Among the numerous natural hazards, landslides are one of the greatest, as they can cause enormous loss of life and property, and affect the natural ecosystem and their services. Landslides are disasters that cause damage to anthropic activities and innumerable loss of human life, globally. The landslide risk assessed by the integration of susceptibility and vulnerability maps has recently become a manner of studying sites prone to landslide events and managing these regions well. Developing countries, where the impact of landslides is frequent, need risk assessment tools that enable them to address these disasters, starting with their prevention, with free spatial data and appropriate models. Our study shows a heuristic risk model by integrating a susceptibility map made by AutoML and a vulnerability one that is made considering ecological vulnerability and socio-economic vulnerability. The input data used in the State of Guerrero (México) approach uses spatial data, such as remote sensing, or official Mexican databases. This aspect makes this work adaptable to other parts of the world because the cost is low, and the frequency adaptation is high. Our results show a great difference between the distribution of vulnerability and susceptibility zones in the study area, and even between the socio-economic and ecological vulnerabilities. For instance, the highest ecological vulnerability is in the mountainous zone in Guerrero, and the highest socio-economic vulnerability values are found around settlements and roads. Therefore, the final risk assessment map is an integrated index that considers susceptibility and vulnerability and would be a good first attempt to challenge landslide disasters.

Natural hazards include a wide range of high-impact phenomena that affect socioeconomic and natural systems. Landslides are a natural hazard whose destructive power has caused a significant number of victims and substantial damage around the world. Remote sensing provides many data types and techniques that can be applied to monitor their effects through landslides inventory maps. Three unsupervised change detection methods were applied to the Advanced Spaceborne Thermal Emission and Reflection Radiometer (Aster)-derived images from an area prone to landslides in the south of Mexico. Linear Regression (LR), Chi-Square Transformation, and Change Vector Analysis were applied to the principal component and the Normalized Difference Vegetation Index (NDVI) data to obtain the difference image of change. The thresholding was performed on the change histogram using two approaches: the statistical parameters and the secant method. According to previous works, a slope mask was used to classify the pixels as landslide/No-landslide; a cloud mask was used to eliminate false positives; and finally, those landslides less than 450 m² (two Aster pixels) were discriminated. To assess the landslide detection accuracy, 617 polygons (35,017 pixels) were sampled, classified as real landslide/No-landslide, and defined as ground-truth according to the interpretation of color aerial photo slides to obtain omission/commission errors and Kappa coefficient of agreement. The results showed that the LR using NDVI data performs the best results in landslide detection. Change detection is a suitable technique that can be applied for the landslides mapping and we think that it can be replicated in other parts of the world with results similar to those obtained in the present work.

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.

The aim of the topographic normalization of remotely sensed imagery is to reduce reflectance variability caused by steep terrain and thus improve further processing of images. A process of topographic correction was applied to Landsat imagery in a mountainous forest area in the south of Mexico. The method used was the Sun Canopy Sensor + C correction (SCS + C) where the C parameter was differently determined according to a classification of the topographic slopes of the studied area in nine classes for each band, instead of using a single C parameter for each band. A comparative, visual, and numerical analysis of the normalized reflectance was performed based on the corrected images. The results showed that the correction by slope classification improves the elimination of the effect of shadows and relief, especially in steep slope areas, modifying the normalized reflectance values according to the combination of slope, aspect, and solar geometry, obtaining reflectance values more suitable than the correction by non-slope classification. The application of the proposed method can be generalized, improving its performance in forest mountainous areas.

In the performance of change detection analysis, the change/unchanged pixel categorization is usually made through empirical methods or trial-and-error manual procedures whose reliability may affect the results. To detect land-cover changes, an unsupervised change detection technique was applied to Landsat images from an area in the south of México. At first, normalized surface reflectance, principal components, and tasselled cap images were used to develop the chi-square transformation (CST) applied to each kind of image organized in absolute and relative values and thus, obtain the continuous image of change. Later, the histogram secant technique was applied to change images to automatically define the thresholds and categorize as change/unchanged the pixels. Finally, to assess the change detection accuracy, 86 polygons (14,512 pixels) were sampled, classified as real change/unchanged sites, and defined as ground-truth, from the interpretation of color aerial photo slides aided by the land-cover maps to obtain omission/commission errors and kappa coefficient of agreement. The results show that the CST and automatic histogram secant thresholding are suitable techniques that can be applied for unsupervised analysis change detection.