Landslide Susceptibility Prediction Based on Remote Sensing Images and GIS: Comparisons of Supervised and Unsupervised Machine Learning Models

Landslide susceptibility assessment based on frequency ratio and semi-supervised heterogeneous ensemble learning model

Epistemic uncertainty in data-driven landslide susceptibility assessment often tends to be increased by the limited accuracy of an individual model, as well as uncertainties associated with the selection of non-landslide samples. To address these issues, this paper centers on the landslide disaster in Ji'an City, China, and proposes a heterogeneous ensemble learning method incorporating frequency ratio (FR) and semi-supervised sample expansion. Based on the superimposed results of 12 environmental factor frequency ratios (FFR), non-landslide samples were selected and input into light gradient boosting machine (LightGBM), random forest (RF), and convolutional neural network (CNN) models for prediction along with historical landslide samples. The predicted probability values are integrated by four heterogeneous ensemble strategies to expand samples from high-confidence results. The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC), partition frequency ratio (PFR), and other verification methods. The results demonstrate that the negative sample based on FFR sampling is more accurate than the random sampling method, and the FR-SSELR model based on frequency ratio sampling and semi-supervised ensemble strategy exhibits the highest performance (AUC = 0.971, ACC = 0.941). A more reasonable landslide susceptibility map was drawn based on this model, with the lowest percentage of landslides in the low and very low susceptibility zones (sum of PFR = 0.194), as well as the highest percentage of landslides in the high and very high susceptibility zones (sum of PFR = 6.800). Furthermore, the FR-SSELR model improved economic benefits by 3.82-14.2%, offering valuable guidance for decision-making regarding landslide management and the sustainability of Ji'an City.

Effects of non-landslide sampling strategies on machine learning models in landslide susceptibility mapping

This study aims to explore the effects of different non-landslide sampling strategies on machine learning models in landslide susceptibility mapping. Non-landslide samples are inherently uncertain, and the selection of non-landslide samples may suffer from issues such as noisy or insufficient regional representations, which can affect the accuracy of the results. In this study, a positive-unlabeled (PU) bagging semi-supervised learning method was introduced for non-landslide sample selection. In addition, buffer control sampling (BCS) and K-means (KM) clustering were applied for comparative analysis. Based on landslide data from Qiaojia County, Yunnan Province, China, collected in 2014, three machine learning models, namely, random forest, support vector machine, and CatBoost, were used for landslide susceptibility mapping. The results show that the quality of samples selected using different non-landslide sampling strategies varies significantly. Overall, the quality of non-landslide samples selected using the PU bagging method is superior, and this method performs best when combined with CatBoost for predicting (AUC = 0.897) landslides in very high and high susceptibility zones (82.14%). Additionally, the KM results indicated overfitting, displaying high accuracy for validation but poor statistical outcomes for zoning. The BCS results were the worst.

Land subsidence susceptibility mapping: a new approach to improve decision stump classification (DSC) performance and combine it with four machine learning algorithms

Land subsidence is a worldwide threat. In arid and semiarid lands, groundwater depletion is the main factor that induce the subsidence resulting in environmental damages and socio-economic issues. To foresee and prevent the impact of land subsidence, it is necessary to develop accurate maps of the magnitude and evolution of the subsidences. Land subsidence susceptibility maps (LSSMs) provide one of the effective tools to manage vulnerable areas and to reduce or prevent land subsidence. In this study, we used a new approach to improve decision stump classification (DSC) performance and combine it with machine learning algorithms (MLAs) of naïve Bayes tree (NBTree), J48 decision tree, alternating decision tree (ADTree), logistic model tree (LMT), and support vector machine (SVM) in land subsidence susceptibility mapping (LSSSM). We employ data from 94 subsidence locations, among which 70% were used to train learning hybrid models and the other 30% were used for validation. In addition, the models' performance was assessed by ROC-AUC, accuracy, sensitivity, specificity, odd ratio, root-mean-square error (RMSE), kappa, frequency ratio, and F-score techniques. A comparison of the results obtained from the different models reveals that the new DSC-ADTree hybrid algorithm has the highest accuracy (AUC = 0.983) in preparing LSSSMs as compared to other learning models such as DSC-J48 (AUC = 0.976), DSC-NBTree (AUC = 0.959), DSC-LMT (AUC = 0.948), DSC-SVM (AUC = 0.939), and DSC (AUC = 0.911). The LSSSMs generated through the novel scientific approach presented in our study provide reliable tools for managing and reducing the risk of land subsidence.

