Normalized Difference Water Index Research Articles

Enhancing the Performance of Machine Learning and Deep Learning-Based Flood Susceptibility Models by Integrating Grey Wolf Optimizer (GWO) Algorithm

Flooding is a recurrent hazard occurring worldwide, resulting in severe losses. The preparation of a flood susceptibility map is a non-structural approach to flood management before its occurrence. With recent advances in artificial intelligence, achieving a high-accuracy model for flood susceptibility mapping (FSM) is challenging. Therefore, in this study, various artificial intelligence approaches have been utilized to achieve optimal accuracy in flood susceptibility modeling to address this challenge. By incorporating the grey wolf optimizer (GWO) metaheuristic algorithm into various models—including recurrent neural networks (RNNs), support vector regression (SVR), and extreme gradient boosting (XGBoost)—the objective of this modeling is to generate flood susceptibility maps and evaluate the variation in model performance. The tropical Manimala River Basin in India, severely battered by flooding in the past, has been selected as the test site. This modeling utilized 15 conditioning factors such as aspect, enhanced built-up and bareness index (EBBI), slope, elevation, geomorphology, normalized difference water index (NDWI), plan curvature, profile curvature, soil adjusted vegetation index (SAVI), stream density, soil texture, stream power index (SPI), terrain ruggedness index (TRI), land use/land cover (LULC) and topographic wetness index (TWI). Thus, six susceptibility maps are produced by applying the RNN, SVR, XGBoost, RNN-GWO, SVR-GWO, and XGBoost-GWO models. All six models exhibited outstanding (AUC above 0.90) performance, and the performance ranks in the following order: RNN-GWO (AUC: 0.968) > XGBoost-GWO (AUC: 0.961) > SVR-GWO (AUC: 0.960) > RNN (AUC: 0.956) > XGBoost (AUC: 0.953) > SVR (AUC: 0.948). It was discovered that the hybrid GWO optimization algorithm improved the performance of three models. The RNN-GWO-based flood susceptibility map shows that 8.05% of the MRB is very susceptible to floods. The modeling found that the SPI, geomorphology, LULC, stream density, and TWI are the top five influential conditioning factors.

Estimating Sugarcane Maturity Using High Spatial Resolution Remote Sensing Images

Sugarcane suffers from the increased frequency and severity of droughts and floods, negatively affecting growing conditions. Climate change has affected cultivation, and the growth dynamics have changed over the years. The identification of the development stages of sugarcane is necessary to reduce its vulnerability. Traditional methods are inefficient when detecting those changes, especially when estimating sugarcane maturity—a critical step in sugarcane production. Hence, the study aimed to develop a cost- and time-effective method to estimate sugarcane maturity using high spatial-resolution remote sensing data. Images were acquired using a drone. Field samples were collected and measured in the laboratory for brix and pol values. Normalized Difference Water Index, Green Normalized Difference Vegetation Index and green band were chosen (highest correlation with field samples) for further analysis. Random forest (RF), Support Vector Machine (SVM), and multi-linear regression models were used to predict sugarcane maturity using the brix and pol variables. The best performance was obtained from the RF model. Hence, the maturity index of the study area was calculated based on the RF model results. It was found that the field plot has not yet reached maturity for harvesting. The developed cost- and time-effective method allows temporal crop monitoring and optimizes the harvest time.

Remote Sensing Assessment of Water Resources, Vegetation, and Land Surface Temperature in Eastern Saudi Arabia: Identification, Variability, and Trends

