The United Nations Sustainable Development Goal (SDG) 11.1 emphasizes improving well-being, ensuring housing security, and promoting social equity. Informal settlements, one of the most vulnerable groups, require significant attention due to their dynamic changes and habitat quality. These areas limit the ability to comprehensively capture spatial heterogeneity and dynamic shifts in regional sustainable development. This study proposes an integrated approach using multi-source remote sensing data to extract the spatial distribution of informal settlements in Mumbai and assess their habitat environment quality. Specifically, seasonal spectral indices and texture features were constructed using Sentinel and SAR data, combined with the mean decrease impurity (MDI) indicator and hierarchical clustering to optimize feature selection, ultimately using a random forest (RF) model to extract the spatial distribution of informal settlements in Mumbai. Additionally, an innovative habitat environment index was developed through a Gaussian fuzzy evaluation model based on entropy weighting, providing a more robust assessment of habitat quality for informal settlements. The study demonstrates that: (1) texture features from the gray level co-occurrence matrix (GLCM) significantly improved the classification of informal settlements, with the random forest classification model achieving a kappa coefficient above 0.77, an overall accuracy exceeding 0.89, and F1 scores above 0.90; (2) informal settlements exhibited two primary development patterns: gradual expansion near formal residential areas and dependence on natural resources such as farmland, forests, and water bodies; (3) economic vitality emerged as a critical factor in improving the living environment, while social, natural, and residential conditions remained relatively stable; (4) the proportion of highly suitable and moderately suitable areas increased from 65.62% to 65.92%, although the overall improvement in informal settlements remained slow. This study highlights the novel integration of multi-source remote sensing data with machine learning for precise spatial extraction and comprehensive habitat quality assessment, providing valuable insights into urban planning and sustainable development strategies.

High spatiotemporal resolution land surface temperature (LST) data are essential for monitoring thermal environments. However, existing data sources—meteorological station observations, satellite remote sensing, and reanalysis datasets—each have distinct limitations, including sparse spatial coverage, frequent data gaps, and insufficient resolution for localized studies. As a result, data fusion is needed to combine the strengths of these sources. However, existing data fusion methods typically necessitate extensive pre-tuning of model parameters or error characteristics, as well as the incorporation of complex auxiliary data, placing substantial demands on the expertise of users. Therefore, there is an urgent need for a simple, efficient, and user-friendly algorithm to meet the diverse application requirements. To meet this need, this study introduces a data fusion method based on an Extended Kalman Filter Dual-Cycle Assimilation (EKFDCA) framework. This framework achieves computationally efficient integration of satellite and reanalysis LST by directly extracting dynamic evolution from ERA5-Land LST, eschewing both full model runs and ancillary data needs while matching satellite product accuracy. Applied to GOES-16 LST and ERA5-Land LST, it produces an hourly 2 km LST dataset for 2023, rigorously evaluated against measurements from seven Surface Radiation Budget Network (SURFRAD) stations across the United States. Results demonstrate strong agreement between the fused LST data and ground observations, with coefficient of determination (R²) values exceeding 0.89 during satellite availability, and R² values remaining above 0.87 during periods of satellite unavailability. Bias ranged from -1.27 to 0.90, with root mean square error (RMSE) around 2.7°C during satellite availability, and 2.9°C during satellite unavailability. The trend of the fused data matches the station data, demonstrating the effectiveness of the fused data, while correcting extreme biases in the original data. At the regional scale, the fused product exhibits high consistency with GOES-16 data, capturing spatial patterns while maintaining numerical stability. This method delivers stable, high-quality fused LST data despite gaps in satellite input and does so without prior ground observations, offering an efficient and robust solution for continuous temperature monitoring and analysis.