Applications of machine learning on remote sensing data appear to be endless. Its use in damage identification for early response in the aftermath of a large-scale disaster has a specific issue. The collection of training data right after a disaster is costly, time-consuming, and many times impossible. This study analyzes a possible solution to the referred issue: the collection of training data from past disaster events to calibrate a discriminant function. Then the identification of affected areas in a current disaster can be performed in near real-time. The performance of a supervised machine learning classifier to learn from training data collected from the 2018 heavy rainfall at Okayama Prefecture, Japan, and to identify floods due to the typhoon Hagibis on 12 October 2019 at eastern Japan is reported in this paper. The results show a moderate agreement with flood maps provided by l...

Forest fires are a potential threat to life, as they contribute to reducing forest areas, impact on the services we expect from ecosystems, the health of the inhabitants is affected by smoke and the economic costs for the recovery of affected areas is high. The objective of the study is to apply fuzzy logic to model the risk of forest fires in the Cajamarca-Peru region, incorporating variables that represent biological, topographic, socioeconomic, and meteorological factors. The analysis was based on the acquisition, editing and rasterization of the database, application of fuzzy membership functions and image fuzzification, fuzzy superposition and spatial reclassification of forest fire risk. The results obtained show that 71.68% of the area is under very low or medium forest fire risk. However, 28.32% of the study area has a high to very high fire risk, which makes the occurrence of fi...

La subcuenca Cumbaza cuenta con la mayor cantidad de áreas boscosas (bosques primarios) deforestadas, lo que ha generado el incremento de la erosión hídrica en los suelos. La presente investigación tuvo como objetivo conocer la erosión hídrica en función de las lluvias máximas para diferentes tiempos de retorno mediante el Modelo de la Ecuación Universal de Pérdida de Suelos y el modelamiento de los Sistemas de Información Geográfica (SIG), a fin de proponer medidas de conservación de suelos. Se realizó una investigación empírica de diseño no experimental, para lo cual se evaluaron las lluvias máximas en 24 horas mediante la regional- ización hidrológica utilizando el método Gumbel Tipo I para conocer la distribución de las lluvias en Cumbaza. Luego se evaluaron cartográfi- camente las trece (13) áreas de vulnerabilidad erosiva usando el mod- elamiento SIG realiza...