A Novel Hybrid Method for Landslide Susceptibility Mapping-Based GeoDetector and Machine Learning Cluster: A Case of Xiaojin County, China

Research on machine learning forecasting and early warning model for rainfall-induced landslides in Yunnan province

Landslides are highly destructive geological disasters that pose a serious threat to the safety of people's lives and property. In this study, historical records of landslides in Yunnan Province, along with eight underlying factors of landslide (elevation, slope, aspect, lithology, land cover type, normalized difference vegetation index (NDVI), soil type, and average annual precipitation (AAP)), as well as historical rainfall and current rainfall data were utilized. Firstly, we analyzed the sensitivity of each underlying factor in the study area using the frequency ratio (FR) method and obtained a landslide susceptibility map (LSM). Then, we constructed a regional rainfall-induced landslides (RIL) probability forecasting model based on machine learning (ML) algorithms and divided warning levels. In order to construct a better RIL prediction model and explore the effects of different ML algorithms and input values of the underlying factor on the model, we compared five ML classification algorithms: extreme gradient boosting (XGBoost), k-nearest neighbor (KNN), support vector machine (SVM), logistic regression (LR), and random forest (RF) algorithms and three representatives of the input values of the underlying factors. The results show that among the obtained forecasting models, the LSM-based RF model performs the best, with an accuracy (ACC) of 0.906, an area under the curve (AUC) of 0.954, a probability of detection (POD) of 0.96 in the test set, and a prediction accuracy of 0.8 in the validation set. Therefore, we recommend using RF-LSM model as the RIL forecasting model for Yunnan Province and dividing warning levels.

Soil erosion vulnerability and soil loss estimation for Siran River watershed, Pakistan: an integrated GIS and remote sensing approach

Soil erosion is a problematic issue with detrimental effects on agriculture and water resources, particularly in countries like Pakistan that heavily rely on farming. The condition of major reservoirs, such as Tarbela, Mangla, and Warsak, is crucial for ensuring an adequate water supply for agriculture in Pakistan. The Kunhar and Siran rivers flow practically parallel, and the environment surrounding both rivers' basins is nearly identical. The Kunhar River is one of KP's dirtiest rivers that carries 0.1 million tons of suspended sediment to the Mangla reservoir. In contrast, the Siran River basin is largely unexplored. Therefore, this study focuses on the Siran River basin in the district of Manshera, Pakistan, aiming to assess annual soil loss and identify erosion-prone regions. Siran River average annual total soil loss million tons/year is 0.154. To achieve this, the researchers integrate Geographical Information System (GIS) and remote sensing (RS) data with the Revised Universal Soil Loss Equation (RUSLE) model. Five key variables, rainfall, land use land cover (LULC), slope, soil types, and crop management, were examined to estimate the soil loss. The findings indicate diverse soil loss causes, and the basin's northern parts experience significant soil erosion. The study estimated that annual soil loss from the Siran River basin is 0.154 million tons with an average rate of 0.871 tons per hectare per year. RUSLE model combined with GIS/RS is an efficient technique for calculating soil loss and identifying erosion-prone areas. Stakeholders such as policymakers, farmers, and conservationists can utilize this information to target efforts and reduce soil loss in specific areas. Overall, the study's results have the potential to advance initiatives aimed at safeguarding the Siran River watershed and its vital resources. Protecting soil resources and ensuring adequate water supplies are crucial for sustainable agriculture and economic development in Pakistan.

Application of genetic algorithm in optimization parallel ensemble-based machine learning algorithms to flood susceptibility mapping using radar satellite imagery