Debris flow susceptibility assessment based on information value and machine learning coupling method: from the perspective of sustainable development

Accurately assessing the susceptibility of debris flow disasters is of great significance for reducing the cost of disaster prevention and mitigation, as well as disaster losses. Machine learning (ML) models have been widely used in the susceptibility assessment of debris flow disasters. However, these models often have randomness in the selection of non-disaster data, which can lead to redundant information and poor applicability and accuracy of susceptibility evaluation results. To address this issue, this paper focuses on debris flow disasters in Yongji County, Jilin Province, China; optimizes the sampling method of non-disaster datasets in machine learning susceptibility assessment; and proposes a susceptibility prediction model that couples information value (IV) with artificial neural network (ANN) and logistic regression (LR) models. A debris flow disaster susceptibility distribution map with higher accuracy was drawn based on this model. The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC), information gain ratio (IGR), and typical disaster point verification methods. The results show that the rainfall and topography were found to be decisive factors in the occurrence of debris flow disasters, and the IV-ANN model established in this study had the highest accuracy (AUC = 0.968). Compared to traditional machine learning models, the coupling model produced an increase in economic benefit of about 25% while reducing the average disaster prevention and control investment cost by about 8%. Based on model's susceptibility map, this paper proposes practical disaster prevention and control suggestions that promote sustainable development in the region, such as establishing monitoring systems and information platforms to aid disaster management.

Comparative study on landslide susceptibility mapping based on unbalanced sample ratio

The Zigui-Badong section of the Three Gorges Reservoir area is used as the research area in this study to research the impact of unbalanced sample sets on Landslide Susceptibility Mapping (LSM) and determine the sample ratio interval with the best performance for different models. We employ 12 LSM factors, five training sample sets with different sample ratios (1:1, 1:2, 1:4, 1:8, and 1:16), and C5.0, Support Vector Machine (SVM), Logistic Regression (LR), and one-dimensional Convolution Neural Network (CNN) models are used to obtain landslide susceptibility index and landslide susceptibility zoning in the study area, respectively. The prediction performance of the model is evaluated by the receiver operating characteristic curve area under the curve value, five statistical methods, and specific category precision. The results show that the CNN, SVM, and LR models in the sample ratio of 1:2 achieve better performance than on the balanced sample set, which indicates the importance of the unbalanced sample set in training the LSM modeling. The C5.0 model is always in a state of overfitting in this study and needs to be further studied. The conclusions put forward in this study help improve the scientificity and reliability of LSM.

A novel hybrid random forest linear model approach for forecasting groundwater fluoride contamination

Groundwater quality in the Datong basin is threatened by high fluoride contamination. Laboratory analysis is a standard method for estimating groundwater quality parameters, which is expensive and time-consuming. Therefore, this paper proposes a hybrid random forest linear model (HRFLM) as a novel approach for estimating groundwater fluoride contamination. Light gradient boosting (LightGBM), random forest (RF), and extreme gradient boosting (Xgboost) were also employed in comparison with HRFLM for predicting fluoride contamination in groundwater. 202 groundwater samples were collected to draw up the performance capability of several models in forecasting subsurface water fluoride contamination. The performance of the models was assessed utilizing the receiver operating characteristic (ROC) area under the curve (AUC) and the confusion matrix (CM). The CM results reveal that with nine predictor variables, the hybrid HRFLM achieved an accuracy of 95%, outperforming the Xgboost, LightGBM, and RF models, which attained 88%, 88%, and 85%, respectively. Likewise, the AUC results of the hybrid HRFLM show high performance with an AUC of 0.98 compared to Xgboost, LightGBM, and RF, which achieved an AUC of 0.95, 0.90, and 0.88, respectively. The study demonstrates that the HRFLM can be applied as an advanced approach for groundwater fluoride contamination prediction in the Datong basin and could be adopted in various areas facing a similar challenge.

Optimizing machine learning algorithms for spatial prediction of gully erosion susceptibility with four training scenarios

Gully erosion causes high soil erosion rates and is an environmental concern posing major risk to the sustainability of cultivated areas of the world. Gullies modify the land, shape new landforms, and damage agricultural fields. Gully erosion mapping is essential to understand the mechanism, development, and evolution of gullies. In this work, a new modeling approach was employed for gully erosion susceptibility mapping (GESM) in the Golestan Dam basin of Iran. The measurements of 14 gully erosion (GE) factors at 1042 GE locations were compiled in a spatial database. Four training datasets comprised of 100%, 75%, 50%, and 25% of the entire database were used for modeling and validation (for each data set in the common 70:30 ratio). Four machine learning models-maximum entropy (MaxEnt), general linear model (GLM), support vector machine (SVM), and artificial neural network (ANN)- were employed to check the usefulness of the four training scenarios. The results of random forest (RF) analysis indicated that the most important GE effective factors were distance from the stream, elevation, distance from the road, and vertical distance of the channel network (VDCN). The receiver operating characteristic (ROC) was used to validate the results. Our study showed that the sample size influenced the performance of the four machine learning algorithms. However, the ANN had a lower sensitivity to the reduction of sample size. In addition, validation results revealed that ANN (AUROC = 0.85.7-0.90.4%) had the best performance based on all four sample data sets. The results of this research can be useful and valuable guidelines for choosing machine learning methods when a complete gully inventory is not available in a region.

