Bangladesh, the most climate-vulnerable countries in the world. Rising temperatures worsen climate change consequences, such as heatwave frequency. Monitoring LST is critical for tracking and modelling the localized implications of global warming, as well as informing climate adaptation plans. In this study, linear regression and Mann-Kendall test methods were used to explore the spatiotemporal changing patterns of LST from 2001 to 2023 using MODIS (MOD11A1) datasets. The study looked at how LST changed over time on yearly, seasonal, monthly, and daily levels and explored how it connects to urban and weather-related factors. Firstly, the findings revealed that daytime LST showed an insignificant annual increase of 0.0127 degrees C. Whereas, nighttime LST exhibited a consistent and significant rise of 0.0415 degrees C annually. Approximately 64% of the country's area exhibited rising daytime LST, while 96% of areas experienced increased nighttime LST. Secondly, it showed that the highest mean daytime LST recorded in April and the coldest mean during January. Four and two breakpoints have been detected in the seasonal and temporal components in daily daytime LST and nighttime LST from 2001 to 2023, respectively. The parallel coordination plot (PCP) indicated that urban expansion and vegetation loss were major drivers of elevated LST, underscoring the urban heat island effect. Moreover, cross-wavelet analysis (CWA) demonstrated that LST was positively influenced by sunshine and solar radiation, whereas precipitation and humidity had a cooling effect. The outcome of this study contributes to managing the effects of LST on Bangladesh and provides a theoretical foundation for drafting environmental protection strategies.

Agricultural drought assessment in the northwestern region of Bangladesh is essential for promoting sustainable farming practices, mitigating crop losses, and enhancing resilience to climate variability. This study offers a comprehensive remote sensing-based evaluation of agricultural drought from 2016 to 2024, utilizing Google Earth Engine (GEE) to analyze spatiotemporal variations in drought-related variables and indicators. The results reveal a significant upward trend in Land Surface Temperature (LST), peaking at 32.45 °C in 2024, which heightens the risk of agricultural drought. Meanwhile, the Normalized Difference Vegetation Index (NDVI) remained relatively stable, with slight increases over time, indicating the resilience of irrigated crops. Three drought indices, derived from LST and NDVI—the Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Vegetation Health Index (VHI)—consistently showed that the region predominantly experienced ‘‘no drought’’ conditions, with the most significant area, 33,311 km2 (94

This study investigated land-use changes in Bangladesh from 2017 to 2023 using Sentinel-2 data and projected trends for 2023–2030 using the Cellular Automata-Artificial Neural Network (CA-ANN) model. The findings revealed rapid urban expansion, with built-up areas increasing by 73.93

The thermal consequences of industrial land transformation remain underexplored in rapidly urbanizing regions of Bangladesh. This study presents a novel approach of how extensive industrial expansion in Narayanganj, a major manufacturing hub dominated by textile, knitwear and dyeing industries, has altered land surface temperature (LST) dynamics over the past three decades, including its variation across classes, relationships with biophysical indices and future patterns. Landsat 5 TM and Landsat 8 OLI imagery from 1991, 2007, and 2023 were utilized to map LULC using winter-season images through supervised classification, while multi-seasonal thermal bands were used to derive LST. LST variations were further evaluated using cross-sectional profiles across different land cover types, and correlations were examined with indices including the greenness index (NDVI), moisture index (NDMI), built-up index (NDBI), and barrenness index (NDBAI). Additionally, a future LST map for 2039 was generated using the cellular automata–artificial neural network (CA-ANN) model. Results show that between 1991 and 2023, built-up area and bare land expanded by 16.72% and 14.15%, while vegetation area and water bodies decreased by 26.62% and 4.25%. Average LST increased from 25.94 °C in 1991 to 28.68 °C in 2023, with projections indicating an additional 2 °C rise by 2039. Cross-sectional analysis found that built-up areas consistently showed the maximum surface temperatures, followed by bare land, vegetation and water bodies. In addition, correlation analysis revealed that LST showed an inverse relation with NDVI and NDMI, while showing a positive relationship with NDBI and NDBAI. These findings show the necessity of sustainable urban planning and green infrastructure to reduce surface heating in rapidly urbanizing areas.

