RESUMO
Floods cause substantial losses to life and property, especially in flood-prone regions like northwestern Bangladesh. Timely and precise evaluation of flood impacts is critical for effective flood management and decision-making. This research demonstrates an integrated approach utilizing machine learning and Google Earth Engine to enable real-time flood assessment. Synthetic aperture radar (SAR) data from Sentinel-1 and the Google Earth Engine platform were employed to generate near real-time flood maps of the 2020 flood in Kurigram and Lalmonirhat. An automatic thresholding technique quantified flooded areas. For land use/land cover (LULC) analysis, Sentinel-2's high resolution and machine learning models like artificial neural networks (ANN), random forests (RF) and support vector machines (SVM) were leveraged. ANN delivered the best LULC mapping with 0.94 accuracy based on metrics like accuracy, kappa, mean F1 score, mean sensitivity, mean specificity, mean positive predictive value, mean negative value, mean precision, mean recall, mean detection rate and mean balanced accuracy. Results showed over 600,000 people exposed at peak inundation in July-about 17% of the population. The machine learning-enabled LULC maps reliably identified vulnerable areas to prioritize flood management. Over half of croplands flooded in July. This research demonstrates the potential of integrating SAR, machine learning and cloud computing to empower authorities through real-time monitoring and accurate LULC mapping essential for effective flood response. The proposed comprehensive methodology can assist stakeholders in developing data-driven flood management strategies to reduce impacts.
RESUMO
The increasing trend of population growth along with the rapid groundwater-based agricultural expansion and decreasing trend of mean annual rainfall in the Northwest region of Bangladesh has been exacerbating the declination of groundwater for further expansion. Therefore, the present study attempts to demarcate the potential groundwater abstraction zones from the assessment of potential recharge and available recharge. Potential recharge was obtained with commonly used geospatial-based weighted linear combination (WLC) technique. Here, WLC analysis was based on eight factors related to physiographic (e.g. drainage density, lineament density, slope), geomorphologic (e.g. geomorphology, lithology, soil), land use and land cover (LULC) and hydrology (i.e. rainfall). Available net recharge was assessed for the period 1993-2017 by employing the water table fluctuation method. Finally, the resultant map on potential abstraction was characterized into five different classes, viz. 'very low', 'low', 'moderate', 'high' and 'very high'. The derived map reveals that 'very high' potential zone is distributed along the Teesta river floodplain, especially the northeastern part. In contrast, the Barind Tract (i.e. the southwestern and the southcentral parts) area shows 'very low' groundwater prospect. Such fused interpretations are expected to contribute to the planning of integrated management of water resources.