Durability Performance and Corrosion Mechanism of New Basalt Fiber Concrete under Organic Water Environment

Under corrosive environments, concrete material properties can deteriorate significantly, which can seriously affect structural safety. Therefore, it has important engineering applications to improve the durability performance at a lower economic cost. This paper proposes a new, highly durable concrete using inexpensive construction materials such as basalt fiber, sodium methyl silicate, and inorganic aluminum salt waterproofing agent. With the massive application of sewage treatment projects, the problem of concrete durability degradation is becoming more and more serious. In this paper, five types of concrete are developed for the sewage environment, and the apparent morphology and fine structure of the specimens after corrosion in sewage were analyzed. The density, water absorption, and compressive strength were measured to investigate the deterioration pattern of concrete properties. It was found that ordinary concrete was subject to significant corrosion, generating large deposits of algae on the surface and accompanied by sanding. The new concrete showed superior corrosion resistance compared to conventional concrete. Among other factors, the inorganic aluminum salt waterproofing agent effect was the most prominent. The study found that the strength of ordinary concrete decreased by about 15% in the test environment, while the new concrete had a slight increase. Comprehensive evaluation showed that the combination of basalt fiber and inorganic aluminum salt waterproofing agent had the best effect. Its use is recommended.

Application of convolutional neural networks based on Bayesian optimization to landslide susceptibility mapping of transmission tower foundation

The stability of tower foundation slopes is an important factor to maintain the operation of a power system. However, it is time-consuming and expensive to evaluate tower foundation slopes one by one due to the large area. The aim of this study is to investigate the performance of CNNs with different architectures and training options for transmission tower foundation landslide spatial prediction (LSP) by Bayesian optimization. Accordingly, fourteen influencing factors related to landslide evaluated by gain ratio technique are considered and 424 historical landslide locations in Luoding and Xinyi Counties (Guangdong Province, China) are randomly divided into 80% for training and 20% for testing the CNNs. The CNN performances are investigated by permutating and combining different numbers of convolutional layers, pooling layers and learning rate strategy. In 59 Bayesian optimized cases, three conclusions are drawn: (a) the CNNs yielded the best result with 3 convolution layers, (b) the CNN without a pooling layer performs best, and (c) a piece-wise decay learning rate strategy yields better performance. Meanwhile, the excellent performance of the CNN obtained by Bayesian optimization (CNNB) has also been validated by comparisons with gravitational search optimization algorithm and other landslide spatial models, which indicates that CNNB can be applied to generate the susceptibility maps for locating transmission tower foundations in high landslide susceptibility zones and reducing the impact of landslides on power supply by taking measures in advance.

A bibliometric and content analysis of research trends on GIS-based landslide susceptibility from 2001 to 2020

To assess the status of hotspots and research trends on geographic information system (GIS)-based landslide susceptibility (LS), we analysed 1142 articles from the Thomas Reuters Web of Science Core Collection database published during 2001-2020 by combining bibliometric and content analysis. The paper number, authors, institutions, corporations, publication sources, citations, and keywords are noted as sub/categories for the bibliometric analysis. Thematic LS data, including the study site, landslide inventory, conditioning factors, mapping unit, susceptibility models, and mode fit/prediction performance evaluation, are presented in the content analysis. Then, we reveal the advantages and limitations of the common approaches used in thematic LS data and summarise the development trends. The results indicate that the distribution of articles shows clear clusters of authors, institutions, and countries with high academic activity. The application of remote sensing technology for interpreting landslides provides a more convenient and efficient landslide inventory. In the landslide inventory, most of the sample strategies representing the landslides are point and polygon, and the most frequently used sample subdividing strategy is random sampling. The scale effects, lack of geographic consistency, and no standard are key problems in landslide conditioning factors. Feature selection is used to choose the factors that can improve the model's accuracy. With advances in computing technology and artificial intelligence, LS models are changing from simple qualitative and statistical models to complex machine learning and hybrid models. Finally, five future research opportunities are revealed. This study will help investigators clarify the status of LS research and provide guidance for future research.