The southwest Region of Bangladesh, primarily the Khulna Division, is a rapidly urbanizing area characterized by a diverse landscape. Recently, this area has undergone notable urban expansion, resulting in changes in land cover that affect Land Surface Temperature (LST) and increase the Urban Heat Island (UHI) effect. This study employs cloud-based geospatial analysis in Google Earth Engine (GEE) and machine-learning techniques to examine interactions between Land Use Land Cover (LULC) and LST. Multi-temporal Landsat 5 and Landsat 8 data were used to derive LST and spectral indices, complemented by MODIS LST products, Sentinel-2 land cover data, and ancillary climatic and topographic datasets (GPCP, MERRA-2, SRTM, and GUF). Spectral index analysis (NDVI, NDWI, NDBI), Pearson’s correlation analysis, and Random Forest modeling were applied to identify the drivers of LST variability from 2000 to 2022. The results reveal that urban areas expanded by almost 4.5-fold during the study period, whereas vegetation and water bodies decreased by 9.48 The graphical abstract illustrates the relationship between land use and land cover (LULC) change and land surface temperature (LST) dynamics in the Southwest Region of Bangladesh between 2000 and 2022. Over the 22 years, urban areas expanded by 1821 km², while vegetation and water bodies decreased by 959 km² and 1238 km², respectively, alongside a moderate increase in bare land (376 km²). This transformation led to a substantial rise in LST, with the overall regional temperature increasing by 3.95 °C. Urban areas exhibited the largest increase (5.92 °C), whereas non-urban areas showed a smaller increase (3.05 °C). Vegetation, water, and bare lands individually experienced temperature rises of 2.73 °C, 2.13 °C, and 3.70 °C, respectively, highlighting the disproportionate warming of built-up surfaces. The findings also reveal a pronounced Urban Heat Island (UHI) effect, with urban areas averaging 2.87 °C warmer than non-urban areas, and non-urban-to-urban land transitions contributing an additional 3.52 °C increase. Feature-importance analysis using the Random Forest model indicates that LULC is the dominant factor influencing LST, accounting for 16.83

Heatwaves are severely increasing due to climate change, significantly impacting public health and ecosystems. In April 2023, Baripada, a town in North Odisha, recorded the highest reported near-surface air temperature globally on 14 April 2023, according to global weather observations, which were widely reported by national and international weather monitoring platforms. This study investigates the dynamics behind this heatwave using the Weather Research and Forecasting (WRF) model to simulate atmospheric conditions, focusing on the interplay between upper-level convergence, subsiding air masses, and dry north-westerly winds. Land Surface Temperature (LST) analysis from satellite data like LANDSAT, validated the extreme temperatures, aligning with the model simulations. Results revealed a combination of synoptic and local meteorological factors, including low relative humidity, anti-cyclonic circulation, and soil dryness, as key drivers of this event. By integrating the advanced modelling and observational data, this study highlights the urgent need for robust meteorological early warning systems and adaptive heat-health preparedness strategies to mitigate the impacts of extreme heat events in vulnerable regions. The findings contribute to a deeper understanding of heatwave mechanisms, with broader implications for global climate resilience.

Landslides pose a significant threat to the Chittagong Division of Bangladesh, particularly during the monsoon season, causing substantial socio-economic losses and fatalities. This study aims to develop a landslide susceptibility map (LSM) for the region by integrating remote sensing (RS) and geographic information system (GIS) data with advanced machine learning algorithms, specifically Gradient Boosting Machine (GBM) and Random Forest (RF). A comprehensive set of 12 conditioning factors, including elevation, slope, rainfall, and land use/land cover (LULC), was analyzed to assess landslide susceptibility. Historical landslide data from 170 locations were used to train and validate the models. Both GBM and RF models demonstrated high predictive accuracy, achieving an area under the curve (AUC) of 0.83. The KS Plot further validates the models, with the GBM model attaining KS values of 0.55 for the positive class and 0.54 for the negative class, while the RF model shows KS values of 0.54 for both classes. Comparative performance analysis revealed that the GBM model achieved 0.75 in Accuracy, 0.72 in Precision, 0.66 in Recall, and 0.69 in F1 Score. In contrast, the RF model slightly outperformed it with 0.76 in Accuracy, 0.74 in Precision, 0.67 in Recall, and 0.70 in F1 Score. These consistent improvements indicate that the RF model provides a marginally better overall performance across the evaluated metrics. The GBM model classified larger areas as very low or very high susceptibility, while RF distributed susceptibility more evenly across classes. The study highlights the effectiveness of machine learning in landslide susceptibility mapping and provides valuable insights for disaster risk management, land-use planning, and resource allocation in landslide-prone areas.

