Chinese High Resolution Satellite Data and GIS-Based Assessment of Landslide Susceptibility along Highway G30 in Guozigou Valley Using Logistic Regression and MaxEnt Model

Abstract

Landslide disasters frequently occur along the highway G30 in the Guozigou Valley, the corridor of energy, material, economic and cultural exchange, etc., between Yili and other cities of China and Central Asia. However, little attention has been paid to assess the detailed landslide susceptibility of the strategically important highway, especially with high spatial resolution data and the generative presence-only MaxEnt model. Landslide susceptibility assessment (LSA) is a first and vital step for preventing and mitigating landslide hazards. The goal of the current study was to perform LSA for the landslide-prone highway G30 in Guozigou Valley, China with the aid of GIS tools and Chinese high resolution Gaofen-1 (GF-1) satellite data, and analyze and compare the performance of the maximum entropy (MaxEnt) model and logistic regression (LR). Thirty five landslides were determined in the study region, using GF-1 satellite data, official data, and field surveys. Seven landslide conditioning factors, including altitude, slope, aspect, gully density, lithology, faults density, and NDVI, were used to investigate their existing spatial relationships with landslide occurrences. The LR and MaxEnt model performance were assessed by the receiver operating characteristic curve, presenting areas under the curve equal to 0.85 and 0.94, respectively. The performance of the MaxEnt model was slightly better than that of the LR model. A landslide susceptibility map was created through reclassifying the landslides occurrence probability with the classification method of natural break. According to the MaxEnt model results, 3.29% and 3.82% of the study region is highly and very highly susceptible to future landslide events, respectively, with the highest landslide susceptibility along the highway. The generated landslide susceptibility map could help government agencies and decision-makers to make wise decisions for preventing or mitigating landslide hazards along the highway and design schemes of highway engineering and maintenance in Guozigou Valley, the mountainous areas.

Modeling rules of regional flash flood susceptibility prediction using different machine learning models

“…Using the hydrology function of ArcGIS 10.2 Spatial Analyst Toolbox, streams in the study area are extracted from the DEM. The gully density is also calculated using the ArcGIS Spatial Analyst tool, which is the total length of the streams per unit area (Liu et al, 2022). The distribution of all of the above environmental factors has a significant impact on flash flood development.…”

“…(4) Human activity factors: Highway and population distribution zones are often accompanied by extensive engineering activities, which change the study area's geological characteristics, soil structure, and stress characteristics, thus contributing to the occurrence of geological hazards (Guo et al, 2021;Xiao et al, 2022). Surface radiation is related to Frontiers in Earth Science frontiersin.org absolute surface temperature, which can reflect regional temperature changes, and human activities will also shape surface radiation distribution (Li et al, 2022).…”

“…Although the importance ranking and magnitude of environmental factors differ between machine learning models, they are generally similar. As shown in Figure 8, the environmental factors with a higher importance in the MLP and RF models are elevation, highway density, gully density, rainfall, and population 7.5 Problems and frontiers of machine learning model prediction susceptibility Li et al (2022) proposed a combination of LR and RF models with embedded feature selection for flash flood susceptibility prediction in the mainstream basin of the Songhua River and concluded that both models exhibited accurate and reliable performance. However, the RF model had better prediction performance than the LR model.…”

Feature Engineering of Geohazard Susceptibility Analysis Based on the Random Forest Algorithm: Taking Tianshui City, Gansu Province, as an Example

“…The closer the curve is to the upper left corner, the more accurate the model is. TPR and FPR can be calculated according to Equations ( 12) and (13).…”

Landslide susceptibility mapping based on the coupling of two correlation methods and the BP neural network model: A case study of the Baihetan Reservoir area, China

“…Early landslide susceptibility mapping made substantial use of empirical and statistical analytical methods, such as fuzzy evaluation (Zhao et al, 2017;Salcedo et al, 2018), Certainty factor (CF) model (Wei-dong et al, 2009;Chen et al, 2016) and multiple linear regression (Wenbin et al, 2021). Nowadays, back propagation neural network (BPNN) (Vahidnia Abbas and Hosseinali, 2009;Mohammad H.;Xiong et al, 2019;, support vector machine (SVM) (Huang and Zhao, 2018;Pham et al, 2019;Yu and Chen, 2020), logistic regression (LR) (Abeysiriwardana and Gomes, 2022;Liu et al, 2022), random forest (RF) (Zhao et al, 2020;Sun et al, 2021) and decision tree (DT) (Kadavi et al, 2019;Guo et al, 2021), and other machine learning models, have been found to be applied to regional landslide susceptibility evaluation with high accuracy and significant impact on landslide susceptibility intervals. In this research, we employ BPNN, a common machine learning model, to estimate landslide susceptibility and analyze the accuracy features of its mapping findings.…”