Saudi Arabia has one of the biggest water shortages and the least vegetation in the world, which is presumed to provoke this problem further due to climate change. Therefore, the present study investigates the water, vegetation, and temperature over Al-Asfar Lake region, Al Ahsa, Eastern province of Saudi Arabia using the Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), and Land Surface Temperature (LST: °C) from Landsat-8 based operational land imager (OLI) measurements for the period 2013 to 2023. This study presented annual and seasonal (dry months: June–September and wet months: December–April) spatiotemporal distribution and variations, calculated their absolute change and trends, and examined their relationship. Results showed positive NDWI values over Al-Asfar Lake, indicating waterbodies; while positive NDVI values on the lake's bank, signifying vegetation. Notably, there were significant temporal variations in water and vegetation observed on annual, seasonal, and monthly scales. The study also found an overall decrease in vegetation areas of 5.36 km2 in 2023 compared to 2013, while waterbodies increased by 8.83 km2. The trend analysis using area-averaged data demonstrated that NDWI increased on annual (0.0075/year) and seasonal (dry: 0.0083/year and wet: 0.0049/year) scales, while NDVI decreased (annual: 0.0066/year, dry: 0.0083/year, and wet: 0.0009/year). Moreover, LST was recorded least amount over waterbodies (28.23 °C) and vegetation (32.45 °C) covered areas compared to the entire lake region (38.43 °C), respectively. Remark, LST displayed decreasing trends over waterbodies (−0.05/year), followed by vegetation (−0.17/year), and the entire lake region (−0.0001/year), signifying that water and vegetation are vital components to controlling land surface temperature in this region. Finally, the LST showed a positive correlation with NDVI and negative correlation with NDWI. There may be a direct and indirect impact of climate change upon NDVI, LST, and NDWI as shown by the decreases in NDVI and LST and an increase in NDWI. This study can be considered as a base document to monitor waterbodies, vegetation cover, and temperature changes using remote sensing measurements of NDWI, NDVI, and LST, which will assist policymakers in developing water resource management, irrigation planning, and environmental monitoring strategies.

Delineation of Intermittent Rivers and Ephemeral Streams Using a Hybrid Method

Intermittent rivers and ephemeral streams are crucial for the water cycle and ecosystem services, yet they are often neglected by managers and researchers, especially in headwater areas. This oversight has caused a lack of comprehensive basemaps for these vital river systems. In headwater regions, water bodies are typically sparse and disconnected, with narrow and less distinct channels. Therefore, we propose a novel hybrid method that integrates topographic data and remote sensing imagery to delineate river networks. Our method reestablishes connectivity among sparsely distributed water bodies through topographic pairs, enhances less distinct channel features using the gamma function, and converts topographic and water indices data into a weighted graph to determine optimal channels with the A* algorithm. The topographic and water indices data are derived from the Multi-Error-Removed Improved-Terrain DEM (MERIT DEM) and an average composite of the Modified Normalized Difference Water Index (MNDWI), respectively. In the upper Lancang-Mekong River basin, our method outperformed five publicly available DEM datasets, achieving over 91% positional accuracy within a 30 m buffer. This hybrid method enhances positional accuracy and effectively connects sparse water bodies in headwater areas, offering promising applications for delineating intermittent rivers and ephemeral streams and providing baseline information for these river systems.

Evaluation of the monitoring capability of various vegetation indices and mainstream satellite band settings for grassland drought

In the context of global climate change and increasing human activities, grassland drought has become increasingly severe and complex. The monitoring of grassland drought is crucial for reducing drought-related losses and ensuring national ecological security. This study used the coupled PROSPECT and SAIL radiative transfer models (PROSAIL) to simulate canopy reflectance, considering factors such as grassland growth stages and varying drought conditions. Our objective was to reveal the spectral response characteristics of grasslands to varying drought conditions and identify sensitive spectral bands suitable for drought monitoring during different grassland growth stages. We aligned commonly available satellite bands from moderate resolution imaging spectroradiometer (MODIS), Sentinel 2, Landsat 8, WorldView 2, and Gaofen 2 (GF 2) with these sensitive bands to assess the capabilities of existing satellite data for drought monitoring. Furthermore, this research evaluated the suitability of 16 commonly used remote sensing vegetation indices for grassland drought monitoring, including Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Ratio Vegetation Index (RVI), Difference Vegetation Index (DVI), Modified Soil Adjusted Vegetation Index (MSAVI), Atmospherically Resistant Vegetation Index (ARVI), Modified Normalized Difference Water Index (MNDWI), Global Vegetation Moisture Index (GVMI), Land Surface Water Index (LSWI), Visible and Shortwave Infrared Drought Index (VSDI), Water index(WI), Moisture Stress Index(MSI), Normalized Difference Water Index(NDWI), Normalized Difference Infrared Index (NDII), Photochemical Reflectance Index (PRI), and Optimized Soil-Adjusted Vegetation Index (OSAVI). The simulation and analysis results revealed: 1) Grassland in different growth stages exhibit similar sensitivities to certain spectral bands, namely those within the ranges of 540 nm–720 nm, 1250 nm–1690 nm, 1805 nm–2190 nm, and 2264 nm–2500 nm, which are more sensitive to various drought conditions. 2) Suitable vegetation indices for both growing and stable stages include NDII, MSI, PRI, LSWI, and GVMI, with silhouette coefficients exceeding 0.6 for the growing stage and 0.7 for the stable stage. The least suitable vegetation index is DVI, with an average silhouette coefficient of 0.15 over the entire growth stage. 3) From the spectral band perspective, among the five assessed satellites, MODIS Band 7 exhibits the highest sensitivity to water content across all satellite bands. MODIS's band configuration is most suitable for monitoring grassland drought during different growth stages, while WorldView 2's band configuration is the least suitable.