Precise rainfall forecasting is essential for efficient water resource management and disaster preparedness, especially in areas vulnerable to severe weather conditions. This study presents an integrated approach, combining machine learning techniques and statistical models, to predict rainfall patterns in Bangladesh's southwestern and northwestern regions. To complete this study, the method employs an Evidential Neural Network with the Gaussian Random Fuzzy Numbers (EVNN-GRFN) model, integrated with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm and the Autoregressive Moving Average (ARMA) model. Analyzing 41 years of data from four stations, the research demonstrates superior performance of EVNN-GRFN-M2 for Dinajpur and EVNN-GRFN-M1 for other stations. Results show R2 values over 70

This study aims to explore the impact of fly ash (FA) on two types of free-floating aquatic plants, Eichhornia crassipes and Pistia stratiotes, growing in two different locations. The stress caused by FA has led to a significant biochemical alteration in several leaf properties, including ascorbic acid, relative water, and chlorophyll, as well as anatomical changes in leaf, petiole, and stolon in the growing plants at highly contaminated sites (HCS) relative to the low contaminated site (LCS). According to the study, HCS plants lose total chlorophyll overall, have shallower ascorbic acid levels, and have higher RWC than LCS plants. These findings imply that both species are highly resilient to pollution. The assessment of the shape and size of the epidermis, cortex, palisade cells, air space, bundle sheath, xylem cavity, phloem cells, vascular bundle, parenchyma, pith of the leaves, petioles, and stolon in the HCS is shorter than the LCS. The APTI values of E. crassipes (8.407%) and P. stratiotes (9.681%) are higher in HCS than the values of E. crassipes (7.729%) and P. stratiotes (9.077%) in LCS. These results suggest that both species exhibit greater APTI values in plants from HCS, indicating their tolerance to pollution. We target six water bodies in HCS and LCS to assess the FA-containing water quality. We calculated the water quality using WA-WQI and CCME-WQI. The higher WA-WQI scores indicate higher water pollution levels. The value of WA-WQI is higher in HCS sites included in the KTPP colony (93.94), Amalhanda (91.43), and Barunan Ghoshpara (89.07) than in LCS sites such as in Kashinathpur (88.59), but the CCME-WQI scores are 64.33, 76.09 and 75.71 respectively. The investigation highlights that both species are exceptionally suitable as stress-tolerant plants for fly ash and possess the potential to serve as an option for the restoration of water bodies impacted by fly ash. This study will enhance our comprehension of the potential advantages of these plants, particularly in the phytoremediation of polluted aquatic ecosystems.

Forest fragmentation, caused by human activities, has negative consequences for forest health and biodiversity. The Sundarbans, situated in two densely populated countries, face ongoing human encroachment due to residential construction. This study investigated changes in forest cover and fragmentation in the Sundarbans, Bangladesh, from 2017 to 2023. The analysis used Sentinel-2 imagery and the Google Earth Engine (GEE) platform to classify water bodies, mangrove forests, built-up areas, and agriculture zones. Accuracy levels have not significantly fluctuated, but overall accuracy remained between 88 % and 91 %, with high agreement kappa statistics ranging from 0.83 to 0.88 across all years. The study identified Patch, Edge, Perforated, and Core forest classes, revealing annual shifts in land use. Notably, the 'Patch' class indicated localized regeneration, while the 'Core (>202 ha)' declined due to deforestation, urban expansion, and shifting agriculture. The Core class decreased significantly from 205,421 ha in 2017-73,127 ha in 2020. Additionally, Normalized Difference Vegetation Index (NDVI) indices highlighted fluctuations in forest classes and vegetation/non-vegetation areas. Canopy changes showed a 3 % reduction in high canopy (>0.3) from 2017 to 2023. High-resolution data facilitated the precise mapping of fragmented areas, emphasising the urgent need for conservation planning amidst urbanization while preserving the Sundarbans' ecological integrity.