Floods are the natural disaster that occurs most frequently due to the weather and causes the most widespread destruction. The purpose of the proposed research is to analyze flood susceptibility mapping (FSM) in the Sulaymaniyah province of Iraq. This study employed a genetic algorithm (GA) to fine-tune parallel ensemble-based machine learning algorithms (random forest (RF) and bootstrap aggregation (Bagging)). Four machine learning algorithms (RF, Bagging, RF-GA, and Bagging-GA) were used to build FSM in the study area. To provide inputs into parallel ensemble-based machine learning algorithms, we gathered and processed data from meteorological (Rainfall), satellite image (flood inventory, normalized difference vegetation index (NDVI), aspect, land cover, altitude, stream power index (SPI), plan curvature, topographic wetness index (TWI), slope) and geographic sources (geology). For this research, Sentinel-1 synthetic aperture radar (SAR) satellite images were utilized to locate flooded areas and create an inventory map of floods. To train and validate the model, we employed 70 % and 30 % of 160 selected flood locations, respectively. Multicollinearity, frequency ratio (FR), and Geodetector methods were used for data preprocessing. Four metrics were utilized to assess the FSM performance: the root mean square error (RMSE), the area under the receiver-operator characteristic curve (AUC-ROC), the Taylor diagram, and the seed cell area index (SCAI). The results exhibited that all the suggested models have high accuracy of prediction, but the performance of Bagging-GA (RMSE (Train = 0.1793, Test = 0.4543)) was slightly better than RF-GA (RMSE (Train = 0.1803, Test = 0.4563)), Bagging (RMSE (Train = 0.2191, Test = 0.4566)), and RF (RMSE (Train = 0.2529, Test = 0.4724)). According to the ROC index, the Bagging-GA model (AUC = 0.935) was the most accurate in flood susceptibility modeling, followed by the RF-GA (AUC = 0.904), the Bagging (AUC = 0.872), and the RF (AUC = 0.847) models. The study's identification of high-risk flood zones and the most significant factors contributing to flooding make it a helpful resource for flood management.

Estimation of ecological footprint based on tourism development indicators using neural networks and multivariate regression

The ecological footprint has attracted a lot of attention in the top tourism destination countries, and this issue may be worrying. This study aims to estimate the ecological footprint, using such indicators as economic growth, natural resources, human capital, and the number of tourists in top tourism destination countries. For this purpose, artificial neural network models and multivariate regression were used for a period of 24 years (1995-2019). The results of the study showed a significant positive correlation between economic growth and ecological footprint. Multivariate regression estimation (R = 0.75) is weaker than neural network models (R = 96.3). Regarding predicting the ecological footprint, neural network models have better performance in comparison with the multivariate regression statistical methods. Accordingly, one can say that for planning ecological footprint, deeper look at neural networks can be more effective in predicting top tourism destination countries.

Vegetation assessments under the influence of environmental variables from the Yakhtangay Hill of the Hindu-Himalayan range, North Western Pakistan

Vegetation structures and dynamics are the result of interactions between abiotic and biotic factors in an ecosystem. The present study was designed to investigate vegetation structure and species diversity along various environmental variables in the Yakhtangay Hills of the Hindu-Himalayan Mountain Pakistan, by using multivariate statistical analysis. Quadrat quantitative method was used for the sampling of vegetation. PC-ORD version 5 software was used to classify the vegetation into different plants communities using cluster analysis. The results of regression analysis among various edaphic variables shows that soil organic matter, total dissolved solids, electrical conductivity, CaCO₃ and moisture contents shows a significant positive correlation with species abundance, while the soil pH has inverse relationship with plant species abundance. Similarly, species richness increases with increase in soil organic matter, CaCO₃ and moisture contents, while decrease with increase in soil pH, total dissolved solids and electrical conductivity (p < 0.05). The vegetation was classified into four major plant communities and their respective indicators were identified using indicator species analysis. Indicator species analysis reflects the indicators of the study area are mostly the indicators to the Himalayan or moist temperate ecosystem. These indicators could be considered for micro-habitat conservation and respective ecosystem management plans not only in the study area but also in other region with similar sort of environmental conditions.

Prediction of sustainable management of sediment in rivers and reservoirs

Water structure construction has been the subject of heated discussion for more than a decade. The following concepts include integrated management of water basins or continued sustainable development of water basins. Although there are not a lot of underdeveloped water basins, there have been 150 years of dam development. Dams prevent sediment from moving continuously down rivers by trapping it in reservoirs, which reduces the storage capacity and useable life of the reservoirs and prevents downstream reaches of materials necessary for channel form and aquatic ecosystems. Restricted availability of hydrological and geomorphological data hinders current knowledge of sediment characteristics and dynamics, which affects prediction models required for management. This research tested current models for estimating sediment output and transport based on data mining categorization and prediction approaches and assessed their applicability. This work brings together experience from five continents in controlling reservoir sediments and reducing downstream sediment famine of data on the distribution of sediment particle sizes, and manning's roughness coefficient were shown to have the largest influences on the predicted sediment load. Additionally, parameter uncertainty for river geometry and water flow almost doubled, underlining the fact that more knowledge of these variables might significantly enhance our ability to forecast and control present and future sediment dynamics in the river basin.

