Novel GIS Based Machine Learning Algorithms for Shallow Landslide Susceptibility Mapping

Shirzadi, Ataollah; Soliamani, Karim; Habibnejhad, Mahmood; Kavian, Ataollah; Chapi, Kamran; Shahabi, Himan; Chen, Wei; Khosravi, Khabat; Pham, Binh Thai; Pradhan, Biswajeet; Ahmad, Anuar; Ahmad, Baharin Bin; Bui, Dieu Tien

doi:10.3390/s18113777

Cited by 167 publications

(115 citation statements)

References 74 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…The results illustrate that bagging ADTree and RF-ADTree outperformed ADTree and LR. These results are in line with [42,113,114]. The new model accurately identified the areas that are susceptible to gully erosion based on the past patterns of formation, but it also provides excellent predictions of future development.…”

Section: Discussionsupporting

confidence: 82%

“…In this study, locations at distances less than 100 m from a stream were more likely to see gully formation. Some researchers have confirmed these results [9,13,16,42]. The sheer force of flow can overcome and decrease the strength of soil along the sides of gully forms and lead to the development of gullies of greater dimensions.…”

Section: Discussionmentioning

confidence: 81%

“…The RF and bagging as a meta-classifier can decrease over-fitting and noise problems in the training dataset. Some researchers have confirmed the prediction power of RF in applications to some environmental problems [42,[115][116][117].…”

Section: Discussionmentioning

confidence: 94%

“…However, the RF-ADTree ensemble model outperformed some benchmark models, including SVM based on the polynomial and RBF kernels, LR, naïve Bayes, and ADTtree. Additionally, Shirzadi et al [42] used four meta-classifiers, namely, multiboost, bagging, RF, and random subspace (RS), for the spatial prediction of shallow landslides in Bijar City, Kurdistan province, Iran. They used ADTree as a base classifier for the modeling process.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, machine-learning (ML) techniques have become popular for the spatial prediction of natural hazards like wildfires [22], sinkholes [23], groundwater depletion and flooding [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38], droughts [39], earthquakes [40], land subsidence [41], and landslides [42][43][44][45][46][47][48]. ML is a type of artificial intelligence (AI) that uses computer algorithms to analyze and forecast information by learning from training data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Gully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran

Arabameri

Chen

Blaschke

et al. 2019

Water

Self Cite

View full text Add to dashboard Cite

To more effectively prevent and manage the scourge of gully erosion in arid and semi-arid regions, we present a novel-ensemble intelligence approach-bagging-based alternating decision-tree classifier (bagging-ADTree)-and use it to model a landscape's susceptibility to gully erosion based on 18 gully-erosion conditioning factors. The model's goodness-of-fit and prediction performance are compared to three other machine learning algorithms (single alternating decision tree, rotational-forest-based alternating decision tree (RF-ADTree), and benchmark logistic regression). To achieve this, a gully-erosion inventory was created for the study area, the Chah Mousi watershed, Iran by combining archival records containing reports of gully erosion, remotely sensed data from Google Earth, and geolocated sites of gully head-cuts gathered in a field survey. A total of 119 gully head-cuts were identified and mapped. To train the models' analysis and prediction capabilities, 83 head-cuts (70% of the total) and the corresponding measures of the conditioning factors were input into each model. The results from the models were validated using the data pertaining to the remaining 36 gully locations (30%). Next, the frequency ratio is used to identify which conditioning-factor classes have the strongest correlation with gully erosion. Using random-forest modeling, the relative importance of each of the conditioning factors was determined. Based on the random-forest results, the top eight factors in this study area are distance-to-road, drainage density, distance-to-stream, LU/LC, annual precipitation, topographic wetness index, NDVI, and elevation. Finally, based on goodness-of-fit and AUROC of the success rate curve (SRC) and prediction rate curve (PRC), the results indicate that the bagging-ADTree ensemble model had the best performance, with SRC (0.964) and PRC (0.978). RF-ADTree (SRC = 0.952 and PRC = 0.971), ADTree (SRC = 0.926 and PRC = 0.965), and LR (SRC = 0.867 and PRC = 0.870) were the subsequent best performers. The results also indicate that bagging and RF, as meta-classifiers, improved the performance of the ADTree model as a base classifier. The bagging-ADTree model's results indicate that 24.28% of the study area is classified as having high and very high susceptibility to gully erosion. The new ensemble model accurately Water 2020, 12, 16 2 of 26 identified the areas that are susceptible to gully erosion based on the past patterns of formation, but it also provides highly accurate predictions of future gully development. The novel ensemble method introduced in this research is recommended for use to evaluate the patterns of gullying in arid and semi-arid environments and can effectively identify the most salient conditioning factors that promote the development and expansion of gullies in erosion-susceptible environments.