Evaluation of Landslide Susceptibility Based on CF-SVM in Nujiang Prefecture

At present, landslide susceptibility assessment (LSA) based on landslide characteristics in different areas is an effective measure for landslide management. Nujiang Prefecture in China has steep mountain slopes, a large amount of water and loose soil, and frequent landslide disasters, which have caused a large number of casualties and economic losses. This paper aims to understand the characteristics and formation mechanism of regional landslides through the evaluation of landslide susceptibility so as to provide relevant references and suggestions for spatial planning and disaster prevention and mitigation in Nujiang Prefecture. Based on the grid cell, this study selected 10 parameters, namely elevation, slope, aspect, lithology, proximity to faults, proximity to road, proximity to rivers, normalized difference vegetation index (NDVI), land-use type, and precipitation. Support vector machine (SVM), certainty factor method (CF), and deterministic coefficient method-support vector machine (CF-SVM) were used to evaluate the landslide susceptibility in Nujiang Prefecture. According to these three models, the study area was divided into five landslide susceptibility grades, including extremely high susceptibility, high susceptibility, moderate susceptibility, low susceptibility, and very low susceptibility. Receiver operating characteristic curve (ROC) was applied to verify the accuracy of the model. The results showed that CF model (ROC = 0.865), SVM model (ROC = 0.892), CF-SVM model (ROC = 0.925), and CF-SVM model showed better performance. Therefore, CF-SVM model results were selected for analysis. The study found that the characteristics of high and extremely high landslide-prone areas in Nujiang Prefecture have the following characteristics: intense human activities, large density of buildings and arable land, rich water resources, good economic development, perfect transportation facilities, and complex topography and landform. In addition, there is a finding inconsistent with our common sense that the distribution of landslide disasters in the study area does not decrease with the increase of NDVI value. This is because the Nujiang River basin is a high mountain canyon area with low rock strength, barren soil, and underdeveloped vegetation and root system. In an area with large slope, the probability of landslide disaster will increase with the increase of NDVI. The CF-SVM coupling model adopted in this study is a good first attempt in the study of landslide hazard susceptibility in Nujiang Prefecture.

Landslide Susceptibility Mapping Based on the Germinal Center Optimization Algorithm and Support Vector Classification

A landslide susceptibility model based on a metaheuristic optimization algorithm (germinal center optimization (GCO)) and support vector classification (SVC) is proposed and applied to landslide susceptibility mapping in the Three Gorges Reservoir area in this paper. The proposed GCO-SVC model was constructed via the following steps: First, data on 11 influencing factors and 292 landslide polygons were collected to establish the spatial database. Then, after the influencing factors were subjected to multicollinearity analysis, the data were randomly divided into training and testing sets at a ratio of 7:3. Next, the SVC model with 5-fold cross-validation was optimized by hyperparameter space search using GCO to obtain the optimal hyperparameters, and then the best model was constructed based on the optimal hyperparameters and training set. Finally, the best model acquired by GCO-SVC was applied for landslide susceptibility mapping (LSM), and its performance was compared with that of 6 popular models. The proposed GCO-SVC model achieved better performance (0.9425) than the genetic algorithm support vector classification (GA-SVC; 0.9371), grid search optimized support vector classification (GRID-SVC; 0.9198), random forest (RF; 0.9085), artificial neural network (ANN; 0.9075), K-nearest neighbor (KNN; 0.8976), and decision tree (DT; 0.8914) models in terms of the area under the receiver operating characteristic curve (AUC), and the trends of the other metrics were consistent with that of the AUC. Therefore, the proposed GCO-SVC model has some advantages in LSM and may be worth promoting for wide use.

Automatic Semantic Segmentation of Benthic Habitats Using Images from Towed Underwater Camera in a Complex Shallow Water Environment

Underwater image segmentation is useful for benthic habitat mapping and monitoring; however, manual annotation is time-consuming and tedious. We propose automated segmentation of benthic habitats using unsupervised semantic algorithms. Four such algorithms––Fast and Robust Fuzzy C-Means (FR), Superpixel-Based Fast Fuzzy C-Means (FF), Otsu clustering (OS), and K-means segmentation (KM)––were tested for accuracy for segmentation. Further, YCbCr and the Commission Internationale de l’Éclairage (CIE) LAB color spaces were evaluated to correct variations in image illumination and shadow effects. Benthic habitat field data from a geo-located high-resolution towed camera were used to evaluate proposed algorithms. The Shiraho study area, located off Ishigaki Island, Japan, was used, and six benthic habitats were classified. These categories were corals (Acropora and Porites), blue corals (Heliopora coerulea), brown algae, other algae, sediments, and seagrass (Thalassia hemprichii). Analysis showed that the K-means clustering algorithm yielded the highest overall accuracy. However, the differences between the KM and OS overall accuracies were statistically insignificant at the 5% level. Findings showed the importance of eliminating underwater illumination variations and outperformance of the red difference chrominance values (Cr) in the YCbCr color space for habitat segmentation. The proposed framework enhanced the automation of benthic habitat classification processes.