Slide type landslide susceptibility assessment of the Büyük Menderes watershed using artificial neural network method

The Büyük Menderes watershed is the largest drainage watershed in Western Anatolia with an area of approximately 26,000 km². In the study area, almost 863 landslides occurred, extending over 222 km² with a mean landslide area of 0.21 km². In this study, landslide susceptibility assessments were carried out using artificial neural network method, which is one of the data-driven methods. In this study, that will contribute to the mitigation or control of the landslides caused by the reasons controlling the spatial and temporal distribution of landslides created in the GIS and MATLAB environment by using scientific and technological approaches within the framework. Since derivative activation function is also used in back-propagation artificial neural networks, its derivative is easily calculated in order not to slow down the calculation. Levenberg-Marquardt back-propagation (LM), resilient back propagation back-propagation (trainrp), scaled conjugate gradient back-propagation (trainscg), conjugate gradient with Powell/Beale restarts back-propagation (traincgb), and Fletcher-Powell conjugate gradient back-propagation (traincgf) algorithms are used, which constantly interrogate the link between the input parameter and the result output, and at least one cell's output is given as an input to any other cell. Geology, digital elevation model, slope, topographic wetness index, roughness index, plan, profile curvatures, and proximity to active faults and rivers were used as landslide conditioning factors. In susceptibility assessments, landslides were separated by 70% analysis, 15% test, and 15% validation datasets by random selection method. The performances of the landslide susceptibility maps were assessed by the area under the ROC curve (AUC), accuracy (ACC), precision, recall, F1 score, Kappa test error histogram, and confusion matrix, respectively. The area under the receiver operating characteristic curves, analysis, testing, validation, landslides, and study areas were found between 0.873 and 0.911. The susceptibility map had a high prediction rate in which high and very high susceptible zones corresponded to 26% of the study area including 82% of the recorded landslides.

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

Landslide Susceptibility Assessment Model Construction Using Typical Machine Learning for the Three Gorges Reservoir Area in China

The Three Gorges Reservoir region in China is the Yangtze River Economic Zone’s natural treasure trove. Its natural environment has an important role in development. The unique and fragile ecosystem in the Yangtze River’s Three Gorges Reservoir region is prone to natural disasters, including soil erosion, landslides, debris flows, landslides, and earthquakes. Therefore, to better alleviate these threats, an accurate and comprehensive assessment of the susceptibility of this area is required. In this study, based on the collection of relevant data and existing research results, we applied machine learning models, including logistic regression (LR), the random forest model (RF), and the support vector machine (SVM) model, to analyze landslide susceptibility in the Yangtze River’s Three Gorges Reservoir region to analyze landslide events in the whole study region. The models identified five categories (i.e., topographic, geological, ecological, meteorological, and human engineering activities), with nine independent variables, influencing landslide susceptibility. The accuracy of landslide susceptibility derived from different models and raster cells was then verified by the accuracy, recall, F1-score, ROC curve, and AUC of each model. The results illustrate that the accuracy of different machine learning algorithms is ranked as SVM > RF > LR. The LR model has the lowest generalization ability. The SVM model performs well in all regions of the study area, with an AUC value of 0.9708 for the entire Three Gorges Reservoir area, indicating that the SVM model possesses a strong spatial generalization ability as well as the highest robustness and can be adapted as a real-time model for assessing regional landslide susceptibility.

