Floods are devastating natural disasters causing significant damage worldwide, especially in southern Latin America, where recurrent river floods lead to severe impacts. This study proposes an innovative flood modelling approach using a naive Bayes classifier to simulate flood extents at a regional scale, incorporating spatial and temporal variability. Using 12 features, including topography, soil properties, precipitation and discharge, the model was trained with multiple flood events, avoiding sampling limitations and evaluating optimal pre-processing strategies for continuous data. The predictive capacity resulted in high performance metrics, with temporal validation accuracy (AC) up to 0.98 and a critical success index (CSI) of 0.58, and spatial validation achieved an AC up to 0.97 and CSI of 0.56, outperforming the hydrodynamic model by 65%. A reduced model with significant features improved computational efficiency and achieved a CSI exceeding 0.60. This practical tool supports flood risk management and enhances resilience in vulnerable regions.
Due to recent rainfall extremes and tropical cyclones that form over the Bay of Bengal during the pre- and post-monsoon seasons, the Nagavali and Vamsadhara basins in India experience frequent floods, causing significant loss of human life and damage to agricultural lands and infrastructure. This study provides an integrated hydrologic and hydraulic modeling system that is based on the Soil and Water Assessment Tool model and the 2-Dimensional Hydrological Engineering Centre-River Analysis System, which simulates floods using Global Forecasting System rainfall forecasts with a 48-h lead time. The integrated model was used to simulate the streamflow, flood area extent, and depth for the historical flood events (i.e., 1991-2018) with peak discharges of 1200 m3/s in the Nagavali basin and 1360 m3/s in the Vamsadhara basin. The integrated model predicted flood inundation depths that were in good agreement with observed inundation depths provided by the Central Water Commission. The inundation maps generated by the integrated modeling system with a 48-h lead time for tropical cyclone Titli demonstrated an accuracy of more than 75%. The insights gained from this study will help the public and government agencies make better decisions and deal with floods.
Tropical Cyclone Yaas inflicted substanntial damage on Bhitarkanika National Park (BNP), an eminent wildlife sanctuary housing a vast diversity of flora and fauna, during its occurrence in 2021. The park has experienced a heightened frequency of cyclonic activity in recent years. This study undertakes a comprehensive analysis of the impacts of Tropical Cyclone Yaas on the mangrove forest within BNP, utilizing a broad array of physical, biological, and ecological indices. The assessment method employed in the study encompasses various indicators, such as ecological (Normalized Difference Vegetation Index - NDVI, Enhanced Vegetation Index - EVI, Leaf Area Index - LAI, Normalized Difference Water Index - NDWI, and Normalized Difference Salinity Index - NDSI), biological (Chlorophyll content and Gross Primary Productivity - GPP), and physical (flood monitoring and precipitation) measures. Our findings elucidate the destructive consequences of Cyclone Yaas on the mangrove forest, inflicting significant ecosystem loss attributable to the extreme precipitation and high wind speeds. The biophysical, ecological, and biological indicators reveal profound effects on the local ecosystem, manifested through a decline in vegetation vigor and alterations in soil conditions, notably marked by an increase in salinity.