Landslides are severe and frequent natural disasters that can cause significant adverse impacts on human lives and infrastructure, especially in mountainous areas around the world. Accurate susceptibility assessment and zonation are essential for disaster risk reduction and sustainable development, particularly in the Darjeeling district of West Bengal, India. This study explores the potential of unconventional machine learning techniques, such as Model-Averaged Neural Networks (MA-NNET), Bagged AdaBoost (ADABAG), and Monotone Multilayer Perceptron (MONMLP), which extend beyond standard methodology. To conduct a comprehensive investigation of landslide susceptibility, the study uses an extensive dataset of geological, topographical, hydrological, and anthropogenic factors. The landslide causal factors (LCFs) were selected through correlation analysis, multicollinearity assessment, and the Boruta algorithm. The landslide susceptibility maps constructed through the aforementioned machine-learning methods were validated using the area under the receiver operating characteristic (AUC-ROC) curve and other performance metrics such as precision, specificity, recall (sensitivity), F1-score, overall accuracy, kappa index, and balanced accuracy. According to the evaluation metrics, the ADABAG model outperforms the MA-NNET (training AUC 90.8

Airborne fine particulate matter (PM2.5) is recognized globally as one of the most hazardous air pollutants due to its profound impact on human health, contributing to respiratory and cardiovascular diseases, and increasing the risk of premature mortality. The World Health Organization (WHO) attributes millions of deaths annually to PM2.5 exposure, making it a critical subject of study for both environmental and public health research. In this context, the present study aims to predict PM2.5 concentrations across Maharashtra, India, for the year 2023, employing machine learning models to improve spatial and temporal air quality assessments. The analysis utilizes daily station-specific datasets, incorporating PM2.5 concentrations, Fine Aerosol Optical Depth (FAOD), wind components (u and v), relative humidity (RH), and air temperature (TEMP) to improve prediction accuracy. Four regression models were applied: Random Forest (RF), Multiple Linear Regression (MLR), Linear Regression (LR), and Lasso Regression, using a combination of Fine Aerosol Optical Depth (FAOD) with meteorological data from Google Earth Engine and ground-based observations from Central Pollution Control Board (CPCB) monitoring stations. The study emphasizes the importance of utilizing FAOD as a more refined metric for fine-mode aerosol concentration in PM2.5 modeling, compared to conventional AOD. The RF model achieved the highest accuracy (R2 = 0.87, RMSE = 12.57 µg/m3, MAE = 6.96 µg/m3), outperforming MLR, LR, and Lasso Regression, which showed significantly lower R2 values. This highlights the RF model’s effectiveness in capturing the non-linear relationships between PM2.5 and its environmental factors. This study identified key PM2.5 hotspots in Maharashtra, particularly in densely urbanized areas like Mumbai, Thane, and Pune, with annual PM2.5 concentrations reaching 46.34 µg/m3, far exceeding the Indian National Ambient Air Quality Standards (NAAQS) of 40 µg/m3. Seasonal analysis revealed significant variability, with the highest PM2.5 concentrations observed during the winter months, while levels significantly decreased during the monsoon due to higher rainfall and increased atmospheric moisture. The study identifies key PM2.5 hotspots in urban areas, offering crucial insights for policymakers and urban planners to implement targeted air quality interventions. These findings support improved public health and sustainable environmental management in Maharashtra.