show abstract

Section: Discussionsupporting

confidence: 82%

Section: Discussionmentioning

confidence: 81%

Section: Discussionmentioning

confidence: 94%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Gully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran

Arabameri

Chen

Blaschke

et al. 2019

Water

Self Cite

View full text Add to dashboard Cite

show abstract

Review on remote sensing methods for landslide detection using machine and deep learning

Mohan

Singh

Kumar

et al. 2020

Trans Emerging Tel Tech

169

View full text Add to dashboard Cite

Landslide, one of the most critical natural hazards, is caused due to specific compositional slope movement. In the past decades, due to inflation of urbanized area and climate change, a compelling expansion in landslide prevalence took place which is also termed as mass/slope movement and mass wasting, causing extensive collapse around the world. The principal reason for its pursuance is a reduction in the internal resistance of soil and rocks, classified as a slide, topple, fall, and flow. Slopes can be differentiated based on earth material and the nature of its movements. The downward flow of landslides occurs due to excessive rainfall, snowmelt, earthquake, volcanic eruption, and so on. This review article revisits the conventional approaches for identification of landslides, predicting future risk, associated with slope failures, followed by emphasizing the advantages of modern geospatial techniques such as aerial photogrammetry, satellite remote sensing images (ie, panchromatic, multispectral, radar images), Terrestrial laser scanning, and High‐Resolution Digital Elevation Model (HR‐DEM) in updating landslide inventory maps. Machine learning techniques like Support Vector Machine, Artificial neural network, deep learning has been extensively used with geographical data producing effective results for assessment of natural hazard/resources and environmental research. Based on recent studies, deep learning is a reliable tool addressing remote sensing challenges such as trade‐off in imaging system producing poor quality investigation, in addition, to expedite consequent task such as image recognition, object detection, classification, and so on. Conventional methods, like pixel and object‐based machine learning methods, have been broadly explored. Advanced development in deep learning technique like CNN (Convolutional neural network) has been extensively successful in information extraction from an image and has exceeded other traditional approaches. Over the past few years, minor attempts have been made for landslide susceptibility mapping using CNN. In addition, small sample sizes for training purpose will be major drawback and notably remarkable while using deep learning techniques. Also, assessment of the model's performance with diverse training and testing proportion other than commonly utilized ratio, that is, 70/30 needs to be explored further. The review article briefly highlights the remote sensing methods for landslide detection using machine learning and deep learning.

show abstract

Delineation of groundwater quality locations suitable for target end‐use purposes through deep neural network models

et al. 2021

View full text Add to dashboard Cite

Groundwater is the main source of water for beverages, and its quality varies depending on extraction location; this is particularly the case in regions with complex geology, topography, and multiple forms of land use. Thus, it is important to determine a suitable groundwater extraction location based on intended water use and the related water quality standards. In this study, deep neural network (DNN) models and GIS data relating to groundwater quality were applied to estimate potential maps of Gangwon Province in South Korea, where groundwater is frequently extracted for drinking purposes. These maps specify areas where the groundwater quality is conducive for being used as mineral water and water for brewing coffee (hereafter referred as "coffee water"). Sensitivity analysis identified how inputs were sensitive to model estimation and showed that land-use variables were the most sensitive. The importance of each variable quantified how good or bad its region is for the desired groundwater. The overall features of importance were similar between mineral water and coffee water. However, with differences in hydrogeological units, carbonate rock was a variable of high positive importance for mineral water; metamorphic rock was its equivalent for coffee water. Our results offer a potential map of desired groundwater quality in the absence of a detailed understanding of the underlying hydrochemical processes governing groundwater quality. Additionally, the development of such a potential mapping model can help to determine the appropriate development area of groundwater for their respective purposes. Abbreviations: DNN, deep neural network. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Novel GIS Based Machine Learning Algorithms for Shallow Landslide Susceptibility Mapping

Cited by 167 publications

References 74 publications

Gully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran

Gully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran

Review on remote sensing methods for landslide detection using machine and deep learning

Delineation of groundwater quality locations suitable for target end‐use purposes through deep neural network models

Contact Info

Product

Resources

About