑坡易发性评估统计结果
Table 2. Statistical results of landslide susceptibility evaluation
预测模型 易发性等级(%) 极高 高 中等 低 极低 SBiLSTM-CRF 12.80 13.21 13.67 19.53 40.77 cpLSTM-CRF 8.59 9.33 13.92 22.36 45.80 RF 10.02 16.86 21.99 24.59 26.54 LR 10.9 16.85 21.52 25.53 25.19 SVM 14.87 16.45 18.76 22.84 27.08 SGD 15.2 18.46 20.16 22.15 24.03
下载: 导出CSV
表 3 不同模型对延长县滑坡预测的性能对比
Table 3. Comparison of landslide prediction performance of different models in Yanchang County
模型 SBiLSTM-CRF CPLSTM-CRF RF SVM LR SGD TP 849 809 813 767 729 813 TN 857 701 771 729 724 616 FP 173 329 259 301 306 414 FN 181 221 217 263 301 217 PPR(%) 83.07 71.09 75.84 71.82 70.43 66.26 NPR(%) 82.56 76.03 78.04 73.49 70.63 73.95 TA (%) 82.82 73.30 76.89 72.62 70.53 69.37
下载: 导出CSV
-
Alvarez-Melis, D., Jaakkola, T. S., 2018. Towards Robust Interpretability with Self-Explaining Neural Networks. Advances in Neural Information Processing Systems 31 (NeurIPS 2018). https://arxiv.org/abs/1806.07538 Bhattacharya, P., Tanwar, S., Bodke, U., et al., 2021. BinDaaS: Blockchain-Based Deep-Learning as-a-Service in Healthcare 4.0 Applications. IEEE Transactions on Network Science and Engineering, 8: 1242-1255. doi: 10.1109/TNSE.2019.2961932 Cheng, K. Y., Wang, N., Shi, W. X., et al., 2020. Research Advances in the Interpretability of Deep Learning. Journal of Computer Research and Development, 57(6): 1208-1217 (in Chinese with English abstract). Eiras, C., Souza, J., Freitas, R., et al., 2021. Discriminant Analysis as an Efficient Method for Landslide Susceptibility Assessment in Cities with the Scarcity of Predisposition Data. Natural Hazards, 107: 1427-1442. doi: 10.1007/s11069-021-04638-4 Fang, R. K., Liu, Y. H., Su, Y. C., et al., 2021. A Early Warning Model of Regional Landslide in Qingchuan County, Sichuan Province Based on Logistic Regression. Hydrogeology & Engineering Geology, 48(1): 181-187 (in Chinese with English abstract). http://www.sciengine.com/doi/pdf/D4C4486240D34ED697970D235482A458 Feng, X., Wang, Y., Liu, Y., et al., 2022. Susceptibility Assessment of a Translational Rockslide Considering the Control Mechanism and Spatial Uncertainty of a Weak Interlayer: Application Study in Tiefeng Township, Wanzhou District. Bulletin of Geological Science and Technology, 41(2): 254-266 (in Chinese with English abstract). Forney, G. D., 1973. The Viterbi Algorithm. Proceedings of the IEEE, 61: 268-278. doi: 10.1109/PROC.1973.9030 Gaur, M., Faldu, K., Sheth, A., 2020. Semantics of the Black-Box: Can Knowledge Graphs Help Make Deep Learning Systems More Interpretable and Explainable?. IEEE Internet Computing, 25: 51-59. http://www.xueshufan.com/publication/3130784583 Guo, G., Chen, Y., Li, M. H., et al., 2013. Statistic Relationship between Slope Gradient and Landslide Probability in Soil Slopes around Reservoir. Journal of Engineering Geology, 21(4): 607-612 (in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTOTAL-GCDZ201304021.htm Guo, T. S., Zhang, J. Q., Han, Y., et al., 2019. Evaluation of Landslide Susceptibility in Yanchang County Based on Particle Swarm Optimization-Based Support Vector Machine. Geological Science and Technology Information, 38(3): 236-243 (in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTotal-DZKQ201903025.htm Hong, H. Y., Tsangaratos, P., Ilia, I., et al., 2020. Introducing a Novel Multi-Layer Perceptron Network Based on Stochastic Gradient Descent Optimized by a Meta-Heuristic Algorithm for Landslide Susceptibility Mapping. The Science of the Total Environment, 742: 140549. https://doi.org/10.1016/j.scitotenv.2020.140549 Hu, T., Fan, X., Wang, S., et al., 2020. Landslide Susceptibility Evaluation of