Rapid industrialization and economic growth in South Asia have intensified concerns about environmental sustainability, particularly regarding CO₂ emissions. This study examines the impact of hydropower energy (HPE), financing for clean energy (FCE), foreign direct investment (FDI), gross fixed capital formation (GFCF), and renewable energy consumption (REC) on CO₂ emissions and broader environmental sustainability indicators in South Asian countries from 2004 to 2022. To ensure robust analysis, panel unit root tests, including Phillips and Perron (PP), augmented Dickey–Fuller (ADF), and cross-sectionally augmented lm–Pesaran–Shin (CIPS), are applied to check stationarity, while the Westerlund cointegration test is employed to assess long-run relationships. The study utilizes the common correlated effects mean group (CCEMG) estimator as the primary regression technique, with augmented mean group (AMG) and mean group (MG) estimators for robustness. The findings reveal that REC significantly reduces CO₂ emissions, indicating its role in promoting environmental sustainability. However, HPE and FDI are positively associated with CO₂ emissions, suggesting potential inefficiencies in energy production and capital investment. Meanwhile, FCE and GFCF exhibit an insignificant relationship with CO₂ emissions. These results highlight the need for policymakers to optimize energy infrastructure, encourage sustainable investment practices, and integrate cleaner energy solutions to mitigate environmental degradation. The study provides valuable insights into the energy-emission nexus, offering a strategic direction for South Asia’s sustainability efforts.

Lightning strikes are natural phenomena with significant implications for human safety, infrastructure, and the environment. Predicting lightning events is crucial for mitigating risks, improving public safety, and optimizing the management of electrical grids and aviation operations. Study area has recently witnessed a sharp increase in lightning hazards during the rainy season, with over 20,000 lightning-related incidents recorded in 2023 alone, leading to significant loss of life and property in multiple districts. However, predicting x lightning’s exact location, timing, and intensity remains challenging due to the complex interplay of thunderstorms and atmospheric dynamics. We proposed an integrated framework combining geospatial techniques with an ensemble-based architecture for lightning flash prediction to address these challenges. As the first-level individual learners, the ensemble strategy combines Random Forests (RF), Logistic Regression (LR), and XGBoost. To increase precision, their predictions are integrated using a voting classifier at the second level. The model leverages the geospatial and atmospheric coordinates to accurately forecast lightning strikes, including longitudinal and latitudinal coordinates, radiance, milliseconds, groups, events, etc. The test results reveal that the ensemble model achieves good performance, getting an area under the curve (AUC) score of 88

Unprecedented urban growth in developing countries impacts the existing urban planning as well as prospective urban regeneration. Therefore, evaluating the prospective suitable sites for built-up area development is important to make sustainable urban planning through the urban regeneration process in the industrial-based urban area Asansol Municipal Corporation (AMC). Hence, we analyzed the area-specific built-up suitability using machine learning soft-computing techniques: Artificial Neural Network, Random Forest, and Support Vector Machine. The result showed that the edge of the urban center and periphery of the Asansol, Kulti, and Raniganj were found to be very high (21.52%, 19.87%, 26.32%) to high suitable (11.48%, 19%, 27.26%) areas for further urban planning due to vacant land with available services nearby. However, the southern portion, especially along the Damodar River site and the area near the mining sites were found to be low to very low suitable zones due to inadequate service facilities and high pollution. Finally, we proposed a three-tier urban regeneration framework for sustainable built-up development strategies in AMC that helps to achieve the UN’s sustainable development goals-3, 8, 11, 12 and 13. The findings of this study will benefit policymakers by pointing out the ideal areas for suitable built-up area development initiatives in the near future.

Landslides pose significant hazards in the mountainous region of Sikkim, India, necessitating accurate susceptibility mapping to mitigate risks. This study applies four machine learning models: Boosted Tree (BT), Gradient Boosting Machine (GBM), K-Nearest Neighbour (KNN), and Multilayer Perceptron (MLP) to develop a detailed landslide susceptibility map. Feature selection was performed using correlation analysis, the Boruta model, and multicollinearity tests, which identified 13 key landslide conditioning factors based on 1456 landslide inventory points. The GBM model demonstrated the highest predictive performance with an AUC of 0.99, followed by BT (AUC: 0.965), MLP (AUC: 0.940), and KNN (AUC: 0.895) in the testing dataset. The confusion matrix validation confirmed that GBM outperformed other models, achieving the highest F1 score (0.894) and accuracy (89.4%), followed by BT with an F1 score of 0.874 and accuracy of 87.8%. KNN and MLP displayed lower performance, with KNN showing an F1 score of 0.724 and accuracy of 72.6%, and MLP significantly underperforming with an F1 score of 0.096 and accuracy of 48.6%. Statistical significance testing using the Wilcoxon Signed-Rank Test revealed significant differences between BT and MLP (p = 0.018), while other model pairs exhibited no statistically significant performance differences. Additionally, the variable importance analysis highlighted Diurnal Temperature Range (DTR) as the most critical factor influencing landslide occurrence (43.99%), followed by elevation (21.59%). These findings provide valuable insights for policymakers and government authorities, enabling them to take necessary measures for effective landslide management in the vulnerable areas of Sikkim, confirming the efficacy of machine learning models for geohazard assessments.

