Landslide Susceptibility Mapping Using Ant Colony Optimization Strategy and Deep Belief Network in Jiuzhaigou Region

Abstract

Landslide susceptibility mapping (LSM) is the primary link of geological disaster risk evaluation, which is significant for post-earthquake emergency response and rebuilding after disasters. Existing LSM studies applying deep learning (DL) methods have shortcomings such as easy overfitting, slow convergence, and insufficient hyperparametric optimization. In response to these problems, this study proposes an ensemble model based on ant colony optimization strategy and deep belief network (ACO-DBN). In ACO-DBN, DL optimization strategies were added to DBN and their combined parameters were optimized with ACO. Next, Pearson's correlation coefficient and random forest importance ranking methods were utilized to optimize landslide causative factors. Then, the Jiuzhaigou earthquake region was selected as an example to explore the applicability of this model. Besides, we conducted the Wilcoxon signed rank test in order to verify that the differences were statistically significant. In a comprehensive comparative all indexes and landslide density, the model proposed in this paper shows good rationality, scientificity, and interpretability. The newly occurred landslide site further demonstrates that heuristically optimized DL could make scientific and accurate evaluation of landslide susceptibility.Index Terms-ant colony optimization (ACO) algorithm, deep belief network (DBN), Jiuzhaigou earthquake, landslide susceptibility mapping (LSM). I. INTRODUCTIONs one of the most common geological hazards worldwide, landslides have caused huge human casualties and economic losses every year. Especially in China, landslides are the most widespread and costly geological disasters [1]. According to the statistics yearbook of the Geological Disaster Guidance Center of the Ministry of Natural Resources, in 2020, there were 7840 geological disasters in China, of which 4810 Manuscript received xx xx, xx.

Landslide Susceptibility Modeling Using a Deep Random Neural Network

“…• A DNN model with greedy unsupervised learning [52] • SSL-DNN: A novel DNN model with semi-supervised learning [53] • A kernel-based DNN [54] • ACO-DBN: The DNN was integrated with the ant colony optimization strategy [55] • A robust DNN model based on the combination of a DNN, extreme learning machine, ANN, and genetic algorithm [56] • A DNN model with the particle swarm algorithm [57] • A DNN model integrated with the SVM [58] Convolution neural network (CNN)…”

A Study of Optimization in Deep Neural Networks for Regression

“…Supplementing average value [16,17], linear interpolation [17,18], KNN [19,20] Dimensionality reduction PCA [8], pooling layer [21], t-SNE [22], SPCA [23] Removing outliers Pauta criterion [18], EWMA [24] Feature selection PSO [1], LASSO [8,25], ASO [26], GA [27], MI [28], GRA [29], PCC [30], CCA [31] Decomposition EMD [32], EEMD [33], CEEMDAN [19,27,[34][35][36][37][38], ICEEMDAN [39], SSA [40,41], VMD [42], SVMD [43] Normalization [6,17,20,27,30,31,34,42,[44][45][46][47][48][49]…”

“…Several studies have revealed that adjusting the models' hyperparameters through algorithms can achieve better performance. Xiong et al [6] proposed an ensemble deep learning model that combined the ant colony optimization (ACO) strategy and deep belief networks to solve the problem of landslide susceptibility mapping. The numerical results illustrated that the ensemble model could provide better performance due to the use of ACO for optimizing multiple parameters simultaneously.…”

Landslide Susceptibility Evaluation Based on Potential Disaster Identification and Ensemble Learning

“…The data-driven methods primarily consist of logistic regression [ 33 ], frequency ratio [ 34 ], weights of evidence [ 35 ], Information value [ 36 ], shallow machine learning (e.g., support vector machine [ 37 ], artificial neural network [ 38 ], random forest [ 39 ], and decision tree [ 40 ]), and deep learning (e.g., convolutional neural network [ 41 ], deep neural network [ 42 ], recurrent neural network [ 43 ], and deep belief network [ 44 ]) methods. Moreover, some ensemble methods were employed in LSE, including the combination of ant colony optimization and deep belief network [ 45 ], the ensemble of a radial basis function neural network, random subspace, attribute selected classifier, cascade generalization, and dagging [ 46 ], bagging based reduced error pruning trees [ 47 ] and so on. However, the vast majority of present studies conducted LSE based on optical images and known landslides and neglected the serious threat posed by potential landslides.…”