Evaluation of Conditioning Factors of Slope Instability and Continuous Change Maps in the Generation of Landslide Inventory Maps Using Machine Learning (ML) Algorithms

Abstract

Landslides are recognized as high-impact natural hazards in different regions around the world; therefore, they are extensively researched by experts. Landslide inventories are essential to identify areas that are likely to be affected in the future, thereby enabling interventions to prevent loss of life. Today, through combined approaches, such as remote sensing and machine learning techniques, it is possible to apply algorithms that use data derived from satellite images to produce landslide inventories. This work presents the performance of five machine learning methods—k-nearest neighbor (KNN), stochastic gradient descendent (SGD), support vector machine radial basis function (SVM RBF Kernel), support vector machine (SVM linear kernel), and AdaBoost—in landslide detection in a zone of the state of Guerrero in southern Mexico, using continuous change maps and primary landslide factors, such as slope angle, terrain orientation (aspect), and lithology, as inputs. The models were trained with 2/3 of ground truth samples of 671 slidden/non-slidden polygons. The obtained inventory maps were evaluated with the remaining 1/3 of ground truth samples by generating a confusion matrix and applying the Kappa concordance coefficient, accuracy, precision, recall, and F1 score as evaluation metrics, as well as omission and commission errors. According to the results, the AdaBoost classifier reached greater spatial and statistical coherence than the other implemented methods. The best input layer combination for detection was the continuous change maps obtained by the linear regression and image differencing detection methods, together with the slope angle, aspect, and lithology conditioning factors.

An automated machine learning approach for classifying infrastructure cost data

“…To validate the accuracy of the ML models, the crossvalidation method (Porta, 2014) with 10 folds was implemented separately for each of the three class attributes: When predicting the "extra over" items (see Figure 4), the SVM algorithm managed to classify correctly 94% of the instances, whereas gradient boost descendent correctly classified 92% of them in contrast with random forest, which only obtained 87% accuracy.…”

A Sustainable Approach to Geomatic Methods in Ravine Monitoring and Associated Natural Disaster Prevention

“…The effects of gravity that determine the water flows and the materials removed vary depending on the slope (on higher slopes, the gravity and the speed of materials are more significant). This combination causes erosion, water and material transportation, and the induction of stress on the slopes, thus increasing the likelihood of landslides" [15].…”

“…We have considered precipitation as the most prominent factor in the expansion of the ravine. The importance of rainfall in geological hazards has been previously emphasized in other research papers: "Rainfall usually increases the pressure heads in the slope and leads to a groundwater flow pattern change and a groundwater table rise" [15]. Therefore, we considered the quantity of materials dislocated a direct result of the quantity of precipitation in a period of time.…”

An analytic hierarchy process method weighted by an improved Random Forest model considering sample optimization selection for the evaluation of landslide susceptibility

“…The RF model outperforms other algorithms in terms of prediction efficiency, accuracy, and tolerance to outliers and noise. AdaBoost is an acronym for Adaptive Boosting, whose adaptive boosting means that the weight of samples misclassified by the previous basic classifier will increase while the weight of samples correctly classified will decrease, and they will be used to train the following basic classifier again (Bernal et al 2021). With each iteration, a new weak classifier is added until a predetermined error rate or a maximum number of iterations is reached, after which the final strong classifier is determined.…”