Revealing irrigation uniformity with remote sensing: A comparative analysis of satellite-derived uniformity coefficient

This study investigates the use of satellite-derived Christiansen Uniformity Coefficient (SDCUC) values for evaluating irrigation uniformity. In the context of global water scarcity and the imperative for sustainable water management, we explore the potential of remote sensing methods to evaluate irrigation uniformity across large agricultural areas. The findings reveal a consistent tendency for SDCUC to overestimate irrigation uniformity, with an average overestimation rate of 7.83 %. However, accuracy improved with the appropriate method, vegetation index, or spectral band selection. Employing the entire satellite image for SDCUC (SDCUCTOT) assessment improved accuracy. For Sentinel-1 (S1), using the dual-band cross-polarization horizontal transmit/vertical receive band (VH), the bias confidence interval was −0.39–0.69 %, while for Sentinel-2 (S2), using the normalized difference red edge 3 index (NDRE3), it was −1.47–0.66 %, and for Landsat 8 (L8) and Landsat 9 (L9) using the shortwave infrared water stress index (SIWSI) it ranged from 0.36 % to 2.28 %. Improved results were also observed when the normalized difference vegetation index (NDVI) ranged between 0.4 and 0.8 or the evapotranspiration and potential evapotranspiration ratio (ET/PET) ranged between 0.30 and 0.55. In these conditions, SDCUCTOT for the S2, L8, and L9 using the simple ratio index (SR) ranged from 1.00 % to 2.33 %, 0.00–1.83 %, 0.23–2.00 %, respectively, and for S2, the normalized difference water index (NDWI) and NDRE3 ranged from −1.39–0.71 %, and −1.43–2.31 % respectively. These findings underscore the potential of remote sensing techniques to revolutionize water resource management and promote sustainable agriculture, emphasizing the synergistic role of ground-based measurements and the need for continued methodological refinements to improve accuracy. Further advancements and research are warranted to refine the methodology and enhance the accuracy and reliability of remote sensing-based irrigation uniformity assessment, ultimately contributing to more sustainable agricultural irrigation practices.

Environmental Monitoring of Land Use/ Land Cover by Integrating Remote Sensing and Machine Learning Algorithms

Evaluation of the land use/ land cover (LULC) case over large regions is very important in a variety of domains, including natural resources such as soil, water, etc., and climate change risks and LULC change has emerged as a high anxiety for the environment. Therefore, we tested and compared the performance of three classification algorithms: Support Vector Machines (SVM), Random Trees (RT), and Maximum Likelihood (MaxL) to derive and extract LULC information for the district of Sarayönü/ Konya across five distinct classes: water, plantation, grassland, built-up, and bare land. Two remote sensing indices, the normalized difference vegetation index (NDVI) and the normalized difference water index (NDWI), were used as supplementary inputs for the classification of LULC. To evaluate the performance of the algorithms, a confusion matrix was employed. The average overall accuracy of support vector machines, random trees, and maximum likelihood algorithms was found 85.60%, 79.20%, and 74.80%, respectively, and 82.00%, 74.00%, and 68.50% for the Kappa coefficient. These results indicate that the support vector machines algorithm outperforms other algorithms in terms of accuracy. As a result of the research, it was determined that classification algorithms integrated with remote sensing in LULC change monitoring/determination could produce accurate classification maps that can be used as base data. This is due to the ability of machine learning algorithms to learn complex patterns, adapt to diverse data, and continuously improve, making them achieve higher accuracy compared to traditional classifiers. Therefore, their use was recommended for decision-makers.