Evaluating landslide susceptibility is crucial for reducing landslide risks and improving early warning systems, thereby enhancing disaster preparedness and safeguarding vulnerable communities. This study aims to apply machine learning methods for the spatiotemporal analysis of landslide susceptibility in the Hindu Kush Himalaya (HKH) region, integrating geospatial data and advanced modeling techniques to improve the accuracy of risk area identification. Four models—Gradient Boosting Machine (GBM), Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN)—were used for predictive analytics. The GBM model demonstrated the highest performance with an Area Under the Curve (AUC) of 0.93, followed by RF (AUC of 0.92). The analysis indicates that 35–40

Assessing the ecological environmental quality (EEQ) is crucial for protecting the environment. Dhaka’s rapid, unplanned urbanization, driven by economic and social growth, poses significant eco-environmental challenges. Spatiotemporal ecological and environmental quality changes were assessed using remote sensing based ecological index (RSEI) maps derived from Landsat images (1993, 2003, 2013, and 2023). RSEI was based on four indicators—greenness (NDVI), heat index (LST), dryness (NDBSI), and wetness (LSM). Landsat 5 TM and 8 OLI/TIRS images were processed on Google Earth Engine (GEE), with principal component analysis (PCA) applied to determine RSEI. The findings showed a decline in the overall RSEI (1993–2023), with low- and very low-quality areas increasing by about 39% and high- and very high-quality areas decreasing by 24% of the total area. NDBSI and LST were negatively correlated with RSEI, except in 1993, while NDVI and LSM were generally positive but negative in 1993. The global Moran’s I (0.88–0.93) indicated strong spatial correlation in the distribution of EEQ across Dhaka. LISA cluster maps showed high-high clusters in the northeast and east, while low-low clusters were concentrated in the northwest. This research examines the degradation of ecological conditions over time in Dhaka and provides valuable insights for policymakers to address environmental issues and improve future ecological management.

Water scarcity in hilly regions presents unique challenges, particularly in Bangladesh, where obtaining fresh drinking water has become difficult to access. This study aims to evaluate the potential zones for rainwater harvesting (RWH) using machine learning (ML) algorithms and geospatial analysis. Specifically, four ML algorithms—random forest (RF), boosted regression trees (BRT), k-nearest neighbors (KNN), and naïve bayes (NB)—alongside the analytical hierarchy process (AHP) were employed to delineate potential RWH zones in the Chattogram hilly districts, including Chattogram, Rangamati, Bandarban, Khagrachari, and Cox’s Bazar. Eleven influencing factors were considered: aspect, distance from road, drainage density, elevation, hill shade, lineament density, land use/land cover (LULC), slope, topographic wetness index (TWI), rainfall, and geology. Inventory data from the study area, consisting of 135 suitable and 135 non-suitable points, were randomly split, with 70% used for training the models and the remaining 30% for validation using the area under the curve (AUC) values. The southern regions are highly suitable for harvesting rainwater. Among the five models, BRT and RF demonstrated superior performance with AUC values of 0.93 for both models. In contrast, the AHP method yielded the lowest AUC value at 0.82. Notably, drainage density and elevation emerged as the most influential factors in constructing these models. The application of machine learning algorithms has enhanced the precision of rainwater harvesting zone estimate systems by examining diverse aspects. The findings of this study can provide valuable insights for policymakers in making informed decisions regarding RWH in these regions.