GIS-Based Comparative Study of the Bayesian Network, Decision Table, Radial Basis Function Network and Stochastic Gradient Descent for the Spatial Prediction of Landslide Susceptibility

Landslides frequently occur along the eastern margin of the Tibetan Plateau, which poses a risk to the construction, maintenance, and transportation of the proposed Dujiangyan city to Siguniang Mountain (DS) railway, China. Therefore, four advanced machine learning models, namely, the Bayesian network (BN), decision table (DTable), radial basis function network (RBFN), and stochastic gradient descent (SGD), are proposed in this study to delineate landslide susceptibility zones. First, a landslide inventory map was randomly divided into 828 (75%) samples and 276 (25%) samples for training and validation, respectively. Second, the One-R technique was utilized to analyze the importance of 14 variables. Then, the prediction capability of the four models was validated and compared in terms of different statistical indices (accuracy (ACC) and Cohen’s kappa coefficient (k)) and the areas under the curve (AUC) in the receiver operating characteristic curve. The results showed that the SGD model performed best (AUC = 0.897, ACC = 80.98%, and k = 0.62), followed by the BN (AUC = 0.863, ACC = 78.80%, and k = 0.58), RBFN (AUC = 0.846, ACC = 77.36%, and k = 0.55), and DTable (AUC = 0.843, ACC = 76.45%, and k = 0.53) models. The susceptibility maps revealed that the DS railway segments from Puyang town to Dengsheng village are in high and very high-susceptibility zones.

Integrating Multivariate (GeoDetector) and Bivariate (IV) Statistics for Hybrid Landslide Susceptibility Modeling: A Case of the Vicinity of Pinios Artificial Lake, Ilia, Greece

Over the last few years, landslides have occurred more and more frequently worldwide, causing severe effects on both natural and human environments. Given that landslide susceptibility (LS) assessments and mapping can spatially determine the potential for landslides in a region, it constitutes a basic step in effective risk management and disaster response. Nowadays, several LS models are available, with each one having its advantages and disadvantages. In order to enhance the benefits and overcome the weaknesses of individual modeling, the present study proposes a hybrid LS model based on the integration of two different statistical analysis models, the multivariate Geographical Detector (GeoDetector) and the bivariate information value (IV). In a GIS-based framework, the hybrid model named GeoDIV was tested to generate a reliable LS map for the vicinity of the Pinios artificial lake (Ilia, Greece), a Greek wetland. A landslide inventory of 60 past landslides and 14 conditioning (morphological, hydro-lithological and anthropogenic) factors was prepared to compose the spatial database. An LS map was derived from the GeoDIV model, presenting the different zones of potential landslides (probability) for the study area. This map was then validated by success and prediction rates—which translate to the accuracy and prediction ability of the model, respectively. The findings confirmed that hybrid modeling can outperform individual modeling, as the proposed GeoDIV model presented better validation results than the IV model.

Spatial and Temporal Characteristics of Hand-Foot-and-Mouth Disease and Their Influencing Factors in Urumqi, China

Hand, foot, and mouth disease (HFMD) remains a serious health threat to young children. Urumqi is one of the most severely affected cities in northwestern China. This study aims to identify the spatiotemporal distribution characteristics of HFMD, and explore the relationships between driving factors and HFMD in Urumqi, Xinjiang.

METHODS

HFMD surveillance data from 2014 to 2018 were obtained from the China Center for Disease Control and Prevention. The center of gravity and geographical detector model were used to analyze the spatiotemporal distribution characteristics of HFMD and identify the association between these characteristics and socioeconomic and meteorological factors.

RESULTS

A total of 10,725 HFMD cases were reported in Urumqi during the study period. Spatially, the morbidity number of HFMD differed regionally and the density was higher in urban districts than in rural districts. Overall, the development of HFMD in Urumqi expanded toward the southeast. Temporally, we observed that the risk of HFMD peaked from June to July. Furthermore, socioeconomic and meteorological factors, including population density, road density, GDP, temperature and precipitation were significantly associated with the occurrence of HFMD.

CONCLUSIONS

HFMD cases occurred in spatiotemporal clusters. Our findings showed strong associations between HFMD and socioeconomic and meteorological factors. We comprehensively considered the spatiotemporal distribution characteristics and influencing factors of HFMD, and proposed some intervention strategies that may assist in predicting the morbidity number of HFMD.