Sukanya Ghosh

Deep learning has changed the approach of urban environmental risk assessment and management. These methods enable solid models for large data sets, enabling early identification, prediction, and description of environmental risks. The current work analyses the advances in deep learning for urban environmental hazard assessments and disaster studies to provide monitoring, management, and mitigation measures. It reports the improvement in self-supervised learning, transformer architectures, persistent learning, attention mechanisms, adversarial robustness, associated learning, meta-learning, and multimodal learning within the domain of urban environmental hazard analysis. These approaches allow the creation of robust models for handling vast data volumes, facilitating early detection, prediction, and characterisation of diverse environmental threats. This trends analysis for urban applications will bring insights for connecting deep-learning models for effective and proactive approaches to tackle urban environmental hazards and disasters.

Satellite-based remote sensing datasets are suitable for various applications including real-time flood intensity, progression, and deterioration monitoring. Google Earth Engine (GEE) has emerged as a leading cloud-based geo-computing platform for large-scale geoprocessing tools to offer higher computational speed through Google’s servers. It offers a unique platform for processing a variety of datasets without downloading raw imagery through the code editor. The cloud-based computing platforms offer a capability of real-time data for processing with space-based inputs. This platform facilitates customized algorithms with customized codes to perform the analysis on multiple datasets to generate the results. The study elucidates the geo-processing of large-scale remote sensing datasets in a cloud-based computing platform with the adapted algorithms and codes. It assesses and analyses the impact of floods over settlements, agricultural fields, vegetation cover, and other features in the selected parts of eastern India containing West Bengal, Bihar, and Jharkhand. The effect on vegetation cover is evaluated with satellite-derived indices containing normalized difference vegetation index (NDVI), enhanced vegetation index (EVI) with proper validation. The outcomes are available with the area statistics and flood maps to visualize the damages across the settlements, agricultural fields, and vegetation cover. These will help policymakers to undertake precautionary measures for disaster management. Furthermore, analogous work can be replicated to quantity the flood-inundated areas with precise scale to offer quicker responses with optimal utilization of resources.

Around the month of July 2020, the people suffering from the COVID-19 pandemic got added burden of disastrous floods. The current study tries to understand the impact of flood inundation on the vegetation cover across the Ganga Basin with the help of a cloud-based computing platform like Google Earth Engine (GEE) in a near real-time scenario. This offers a semi-automatic scheme with customized algorithms to process the large scale of datasets to further analyze and derive the required information from space-based satellite images like Synthetic Aperture Radar (SAR) images. The direct impact of floods on vegetation cover is assessed with the satellite-derived normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI). The results of post-flood NDVI and EVI readings showed a considerable reduction due to the protracted flood water submergence. The results show the flood extent maps for the selected regions for the lower Ganga Basin having inundations in parts of Bihar and West Bengal. This affects the settlements, agricultural land, and vegetation cover with damage to the large population. The outcomes of the work may be utilized to assess the precise flood-inundated areas at a faster rate to offer a faster response even in the pandemic.