Early identification of damage after a landslide is important. However, image deciphering by specialists is time-consuming and costly. In recent years, there has been discussion on delegating the image interpretation part to AI. Yet, a comprehensive model capable of detecting widespread and simultaneous sediment-related disasters has not been established. In addition, these models often rely solely on image data and do not consider the specific characteristics of the affected areas. Therefore, in this study, we developed a damage detection model that enables early detection of landslides using YOLO. Additionally, we developed a model that categorizes the factors causing landslides in the July 2018 torrential rainfall into predisposing factors and triggers, and quantitatively evaluates them using binomial logistic regression analysis. The combination of these approaches was shown to complement the results obtained from using only image decipherment.

In a semi-arid zone, digging wells improves access to drinking water. Wells could be dug efficiently with a high probability of success if potential groundwater sites could be estimated by remote sensing and Geographic Information System (GIS)-based methods. Thus, a potential groundwater map in semi-arid zones was created by applying folkloric knowledge to optical sensor data and geographical information. The test area is located in the Umerkot area, Sindh Province, Pakistan. By quantifying, weighting, and adding the topography, ground surface dryness and wetness, and the existence of vegetation and geology, we classified the total score for potential groundwater in the semi-arid zone (PGW_SAZ), into five levels. The possibility of the existence of groundwater in the flood plain in the western part is higher than that in the desert in the eastern part of the test area. There were 67 wells in the eight villages selected for a detailed survey. The possibility of the existence of groundwater (PGW_SAZ) at each existing well was examined. Of the 67 wells, 87% fell into the Moderate and Good classes, for which the possibility of the existence of groundwater was high. Therefore, it can be said that the created map is effective for determining candidate sites for digging wells.