Landslide Susceptibility Assessment Using an AutoML Framework

The risks associated with landslides are increasing the personal losses and material damages in more and more areas of the world. These natural disasters are related to geological and extreme meteorological phenomena (e.g., earthquakes, hurricanes) occurring in regions that have already suffered similar previous natural catastrophes. Therefore, to effectively mitigate the landslide risks, new methodologies must better identify and understand all these landslide hazards through proper management. Within these methodologies, those based on assessing the landslide susceptibility increase the predictability of the areas where one of these disasters is most likely to occur. In the last years, much research has used machine learning algorithms to assess susceptibility using different sources of information, such as remote sensing data, spatial databases, or geological catalogues. This study presents the first attempt to develop a methodology based on an automatic machine learning (AutoML) framework. These frameworks are intended to facilitate the development of machine learning models, with the aim to enable researchers focus on data analysis. The area to test/validate this study is the center and southern region of Guerrero (Mexico), where we compare the performance of 16 machine learning algorithms. The best result achieved is the extra trees with an area under the curve (AUC) of 0.983. This methodology yields better results than other similar methods because using an AutoML framework allows to focus on the treatment of the data, to better understand input variables and to acquire greater knowledge about the processes involved in the landslides.

Automated Landslide-Risk Prediction Using Web GIS and Machine Learning Models

Spatial susceptible landslide prediction is the one of the most challenging research areas which essentially concerns the safety of inhabitants. The novel geographic information web (GIW) application is proposed for dynamically predicting landslide risk in Chiang Rai, Thailand. The automated GIW system is coordinated between machine learning technologies, web technologies, and application programming interfaces (APIs). The new bidirectional long short-term memory (Bi-LSTM) algorithm is presented to forecast landslides. The proposed algorithm consists of 3 major steps, the first of which is the construction of a landslide dataset by using Quantum GIS (QGIS). The second step is to generate the landslide-risk model based on machine learning approaches. Finally, the automated landslide-risk visualization illustrates the likelihood of landslide via Google Maps on the website. Four static factors are considered for landslide-risk prediction, namely, land cover, soil properties, elevation and slope, and a single dynamic factor i.e., precipitation. Data are collected to construct a geospatial landslide database which comprises three historical landslide locations—Phu Chifa at Thoeng District, Ban Pha Duea at Mae Salong Nai, and Mai Salong Nok in Mae Fa Luang District, Chiang Rai, Thailand. Data collection is achieved using QGIS software to interpolate contour, elevation, slope degree and land cover from the Google satellite images, aerial and site survey photographs while the physiographic and rock type are on-site surveyed by experts. The state-of-the-art machine learning models have been trained i.e., linear regression (LR), artificial neural network (ANN), LSTM, and Bi-LSTM. Ablation studies have been conducted to determine the optimal parameters setting for each model. An enhancement method based on two-stage classifications has been presented to improve the landslide prediction of LSTM and Bi-LSTM models. The landslide-risk prediction performances of these models are subsequently evaluated using real-time dataset and it is shown that Bi-LSTM with Random Forest (Bi-LSTM-RF) yields the best prediction performance. Bi-LSTM-RF model has improved the landslide-risk predicting performance over LR, ANNs, LSTM, and Bi-LSTM in terms of the area under the receiver characteristic operator (AUC) scores by 0.42, 0.27, 0.46, and 0.47, respectively. Finally, an automated web GIS has been developed and it consists of software components including the trained models, rainfall API, Google API, and geodatabase. All components have been interfaced together via JavaScript and Node.js tool.