Potential distribution of malaria vectors in Central Vietnam: A MaxEnt modeling approach.

In Central Vietnam, Anopheles dirus and Anopheles minimus are the primary malaria vector species. These Anopheles spp.' distribution and prevalence are determined by environmental, climatic, and socioeconomic conditions. This study aimed to predict the potential distribution of these two Anopheles spp. in this region. This study was conducted in 15 Central Vietnamese provinces. From 2014 to 2018, we utilized An. dirus and An. minimus presence records. Proxy data from the Google Earth Engine platform for the study area, encompassing environmental, climatic, and socioeconomic factors. MaxEnt software predicted the potential environmental, climatic, and socioeconomic suitability of these two Anopheles spp. in Central Vietnam. The test area under the curve values for An. dirus and An. minimus MaxEnt models averaged 0.801 and 0.806, respectively, showing excellent performance. Minimum air temperature had the greatest impact on the distribution of both species. A negative correlation between precipitation and normalized difference water index influences the occurrence of An. dirus. In the temperature range of 13-19.5°C, An. minimus is most likely to be present, with nighttime light detrimentally influencing its distribution. The Central Highlands region is inhabited by both species, with some presence in North-Central and South-Central Coastal areas. The importance of temperature in determining the presence of both species is emphasized by our findings, with subtle differences in the temperature-related factors shaping their distributions. The results highlight the need for focused malaria vector control and surveillance initiatives in the study area.

Hyperspectral Reflectance-Based High Throughput Phenotyping to Assess Water-Use Efficiency in Cotton

Cotton is a pivotal global commodity underscored by its economic value and widespread use. In the face of climate change, breeding resilient cultivars for variable environmental conditions becomes increasingly essential. However, the process of phenotyping, crucial to breeding programs, is often viewed as a bottleneck due to the inefficiency of traditional, low-throughput methods. To address this limitation, this study utilizes hyperspectral remote sensing, a promising tool for assessing crucial crop traits across forty cotton varieties. The results from this study demonstrated the effectiveness of four vegetation indices (VIs) in evaluating these varieties for water-use efficiency (WUE). The prediction accuracy for WUE through VIs such as the simple ratio water index (SRWI) and normalized difference water index (NDWI) was higher (up to R2 = 0.66), enabling better detection of phenotypic variations (P < 0.05) among the varieties compared to physiological-related traits (from R2 = 0.21 to R2= 0.42), with high repeatability and a low RMSE. These VIs also showed high Pearson correlations with WUE (up to r = 0.81) and yield-related traits (up to r = 0.63). We also selected high-performing varieties based on the VIs, WUE, and fiber quality traits. This study demonstrated that the hyperspectral-based proximal sensing approach helps rapidly assess the in-season performance of varieties for imperative traits and aids in precise breeding decisions.

Enhancing human resilience against climate change: Assessment of hydroclimatic extremes and sea level rise impacts on the Eastern Shore of Virginia, United States

Coastal regions face climate-induced threats that have likely increased over the past four decades. In this work, we quantify the future climate impacts on hydroclimatic extremes in the risk-prone, 15-m-above-sea-level Eastern Shore of Virginia (ESVA) region, utilizing the Sixth International Coupled Model Intercomparison Project (CMIP6) Assessment Report 6 (AR6) and General Circulation Models (GCMs). We incorporate historical data on demographics and disasters, land use land cover (LULC), Landsat imagery, and sea level rise (SLR) to better understand and highlight the correlation between hydroclimatic extremes and societal components in this region. The hydrological model Soil and Water Assessment Tool (SWAT), Standardized Precipitation Index (SPI), Normalized Difference Water Index (NDWI), and Interquartile Range (IQR) method have been used to evaluate the intensity and frequency of projected climate extremes, in which SLR projections under different greenhouse gas emission pathways are temporally and spatially quantified. Our findings include (1) a trend towards wetter conditions is found with an increase in the number of flood events and up to an 8.9 % rise in the severity of flood peaks compared to the 2003–2020 period; (2) current coastal high-risk regions, identified using historical data of natural disasters, demographics, and LULC, are projected to be more susceptible to future climate impacts; and (3) low-lying coastal towns and regions are identified as currently vulnerable to coastal and SLR-induced flooding and are projected to become even more susceptible by 2100. This is the first effort that provides a valuable scientific basis for anticipated shifts in future climate patterns, essential for natural hazard prevention in ESVA. It highlights the need for authorities and decision-makers to plan and implement adaptive strategies and sustainable policies for the ESVA region and other coastal areas across the United States.

