This study employs machine learning techniques to map and predict landslide-prone areas in São Sebastião, Brazil, a region susceptible to landslides due to its steep terrain and intense rainfall. We compared...
详细信息
Landslides are a pressing natural hazard, particularly in regions prone to extreme weather events, and their frequency is expected to rise due to climate change. This paper investigates landslide susceptibility in S&#...
详细信息
This study investigates ground subsidence in Maceió, the capital of Alagoas, Brazil, utilizing Sentinel-1 Synthetic Aperture Radar (SAR) data from November 2019 to December 2023. Ground subsidence poses significa...
详细信息
Disaster forensic approaches aim to identify the causes of disasters to support disaster risk ***,few studies have conducted a systematic literature review of scientific articles that labeled themselves as a forensic ...
详细信息
Disaster forensic approaches aim to identify the causes of disasters to support disaster risk ***,few studies have conducted a systematic literature review of scientific articles that labeled themselves as a forensic approach to *** article provides a qualitative analysis of these forensic studies,focusing on five main issues:(1)the methodologies applied;(2)the forensic approaches used in the disaster risk management phases;(3)the hazards addressed;(4)if the methodologies involve social participation,and using what types of participation;and(5)if there are references to urban planning in the scientific studies *** results showed a predominance of the Forensic Investigations of disasters(FORIN)and Post-Event Review Capability(PERC)methodologies used in isolation or *** is a need for methodologies that engage people in participatory FORIN,fostering the co-production of knowledge and action research approaches.
Algal blooms are a frequent subject in scientific discussions and are the focus of many recent studies,mainly due to their adverse effect on *** the lack of ground truth data and the need to develop tools for their de...
详细信息
Algal blooms are a frequent subject in scientific discussions and are the focus of many recent studies,mainly due to their adverse effect on *** the lack of ground truth data and the need to develop tools for their detection and monitoring,this research proposes a novel method to automate *** derived from multi-temporal image series processing,spectral indices and classification with Oneclass Support Vector Machine(OC-SVM)are used in this *** from multi-spectral sensors on Landsat-8 and MODIS were acquired through the Google Earth Engine API(GEE API).In order to evaluate our method,two bloom detection case studies(Lake Erie(USA)and Lake Taihu(China))were *** were made with methods based on spectral index ***,to demonstrate the performance of the OC-SVM classifier compared to other machine learning methods,the proposal was adapted to be used with a Random Forest(RF)classifier,having its results added to the *** situ measurements show that the proposed method delivers highly accurate results compared to spectral index thresholding ***,a drawback of the proposal refers to its higher computational *** application of the new method to a real-world bloom case is demonstrated.
Statement of problem: The students’ academic performance is influenced by a complex interplay among several factors. Traditional educational approaches often struggle to accommodate the diverse needs of students, lea...
详细信息
The disaster database enables managers to support prevention, preparedness, and mitigation actions, especially in Latin American countries, where disaster risk data are scarce. This article surveys and analyses a data...
详细信息
Petrópolis, located in the mountainous region of Rio de Janeiro, Brazil, is frequently impacted by severe landslides, exacerbated by intense rainfall, steep topography, and unregulated urban growth. This study em...
详细信息
Petrópolis, located in the mountainous region of Rio de Janeiro, Brazil, is frequently impacted by severe landslides, exacerbated by intense rainfall, steep topography, and unregulated urban growth. This study employs machine learning to assess and predict landslide susceptibility, integrating geological, hydrological, and anthropogenic factors. Five models—Random Forest, CatBoost, Support Vector Machine, Artificial Artificial Neural Network (ANN), and XGBoost—were evaluated, with CatBoost emerging as the optimal model (F1-score: 0.82; AUC-ROC: 0.88). Variable importance analysis revealed soil type and erodibility as critical soil parameters influencing susceptibility, alongside lithology, underscoring the significance of geological over purely topographic factors. These findings emphasize the utility of machine learning for landslide modeling, providing scalable methodologies applicable to similar geospatial risk assessments worldwide. Beyond local applications, this work offers actionable insights for urban planning and disaster risk management in mountainous urban regions.
Change detection is a type of technique applied to remotely sensed data to map temporal changes. This approach serves as a vital tool for assessing the impacts of disasters, offering large-scale data acquisition at a ...
详细信息
Change detection is a type of technique applied to remotely sensed data to map temporal changes. This approach serves as a vital tool for assessing the impacts of disasters, offering large-scale data acquisition at a lower cost. This study introduces a novel fully automatic and computationally efficient change detection technique designed for large multispectral remote sensing image series. The proposed method exploits the concept of thresholding deviations observed in time series data. To demonstrate the effectiveness of the proposed technique, case studies were conducted on two disaster-affected areas in 2023: one in Brazil, impacted by a landslide, and the other in Mozambique, affected by flooding, using data from Landsat-8 and Sentinel-2, respectively. The results showed superior accuracy compared to an alternative technique reported in the literature, with F1-Scores of 22.09% and 0.28% higher in the first and second study areas, respectively. Additionally, qualitative analyses revealed that the developed method more effectively identifies disaster-affected areas, requiring significantly less processing time than the alternative method.
Legitimacy plays a decisive role in shaping the acceptance of technology in a sociotechnical regime, and it results from the interplay between discourses and policy actors. This study examines the discourses and roles...
详细信息
暂无评论