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Landslides are one of the major geohazards threatening human society. The objective of this study was to conduct a landslide hazard susceptibility assessment for Ruijin, Jiangxi, China, and to provide technical support to the local government for implementing disaster reduction and prevention measures. Machine learning approaches, e.g., random forests (RFs) and support vector machines (SVMs) were employed and multiple geo-environmental factors such as land cover, NDVI, landform, rainfall, lithology, and proximity to faults, roads, and rivers, etc., were utilized to achieve our purposes. For categorical factors, three processing approaches were proposed: simple numerical labeling (SNL), weight assignment (WA)-based and frequency ratio (FR)-based. Then 19 geo-environmental factors were respectively converted into raster to constitute three 19-band datasets, i.e., DS1, DS2, and DS3 from three different processes. Then, 155 observed landslides that occurred in the past decades were vectorized, among which 70% were randomly selected to compose a training set (TS1) and the remaining 30% to form a validation set (VS1). A number of non-landslide (no-risk) samples distributed in the whole study area were identified in low slope (<1–3°) zones such as urban areas and croplands, and also added to the TS1 and VS1 in the same ratio. For comparison, we used the FR approach to identify the no-risk samples in both flat and non-flat areas, and merged them into the field-observed landslides to constitute another pair of training and validation sets (TS2 and VS2) using the same ratio of 7:3. The RF algorithm was applied to model the probability of the landslide occurrence using DS1, DS2, and DS3 as predictive variables and TS1 and TS2 for training to obtain the SNL-based, WA-based, and FR-based RF models, respectively. Verified against VS1 and VS2, the three models have similar overall accuracy (OA) and Kappa coefficient (KC), which are 89.61%, 91.47%, and 94.54%, and 0.7926, 0.8299, and 0.8908, respectively. All of them are much better than the three models obtained by SVM algorithm with OA of 81.79%, 82.86%, and 83%, and KC of 0.6337, 0.655, and 0.660. New case verification with the recent 26 landslide events of 2017–2020 revealed that the landslide susceptibility map from WA-based RF modeling was able to properly identify the high and very high susceptibility zones where 23 new landslides had occurred, and performed better than the SNL-based and FR-based RF modeling, though the latter has a slightly higher OA and KC. Hence, we concluded that all three RF models achieve reasonable risk prediction, but WA-based and FR-based RF modeling deserves a recommendation for application elsewhere. The results of this study may serve as reference for the local authorities in prevention and early warning of landslide hazards.

A Hybrid Model Consisting of Supervised and Unsupervised Learning for Landslide Susceptibility Mapping

Landslides cause huge damage to social economy and human beings every year. Landslide susceptibility mapping (LSM) occupies an important position in land use and risk management. This study is to investigate a hybrid model which makes full use of the advantage of supervised learning model (SLM) and unsupervised learning model (ULM). Firstly, ten continuous variables were used to develop a ULM which consisted of factor analysis (FA) and k-means cluster for a preliminary landslide susceptibility map. Secondly, 351 landslides with “1” label were collected and the same number of non-landslide samples with “0” label were selected from the very low susceptibility area in the preliminary map, constituting a new priori condition for a SLM, and thirteen factors were used for the modeling of gradient boosting decision tree (GBDT) which represented for SLM. Finally, the performance of different models was verified using related indexes. The results showed that the performance of the pretreated GBDT model was improved with sensitivity, specificity, accuracy and the area under the curve (AUC) values of 88.60%, 92.59%, 90.60% and 0.976, respectively. It can be concluded that a pretreated model with strong robustness can be constructed by increasing the purity of samples.

A Comparison Method for 3D Laser Point Clouds in Displacement Change Detection for Arch Dams

Dam deformation monitoring can directly identify the safe operation state of a dam in advance, which plays an important role in dam safety management. Three-dimensional (3D) terrestrial laser scanning technology is widely used in the field of deformation monitoring due to its fast, complete, and high-density 3D data acquisition capabilities. However, 3D point clouds are characterized by rough surfaces, discrete distributions, which affect the accuracy of deformation analysis of two states data. In addition, it is impossible to directly extract the correspondence points from an irregularly distributed point cloud to unify the coordinates of the two states’ data, and the correspondence lines and planes are often difficult to obtain in the natural environment. To solve the above problems, this paper studies a displacement change detection method for arch dams based on two-step point cloud registration and contour model comparison method. In the environment around a dam, the stable rock is used as the correspondence element to improve the registration accuracy, and a two-step registration method from rough to fine using the iterative closest point algorithm is present to describe the coordinate unification of the two states’ data without control network and target. Then, to analyze the displacement variation of an arch dam surface in two states and improve the accuracy of comparing the two surfaces without being affected by the roughness of the point cloud, the contour model fitting the point clouds is used to compare the change in distance between models. Finally, the method of this paper is applied to the Xiahuikeng Arch Dam, and the displacement changes of the entire dam in different periods are visualized by comparing with the existing methods. The results show that the displacement change in the middle area of the dam is generally greater than that of the two banks, increasing with the increase in elevation, which is consistent with the displacement change behavior of the arch dam during operation and can reach millimeter-level accuracy.