Monitoring of coastline change using Sentinel-2 MSI data. A case study in Thanh Hoa Province, Vietnam

Vietnam is a coastal country with a coastline of more than 3,260 km, stretching from north to south. Coastal change in Vietnam is complicated further by the effects of climate change, including erosion and accretion, causing great impacts on infrastructure and the environment. This article presents the results of assessing coastline changes in Thanh Hoa Province (North Central region of Vietnam) from Sentinel-2 MSI satellite image data for the period 2015–23. Three Sentinel-2 MSI images taken in December 2015, December 2020 and December 2023 were used to calculate the water indices, including Normalised Difference Water Index (NDWI), Modified Normalised Difference Water Index (MNDWI) Argumented Normalised Difference Water Index (ANDWI) and Automated Water Extraction Index (AWEIsh), then extract the shoreline using the thresholding method and select the water index with the highest accuracy through comparing the overall accuracy and Kappa coefficient. The coastlines of 2015, 2020 and 2023 years are overlaid to evaluate the coastal changes in the study area. The results received in the study provide objective and timely information, helping managers effectively monitor and respond to coastline changes.

Bankline Migration Analysis of Brahmaputra River in Morigaon District, Assam using Automated Method

Objectives: The study examines spatio-temporal changes, forecasts bankline migration and seeks to determine its underlying causes and consequences. Methods: Bankline change detection was performed through comprehensive GPS-based field surveys and remote sensing data, validated with ground-based data. The NDWI and MNDWI used to delineate the bankline positions from 1988-2022, with temporal changes estimated using the DSAS model. Findings: The left and right riverbank have been divided into three exclusive zones to find out which zone is severely erosion and accretion prone regions for zone-wise exclusive analysis. In the analysis, it has noticed that the left bank experiencing severe bank erosion and the right bank is experiencing an accretion rate increase in the last few decades. The LRR statistics show that the erosion rate in the left bank (81.17 m/y) is significantly high with an accretion rate of 0 m/y in the observed area. On the other hand, in the right bank, the rate of erosion is 83.59 m/y and the rate of accretion is 68.45 m/y. The left bank’s erosion is notably high. Additionally, the erosion rate is severe in the zone C (118.22 m/y) of left bank line. In this zone, the erosion rate hiked by 59.58 m/y in 34 years. Novelty: This study addresses a significant gap in understanding the riverbank shifting dynamics along with its causes and socio-economic impact of the Brahmaputra River in the Morigaon district. By combining the hydrodynamic modelling and cause-effect analysis, it provides a comprehensive analysis of bankline migration patterns and their causes and consequences. Unlike previous research, which primarily focuses on bankline migration rates and land use changes, this research work uniquely explores the direct impact of riverbank shifting on local communities. The integration of advanced predictive models with detailed primary and secondary data analysis offers novel insights crucial for efficient flood management and policy making practices. Keywords: Normalised Difference Water Index (NDWI), Modified Normalized Difference Index (MNDWI), Digital Shoreline Analysis System (DSAS), EPR and LRR Model, Bankline Shift

Spatiotemporal lakes surface area changes over 35 years and potential causes in the Central Rift Valley, Ethiopia

