Urban resilience is essential for cities to endure and adjust to environmental and socioeconomic upheavals. The static indicators and rule-based spatial frameworks that are the mainstays of traditional resilience assessment models frequently fall short of capturing the dynamic character of coastal and urban resilience. This paper suggests a deep learning-based categorization framework for identifying resilience levels in urban and coastal settings by combining Long Short-Term Memory (LSTM) networks with multi-sensor remote sensing data. The Copernicus Marine Data Service's spatiotemporal ocean physics data, namely the eastward (uo) and northward (vo) seawater velocity, are used in the model to increase the precision of resilience evaluations. The methodology includes a multi-step deep learning pipeline, incorporating data preprocessing, feature extraction, class balancing with SMOTE, and LSTM-based classification. The proposed LSTM model is optimized to enhance performance with dropout regularisation (0.3), an Adam optimizer (learning rate = 0.0003), and class weighting strategies. The model is evaluated using accuracy, F1-score, confusion matrices, and loss curves, ensuring reliable classification across different resilience categories. Results indicate that the framework achieves high classification accuracy (91.5%), demonstrating superior performance compared to traditional machine learning approaches. Regarding multi-sensor fusion and deep learning, this study provides a scalable, adaptive, and data-driven solution for resilience classification, supporting climate adaptation strategies, disaster risk management, and sustainable urban development. The proposed methodology offers a robust tool for policymakers and urban planners, enabling more effective resilience monitoring and decision-making in rapidly evolving urban and coastal environments.

Rivers have historically been the primary water source for all life forms; however, their fluctuating flow patterns pose significant risks, particularly in coastal and flood-prone regions. This study evaluates the applicability of the Hydrologic Engineering Centers River Analysis System (HEC-RAS) for simulating water surface profiles and quantifying flood magnitudes across multiple flood events with varying return periods. The study employs the Kolmogorov–Smirnov test to identify the most suitable probability distribution for flood frequency analysis at the gauging station, where the Log Pearson Type III (LP3) distribution was the best fit. The estimated flood discharges for 5-, 10-, 50-, 100-, and 150-year return periods were computed using the Log-Normal (LN), Gumbel, and LP3 distributions. The discharge values (in m³/s) for LN were 4887, 5467, 6521, 6907, and 7179, for Gumbel 4968, 5417, 6405, 6822, and 7066, and LP3 4906, 5480, 6344, 6755, and 7155, respectively. The analysis revealed that a 50-year return period flood with a discharge of 5299 m³/s at the study area would result in an inundation area 500% larger than that caused by natural surges. This study integrates HEC-RAS simulations with flood frequency analysis to provide a detailed assessment of floodplain extents, water velocity dynamics, and high-risk zones. The results offer critical insights into flood management, enabling policymakers, engineers, and disaster management authorities to enhance flood preparedness and mitigation strategies. These findings can support the development of early warning systems, land-use planning, and infrastructure resilience in flood-prone regions. Overall, this study highlights the efficiency of HEC-RAS modeling in predicting flood hazards and provides a framework for floodplain mapping and risk assessment in riverine environments. Future research should incorporate climate change projections and real-time hydrological data to improve flood forecasting accuracy and resilience planning.

Developing countries are struggling with urban waste management. Focusing on Islamabad, Pakistan, cross-sectional data determines how contextual variants impact domestic waste management. The study deployed a multifaceted approach to assessments. Hence, waste-bin density is a reliable proxy variable for situational analysis. It emerged that the waste-bin density in Islamabad is asymmetrical. It formulates that some localities in Islamabad receive preferential treatment, which contradicts the principles of “parity” and “environmental justice.” The analysis entails synchronizing efforts based on the principle “ Polluters pay the price”. Likewise, it emerged that solid waste management in Islamabad inherently relies on landfills. This “Low-hanging fruit” option is not sustainable. Hence, technologicalbased solutions through market-driven measures seem more dependable. Messages in monetary terms are persuasive and automatically prioritize waste disposal options. Therefore, the study analysis analyzed the feedback from 305 respondents. The female representation was 36.4%, much lower than their due. A greater focus on capacity-building and female empowerment is required to reverse this trend. (96.4%) demanded integrated waste management, (41%) remain dissatisfied with the current arrangements, and (88.5%) believe that bad waste management depreciates property value. The assessments based on (Age, Gender, Education, Nature of employment, and Duration of stay) render that the respondents’ views significantly modified (p≤0.05%) with Age and Duration of stay. Resilient domestic waste management requires resource recovery mechanisms such as a “circular economy framework”. It seems a plausible option in countries like Pakistan, as it generates revenue. Urban residents prefer whatever is productive and cost-effective. It demands a paradigm shift in strategies through public participation and contextbased assessments. The assessments affirm that GIS-based spatial analysis techniques are dependable for improvising measures to manage urban domestic waste.