Uncertainties Analysis of Collapse Susceptibility Prediction Based on Remote Sensing and GIS: Influences of Different Data-Based Models and Connections between Collapses and Environmental Factors

To study the uncertainties of a collapse susceptibility prediction (CSP) under the coupled conditions of different data-based models and different connection methods between collapses and environmental factors, An’yuan County in China with 108 collapses is used as the study case, and 11 environmental factors are acquired by data analysis of Landsat TM 8 and high-resolution aerial images, using a hydrological and topographical spatial analysis of Digital Elevation Modeling in ArcGIS 10.2 software. Accordingly, 20 coupled conditions are proposed for CSP with five different connection methods (Probability Statistics (PSs), Frequency Ratio (FR), Information Value (IV), Index of Entropy (IOE) and Weight of Evidence (WOE)) and four data-based models (Analytic Hierarchy Process (AHP), Multiple Linear Regression (MLR), C5.0 Decision Tree (C5.0 DT) and Random Forest (RF)). Finally, the CSP uncertainties are assessed using the area under receiver operation curve (AUC), mean value, standard deviation and significance test, respectively. Results show that: (1) the WOE-based models have the highest AUC accuracy, lowest mean values and average rank, and a relatively large standard deviation; the mean values and average rank of all the FR-, IV- and IOE-based models are relatively large with low standard deviations; meanwhile, the AUC accuracies of FR-, IV- and IOE-based models are consistent but higher than those of the PS-based model. Hence, the WOE exhibits a greater spatial correlation performance than the other four methods. (2) Among all the data-based models, the RF model has the highest AUC accuracy, lowest mean value and mean rank, and a relatively large standard deviation. The CSP performance of the RF model is followed by the C5.0 DT, MLR and AHP models, respectively. (3) Under the coupled conditions, the WOE-RF model has the highest AUC accuracy, a relatively low mean value and average rank, and a high standard deviation. The PS-AHP model is opposite to the WOE-RF model. (4) In addition, the coupled models show slightly better CSP performances than those of the single data-based models not considering connect methods. The CSP performance of the other models falls somewhere in between. It is concluded that the WOE-RF is the most appropriate coupled condition for CSP than the other models.

MODIS Sensor Capability to Burned Area Mapping-Assessment of Performance and Improvements Provided by the Latest Standard Products in Boreal Regions

This paper presents an accuracy assessment of the main global scale Burned Area (BA) products, derived from daily images of the Moderate-Resolution Imaging Spectroradiometer (MODIS) Fire_CCI 5.1 and MCD64A1 C6, as well as the previous versions of both products (Fire_CCI 4.1 and MCD45A1 C5). The exercise was conducted on the boreal region of Alaska during the period 2000–2017. All the BA polygons registered by the Alaska Fire Service were used as reference data. Both new versions doubled the annual BA estimate compared to the previous versions (66% for Fire_CCI 5.1 versus 35% for v4.1, and 63% for MCD64A1 C6 versus 28% for C5), reducing the omission error (OE) by almost one half (39% versus 67% for Fire_CCI and 48% versus 74% for MCD) and slightly increasing the commission error (CE) (7.5% versus 7% for Fire_CCI and 18% versus 7% for MCD). The Fire_CCI 5.1 product (CE = 7.5%, OE = 39%) presented the best results in terms of positional accuracy with respect to MCD64A1 C6 (CE = 18%, OE = 48%). These results suggest that Fire_CCI 5.1 could be suitable for those users who employ BA standard products in geoinformatics analysis techniques for wildfire management, especially in Boreal regions. The Pareto boundary analysis, performed on an annual basis, showed that there is still a potential theoretical capacity to improve the MODIS sensor-based BA algorithms.

Assessment of Landslide Susceptibility Combining Deep Learning with Semi-Supervised Learning in Jiaohe County, Jilin Province, China

Accurate and timely landslide susceptibility mapping (LSM) is essential to effectively reduce the risk of landslide. In recent years, deep learning has been successfully applied to landslide susceptibility assessment due to the strong ability of fitting. However, in actual applications, the number of labeled samples is usually not sufficient for the training component. In this paper, a deep neural network model based on semi-supervised learning (SSL-DNN) for landslide susceptibility is proposed, which makes full use of a large number of spatial information (unlabeled data) with limited labeled data in the region to train the mode. Taking Jiaohe County in Jilin Province, China as an example, the landslide inventory from 2000 to 2017 was collected and 12 metrological, geographical, and human explanatory factors were compiled. Meanwhile, supervised models such as deep neural network (DNN), support vector machine (SVM), and logistic regression (LR) were implemented for comparison. Then, the landslide susceptibility was plotted and a series of evaluation tools such as class accuracy, predictive rate curves (AUC), and information gain ratio (IGR) were calculated to compare the prediction of models and factors. Experimental results indicate that the proposed SSL-DNN model (AUC = 0.898) outperformed all the comparison models. Therefore, semi-supervised deep learning could be considered as a potential approach for LSM.