Study RegionCentral Rift Valley (CRV) region, Ethiopia. Study FocusThe study aims to investigate the spatiotemporal change in lake water surface extents over 35 years (1986–2020) and identify potential causes. Three alternative multispectral water indices—Normalized Difference Water Index (NDWI), Automatic Water Extraction Index (AWEI), and Modified Normalized Difference Water Index (MNDWI)—derived from Landsat sensors (TM, ETM+, OLI) were utilized to extract and analyze the lake surface area. The Mann-Kendall correlation was applied to examine whether hydro-meteorological and anthropogenic variables are possible causes for changes. New Hydrological Insights for the RegionMNDWI outperforms other indices with over 96 % accuracy in mapping lake surface area. Lake Abiyata experienced the most significant reduction in surface area from 1986 to 2020 (>50 %), followed by Lake Ziway (<2 %) while Lake Langano remained relatively stable. This significant reduction positively correlates to alterations in lake water depth (R2=0.92). Factors such as increased temperature, evaporation, and water abstraction for soda ash production negatively correlated with lake surface area, while inflow from Bulbula River and mean annual rainfall showed positive correlations. Abiyata Lake's decrease in surface area is primarily attributed to water abstraction for soda-ash manufacturing and incoming river flow. If the current trends in water abstraction from the Lake and income water diversion continue, there is a high possibility that Lake Abiyata will change into a terminal lake shortly.

Geospatial Assessment of Wetland Changes in the Fringe Area of Dhaka City: Past, Present and Future Scenarios

This study examines the changes in wetlands in the fringe area of Dhaka city using geospatial assessment techniques. The wetland in the area is crucial as they serve as a buffer zone for the Dhaka Metropolitan Area (DMA) and play a significant role in maintaining the region's ecological balance. Thirty-meter NASA Landsat 4-5TM and Landsat 8 OLI satellite imagery were used to extract wetland features in the fringe area of Dhaka city. The Modified Normalized Difference Water Index (MNDWI) was applied to delineate wetland features. Finally, ArcGIS geometric computing was used to detect yearly changes, and a Cellular Automaton (CA) Markov Model was applied to predict future transitions. The research findings reveal that wetlands in the Dhaka Metropolitan Area are declining at a rate of 1.1% between 1991 and 2016, indicating the urgency of addressing this issue to ensure the sustainability of the region's natural resources. The percentage of wetlands in the fringe area has been decreasing significantly over the years, with wetlands making up only 12.98% of the fringe area in 2022, down from 28.22% in 1989. This trend is predicted to continue, with wetlands accounting for only 8.02% of the total area by 2034. The strong negative correlation coefficient between the year and wetland area suggests that the trend of decreasing wetland is likely to continue unless significant measures are taken to protect wetlands. The study highlights the importance of conserving and restoring wetlands in Dhaka's fringe areas to maintain the ecological balance of the region and support the well-being of both humans and wildlife. The Dhaka University Journal of Earth and Environmental Sciences, Vol. 12(2), 2023, P 97-117

Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset

Ireland’s coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep learning methods. However, limited research exists in this area, particularly for Ireland. This paper presents the Landsat Irish Coastal Segmentation (LICS) dataset, which aims to facilitate the development of deep learning methods for coastal water body segmentation while addressing modelling challenges specific to Irish meteorology and coastal types. The dataset is used to evaluate various automated approaches for segmentation, with U-NET achieving the highest accuracy of 95.0% among deep learning methods. Nevertheless, the Normalised Difference Water Index (NDWI) benchmark outperformed U-NET with an average accuracy of 97.2%. The study suggests that deep learning approaches can be further improved with more accurate training data and by considering alternative measurements of erosion. The LICS dataset and code are freely available to support reproducible research and further advancements in coastal monitoring efforts.

Exploring Urban Heat Distribution and Thermal Comfort Exposure Using Spatiotemporal Weighted Regression (STWR)