Sinan County Using Logistics Regression Model and 3S Technology. Bulletin of Geological Science and Technology, 39(2): 113-121 (in Chinese with English abstract). Huang, F., Cao, Z., Jiang, S. H., et al., 2020a. Landslide Susceptibility Prediction Based on a Semi-Supervised Multiple-Layer Perceptron Model. Landslides, 17: 2919-2930. doi: 10.1007/s10346-020-01473-9 Huang, F., Zhang, J., Zhou, C., et al., 2020b. A Deep Learning Algorithm Using a Fully Connected Sparse Autoencoder Neural Network for Landslide Susceptibility Prediction. Landslides, 17: 217-229. doi: 10.1007/s10346-019-01274-9 Huang, F. M., Ye, Z., Yao, C., et al., 2020. Uncertainties of Landslide Susceptibility Prediction: Different Attribute Interval Divisions of Environmental Factors and Different Data-Based Models. Earth Science, 45(12): 4535-4549 (in Chinese with English abstract). Jia, G., Gariano, S. L., Tang, Q., 2021. Advancing Rainfall-Induced Landslide Detection Using Homogeneous Slope Units and Distributed Rainfall Thresholds. EGU General Assembly Conference Abstracts, EGU21-6145. http://ui.adsabs.harvard.edu/abs/2021EGUGA..23.6145J/abstract Khan, R., Yousaf, S., Haseeb, A., et al., 2021. Exploring a Design of Landslide Monitoring System. Complexity, 2021: 5552417. https://doi.org/10.1155/2021/5552417 Li, W. B., Fan, X. M., Huang, F. M., et al., 2021. Uncertainties of Landslide Susceptibility Modeling under Different Environmental Factor Connections and Prediction Models. Earth Science, 46(10): 3777-3795 (in Chinese with English abstract). http://www.sciencedirect.com/science/article/pii/S0341816221001090 Luo, L. G., Pei, X. J., Huang, R. Q., et al. 2021. Evaluation of Landslide Susceptibility in Jiuzhaigou Scenic Spot by CF and Logistic Regression Coupled with GIS. Journal of Engineering Geology, 29: 526-535 (in Chinese with English abstract). Linardatos, P., Papastefanopoulos, V., Kotsiantis, S., 2020. Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy (Basel, Switzerland), 23(1): 18. https://doi.org/10.3390/e23010018 Lipton, Z. C., 2018. In Machine Learning, the Concept of Interpretability is Both Important and Slippery. Queue, 16: 28. doi: 10.1145/3291276.3295691 Moragues, S., Lenzano, M. G., Lanfri, M., et al., 2020. Analytic Hierarchy Process Applied to Landslide Susceptibility Mapping of the North Branch of Argentino Lake, Argentina. Natural Hazards, 105: 915-941. http://econpapers.repec.org/article/sprnathaz/v_3a105_3ay_3a2021_3ai_3a1_3ad_3a10.1007_5fs11069-020-04343-8.htm Pradhan, B., 2013. A Comparative Study on the Predictive Ability of the Decision Tree, Support Vector Machine and Neuro-Fuzzy Models in Landslide Susceptibility Mapping Using GIS-Science Direct. Computers & Geosciences, 51: 350-365. Tian, N. M., Lan, H. X., Wu, Y. M., et al., 2020. Performance Comparison of BP Artificial Neural Network and CART Decision Tree Model in Landslide Susceptibility Prediction. Journal of Geo-Information Science, 22(12): 2304-2316 (in Chinese with English abstract). Wei, Z. J., 2020. Multi-Stage Series Deep Convolutional Neural Network Medical Image Registration Method (Dissertation). Hunan University, Changsha (in Chinese with English abstract). Wu, R. Z., Hu, X. D., Mei, H. B., et al., 2021. Spatial Susceptibility Assessment of Landslides Based on Random Forest: A Case Study from Hubei Section in the Three Gorges Reservoir Area. Earth Science, (1): 321-330 (in Chinese with English abstract). Xu, M., Feng, Q., Mei, Q., et al., 2018. Deep Type: On-Device Deep Learning for Input Personalization Service with Minimal Privacy Concern. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2: 1-26. http://www.researchgate.net/publication/329957041_DeepType_On-Device_Deep_Learning_for_Input_Personalization_Service_with_Minimal_Privacy_Concern Yao, J., Qin, S., Qiao, S., et al., 2022. Application of a Two-Step Sampling Strategy Based on Deep Neural Network for Landslide Susceptibility Mapping. Bulletin of Engineering Geology and the Environment, 81: 1-20. doi: 10.1007/s10064-021-02521-x Yao, X., Tham, L., Dai, F., 2008. Landslide Susceptibility Mapping Based on Support Vector Machine: A Case Study on Natural Slopes of Hong Kong, China. Geomorphology, 101: 572-582. doi: 10.1016/j.geomorph.2008.02.011 Zeng, C. Y., Yan, K., Wang, Z. F., et al., 2021. Survey of Interpretability Research on Deep Learning Models. Computer Engineering and Applications, 57(8): 1-9 (in Chinese with English abstract). Zhang, Y., Tino, P., Leonardis, A., et al., 2021. A Survey on Neural Network Interpretability. IEEE Transactions on Emerging Topics in Computational Intelligence, 5: 1-17. doi: 10.1109/TETCI.2021.3109765 Zhao, H. B., Liu, R., Liu, Y. H., et al., 2022. Research on Classification and Identification of Mine Microseismic Signals Based on Deep Learning Method. Journal of Mining Science and Technology, 7(2): 166-174 (in Chinese with English abstract). Zhou, T., Wu, W., Peng, L., et al., 2022. Evaluation of Urban Bus Service Reliability on Variable Time Horizons Using a Hybrid Deep Learning Method. Reliability Engineering and System Safety, 217(3): 108090. http://www.sciencedirect.com/science/article/pii/S0951832021005883 Zhu, L., Huang, L. H., Fan, L. Y., et al., 2020. Landslide Susceptibility Prediction Modeling Based on Remote Sensing and a Novel Deep Learning Algorithm of a Cascade-Parallel Recurrent Neural Network. Sensors (Basel, Switzerland), 20(6): 1576. https://doi.org/10.3390/s20061576 成科扬, 王宁, 师文喜, 等, 2020. 深度学习可解释性研究进展. 计算机研究与发展, 57(6): 1208-1217. https://www.cnki.com.cn/Article/CJFDTOTAL-JFYZ202006008.htm 方然可, 刘艳辉, 苏永超, 等, 2021. 基于逻辑回归的四川青川县区域滑坡灾害预警模型. 水文地质工程地质, 48(1): 181-187. https://www.cnki.com.cn/Article/CJFDTOTAL-SWDG202101022.htm 冯霄, 王禹, 刘洋, 等, 2022. 考虑软弱夹层控滑机制及其空间不确定性的顺层岩质滑坡易发性评价: 万州区铁峰乡应用研究. 地质科技通报, 41(2): 254-266. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202202026.htm 郭果, 陈筠, 李明惠, 等, 2013. 土质滑坡发育概率与坡度间关系研究. 工程地质学报, 21(4): 607-612. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201304021.htm 郭天颂, 张菊清, 韩煜, 等, 2019. 基于粒子群优化支持向量机的延长县滑坡易发性评价. 地质科技情报, 38(3): 236-243. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201903025.htm 胡涛, 樊鑫, 王硕, 等, 2020. 基于逻辑回归模型和3S技术的思南县滑坡易发性评价. 地质科技通报, 39(2): 113-121. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202002013.htm 黄发明, 叶舟, 姚池, 等, 2020. 滑坡易发性预测不确定性: 环境因子不同属性区间划分和不同数据驱动模型的影响. 地球科学, 45(12): 4535-4549. doi: 10.3799/dqkx.2020.247 李文彬, 范宣梅, 黄发明, 等, 2021. 不同环境因子联接和预测模型的滑坡易发性建模不确定性. 地球科学, 46(10): 3777-3795. doi: 10.3799/dqkx.2021.042 罗路广, 裴向军, 黄润秋, 等, 2021. GIS支持下CF与Logistic回归模型耦合的九寨沟景区滑坡易发性评价. 工程地质学报, 29: 526-535. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ202102022.htm 田乃满, 兰恒星, 伍宇明, 等, 2020. 人工神经网络和决策树模型在滑坡易发性分析中的性能对比. 地球信息科学学报, 22(12): 2304-2316. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX202012004.htm 魏志军, 2020. 多级串联深度卷积神经网络医学图像配准方法(硕士学位论文). 长沙: 湖南大学. 吴润泽, 胡旭东, 梅红波, 等, 2021. 基于随机森林的滑坡空间易发性评价: 以三峡库区湖北段为例. 地球科学, 46 (1): 321-330. doi: 10.3799/dqkx.2020.032 曾春艳, 严康, 王志锋, 等, 2021. 深度学习模型可解释性研究综述. 计算机工程与应用, 57(8): 1-9. https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202108002.htm 赵洪宝, 刘瑞, 刘一洪, 等, 2022. 基于深度学习方法的矿山微震信号分类识别研究. 矿业科学学报, 7(2): 166-174. https://www.cnki.com.cn/Article/CJFDTOTAL-KYKX202202003.htm -
点击查看大图
图(8) / 表(3)
计量
- 文章访问数: 1182
- HTML全文浏览量: 632
- PDF下载量: 153
- 被引次数: 0