Landslide Susceptibility Prediction Considering Regional Soil Erosion Based on Machine-Learning Models

Soil erosion (SE) provides slide mass sources for landslide formation, and reflects long-term rainfall erosion destruction of landslides. Therefore, it is possible to obtain more reliable landslide susceptibility prediction results by introducing SE as a geology and hydrology-related predisposing factor. The Ningdu County of China is taken as a research area. Firstly, 446 landslides are obtained through government disaster survey reports. Secondly, the SE amount in Ningdu County is calculated and nine other conventional predisposing factors are obtained under both 30 m and 60 m grid resolutions to determine the effects of SE on landslide susceptibility prediction. Thirdly, four types of machine-learning predictors with 30 m and 60 m grid resolutions—C5.0 decision tree (C5.0 DT), logistic regression (LR), multilayer perceptron (MLP) and support vector machine (SVM)—are applied to construct the landslide susceptibility prediction models considering the SE factor as SE-C5.0 DT, SE-LR, SE-MLP and SE-SVM models; C5.0 DT, LR, MLP and SVM models with no SE are also used for comparisons. Finally, the area under receiver operating feature curve is used to verify the prediction accuracy of these models, and the relative importance of all the 10 predisposing factors is ranked. The results indicate that: (1) SE factor plays the most important role in landslide susceptibility prediction among all 10 predisposing factors under both 30 m and 60 m resolutions; (2) the SE-based models have more accurate landslide susceptibility prediction than the single models with no SE factor; (3) all the models with 30 m resolutions have higher landslide susceptibility prediction accuracy than those with 60 m resolutions; and (4) the C5.0 DT and SVM models show higher landslide susceptibility prediction performance than the MLP and LR models.

Landslide Susceptibility Mapping: Machine and Ensemble Learning Based on Remote Sensing Big Data

Predicting landslide occurrences can be difficult. However, failure to do so can be catastrophic, causing unwanted tragedies such as property damage, community displacement, and human casualties. Research into landslide susceptibility mapping (LSM) attempts to alleviate such catastrophes through the identification of landslide prone areas. Computational modelling techniques have been successful in related disaster scenarios, which motivate this work to explore such modelling for LSM. In this research, the potential of supervised machine learning and ensemble learning is investigated. Firstly, the Flexible Discriminant Analysis (FDA) supervised learning algorithm is trained for LSM and compared against other algorithms that have been widely used for the same purpose, namely Generalized Logistic Models (GLM), Boosted Regression Trees (BRT or GBM), and Random Forest (RF). Next, an ensemble model consisting of all four algorithms is implemented to examine possible performance improvements. The dataset used to train and test all the algorithms consists of a landslide inventory map of 227 landslide locations. From these sources, 13 conditioning factors are extracted to be used in the models. Experimental evaluations are made based on True Skill Statistic (TSS), the Receiver Operation characteristic (ROC) curve and kappa index. The results show that the best TSS (0.6986), ROC (0.904) and kappa (0.6915) were obtained by the ensemble model. FDA on its own seems effective at modelling landslide susceptibility from multiple data sources, with performance comparable to GLM. However, it slightly underperforms when compared to GBM (BRT) and RF. RF seems most capable compared to GBM, GLM, and FDA, when dealing with all conditioning factors.

Landslide Susceptibility Prediction Modeling Based on Remote Sensing and a Novel Deep Learning Algorithm of a Cascade-Parallel Recurrent Neural Network

Landslide susceptibility prediction (LSP) modeling is an important and challenging problem. Landslide features are generally uncorrelated or nonlinearly correlated, resulting in limited LSP performance when leveraging conventional machine learning models. In this study, a deep-learning-based model using the long short-term memory (LSTM) recurrent neural network and conditional random field (CRF) in cascade-parallel form was proposed for making LSPs based on remote sensing (RS) images and a geographic information system (GIS). The RS images are the main data sources of landslide-related environmental factors, and a GIS is used to analyze, store, and display spatial big data. The cascade-parallel LSTM-CRF consists of frequency ratio values of environmental factors in the input layers, cascade-parallel LSTM for feature extraction in the hidden layers, and cascade-parallel full connection for classification and CRF for landslide/non-landslide state modeling in the output layers. The cascade-parallel form of LSTM can extract features from different layers and merge them into concrete features. The CRF is used to calculate the energy relationship between two grid points, and the extracted features are further smoothed and optimized. As a case study, the cascade-parallel LSTM-CRF was applied to Shicheng County of Jiangxi Province in China. A total of 2709 landslide grid cells were recorded and 2709 non-landslide grid cells were randomly selected from the study area. The results show that, compared with existing main traditional machine learning algorithms, such as multilayer perception, logistic regression, and decision tree, the proposed cascade-parallel LSTM-CRF had a higher landslide prediction rate (positive predictive rate: 72.44%, negative predictive rate: 80%, total predictive rate: 75.67%). In conclusion, the proposed cascade-parallel LSTM-CRF is a novel data-driven deep learning model that overcomes the limitations of traditional machine learning algorithms and achieves promising results for making LSPs.