Between 23 and 25 January 2020, the Metropolitan Region of Belo Horizonte (MRBH) in Brazil experienced 32 natural disasters, which affected 90,000 people, resulted in 13 fatalities, and caused economic damages of approximately USD 250 million. This study aims to describe the synoptic and mesoscale conditions that triggered these natural disasters in the MRBH and the physical properties of the associated clouds and precipitation. To achieve this, we analyzed data from various sources, including natural disaster records from the National Center for Monitoring and Early Warning of Natural Disasters (CEMADEN), GOES-16 satellite imagery, soil moisture data from the Soil Moisture Active Passive (SMAP) satellite mission, ERA5 reanalysis, reflectivity from weather radar, and lightning data from the Lightning Location System. The South Atlantic Convergence Zone, coupled with a low-pressure system off the southeast coast of Brazil, was the predominant synoptic pattern responsible for creating favorable conditions for precipitation during the studied period. Clouds and precipitating cells, with cloud-top temperatures below -65 degrees C, over several days contributed to the high precipitation volumes and lightning activity. Prolonged rainfall, with a maximum of 240 mm day-1 and 48 mm h-1, combined with the region's soil characteristics, enhanced water infiltration and was critical in triggering and intensifying natural disasters. These findings highlight the importance of monitoring atmospheric conditions in conjunction with soil moisture over an extended period to provide additional information for mitigating the impacts of natural disasters.

Sinkholes pose a significant hazard in Mexico City (CDMX), causing substantial economic damage. While the link between sinkhole formation and groundwater extraction has been studied, specific mechanisms vary by site. Our overall aim is to characterize the phenomenon of sinkholes in CDMX. To achieve this, we create a database with 13 influencing factors, including population density, well density, distance to faults, fractures, roads, streams, elevation, slope, clay thickness, lithology, subsidence rate, geotechnical zones, and soil texture. Sinkhole locations were obtained from CDMX's Risk Atlas (2017-2019). We shaped a susceptibility map based on statistical regression methods derived from applying linear regression models. For the susceptibility map, results showed that 40% of variables are significantly correlated with sinkhole density. Despite the regression model explained 24% of sinkhole density variability, it helped choosing variables for the susceptibility map that correlate better (89.7%). Hence, we identified that the northeast CDMX was the most susceptible zone. Therefore, the compound assessment of environmental factors is useful for the evaluation of susceptibility maps to identify prone factors for the generation of sinkholes. This framework provides relevant information for better use of the territory throughout the development of public policies.

Most natural disasters result from geodynamic events such as landslides and slope collapse. These failures cause catastrophes that directly impact the environment and cause financial and human losses. Visual inspection is the primary method for detecting failures in geotechnical structures, but on-site visits can be risky due to unstable soil. In addition, the body design and hostile and remote installation conditions make monitoring these structures inviable. When a fast and secure evaluation is required, analysis by computational methods becomes feasible. In this study, a convolutional neural network (CNN) approach to computer vision is applied to identify defects in the surface of geotechnical structures aided by unmanned aerial vehicle (UAV) and mobile devices, aiming to reduce the reliance on human-led on-site inspections. However, studies in computer vision algorithms still need to be explored in this field due to particularities of geotechnical engineering, such as limited public datasets and redundant images. Thus, this study obtained images of surface failure indicators from slopes near a Brazilian national road, assisted by UAV and mobile devices. We then proposed a custom CNN and low complexity model architecture to build a binary classifier image-aided to detect faults in geotechnical surfaces. The model achieved a satisfactory average accuracy rate of 94.26%. An AUC metric score of 0.99 from the receiver operator characteristic (ROC) curve and matrix confusion with a testing dataset show satisfactory results. The results suggest that the capability of the model to distinguish between the classes 'damage' and 'intact' is excellent. It enables the identification of failure indicators. Early failure indicator detection on the surface of slopes can facilitate proper maintenance and alarms and prevent disasters, as the integrity of the soil directly affects the structures built around and above it.

Landslides present a substantial risk to human lives, the environment, and infrastructure. Consequently, it is crucial to highlight the regions prone to future landslides by examining the correlation between past landslides and various geo-environmental factors. This study aims to investigate the optimal data selection and machine learning model, or ensemble technique, for evaluating the vulnerability of areas to landslides and determining the most accurate approach. To attain our objectives, we considered two different scenarios for selecting landslide-free random points (a slope threshold and a buffer-based approach) and performed a comparative analysis of five machine learning models for landslide susceptibility mapping, namely: Support Vector Machine (SVM), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The study area for this research is an area in Polk County in Western North Carolina that has experienced fatal landslides, leading to casualties and significant damage to infrastructure, properties, and road networks. The model construction process involves the utilization of a dataset comprising 1215 historical landslide occurrences and 1215 non-landslide points. We integrated a total of fourteen geospatial data layers, consisting of topographic variables, soil data, geological data, and land cover attributes. We use various metrics to assess the models ' performance, including accuracy, F1-score, Kappa score, and AUC-ROC. In addition, we used the seeded-cell area index (SCAI) to evaluate map consistency. The ensemble of the five models using Weighted Average produces outstanding results, with an AUC-ROC of 99.4% for the slope threshold scenario and 91.8% for the buffer-based scenario. Our findings emphasize the significant impact of non-landslide random sampling on model performance in landslide susceptibility mapping. Furthermore, by optimally identifying landslide-prone regions and hotspots that need urgent risk management and land use planning, our study demonstrates the effectiveness of machine learning models in analyzing landslide susceptibility and providing valuable insights for informed decision-making and disaster risk reduction initiatives.