With rapid urbanization, many cities have experienced significant changes in land use and land cover (LULC), triggered urban heat islands (UHI), and increased the health risks of citizens’ exposure to UHI. Some studies have recognized residents’ inequitable exposure to UHI intensity. However, few have discussed the spatiotemporal heterogeneity in environmental justice and countermeasures for mitigating the inequalities. This study proposed a novel framework that integrates the population-weighted exposure model for assessing adjusted thermal comfort exposure (TCEa) and the spatiotemporal weighted regression (STWR) model for analyzing countermeasures. This framework can facilitate capturing the spatiotemporal heterogeneities in the response of TCEa to three specified land-surface and built-environment parameters (i.e., enhanced vegetation index (EVI), normalized difference built-up index (NDBI), and modified normalized difference water index (MNDWI)). Using this framework, we conducted an empirical study in the urban area of Fuzhou, China. Results showed that high TCEa was mainly concentrated in locations with dense populations and industrial regions. Although the TCEa’s responses to various land-surface and built-environment parameters differed at locations over time, the TCEa illustrated overall negative correlations with EVI and MNDWI while positive correlations with NDBI. Many exciting spatial details can be detected from the generated coefficient surfaces: (1) The influences of NDBI on TCEa may be magnified, especially in rapidly urbanizing areas. Still, they diminish to some extent, which may be related to the reduction in building construction activities caused by the COVID-19 epidemic and the gradual improvement of urbanization. (2) The influences of EVI on TCEa decline, which may be correlated with the population increase. (3) Compared with NDBI, the MNDWI had more continuous and stable significant cooling effects on TCEa. Several mitigation strategies based on the spatiotemporal heterogeneous relationships also emanated. The effectiveness of the presented framework was verified. It can help analysts effectively evaluate local thermal comfort exposure inequality and prompt timely mitigation efforts.

ASSESSMENT OF URBAN DYNAMICS – A CASE STUDY ON BERHAMPORE MUNICIPALITY AND ITS SURROUNDINGS, WEST BENGAL, INDIA

Berhampore was a former Armenian-to-British colony and historic commercial centre, had steady expansion during the colonial era, a still-ongoing trend. The natural landscape is transforming from the centre to the periphery in an extremely unpredictable way due to rapid urbanization. The current study examines the urban growth of Berhampore town in West Bengal, India, using geospatial techniques. To understand the spatiotemporal dynamics of the urban landscape from remotely sensed data, four indices are used: the Normalized Difference Built-up Index (NDBI), the Normalized Difference Vegetation Index (NDVI), the Built-up Index (BUI), and the Modified Normalized Difference Water Index (MNDWI).The result of these indices shows the unsustainable urbanization in this region. Over the course of thirty years, the built-up area increased by nearly 7.80 percent, depleting the prime vegetative cover, water bodies and, in some cases, the barren land. According to the study, it is helpful to determine current urban growth and development so that local planning authorities may control growth and development in accordance with the ecological or environmental carrying capacity of the region.

Assessing Machine Learning and Statistical Methods for Rock Glacier‐Based Permafrost Distribution in Northern Kargil Region

ABSTRACTEstimating permafrost distribution in high‐mountain areas is challenging. In these situations, rock glaciers, provide valuable insights into permafrost distribution and are often used as proxies for identifying permafrost occurrence. Integrating various climatological and topographical conditioning factors with rock glaciers enables inferring the distribution of permafrost in these environments. This study utilized three machine learning models such as random forest (RF), support vector (SVM), and artificial neural network (ANN), and one statistical model, namely, the frequency ratio (FR), to assess the permafrost probability over the northern Kargil region of Indian Himalayas. Among 198 rock glaciers identified through high‐resolution images from Google Earth, 70% are used as training dataset, rest 30% as testing dataset. The study considered eight factors: slope, aspect, elevation, curvature, mean annual land surface temperature (MA‐LST), mean annual normalized difference snow index (MA‐NDSI), mean annual normalized difference water index (MA‐NDWI), and lithology for mapping. Furthermore, the SHapley Additive exPlanations (SHAP) test assessed the variable importance for model performance. The results revealed that the RF model performs best for permafrost probability mapping, followed by the SVM, FR, and ANN models. The study also found that 11% of the total geographic area has a high and very high probability of permafrost occurrence.

Assessing the land use dynamics and thermal environment using geospatial techniques in the industrial city of Chotanagpur Plateau Region, India.

The phenomenon of urban heat island (UHI) is characterized by industrial, economic development, unplanned and unregulated land use as well as a rapid increase in urban population, resulting a warmer inner core in contrast to the surrounding natural environment, thus requiring immediate attention for a sustainable urban environment. This study examined the land use/land cover (LULC) change, pattern of spectral indices (Normalized Difference Vegetation Index, NDVI; Normalized Difference Water Index, NDWI; Normalized Difference Built-up Index, NDBI and Normalized Difference Bareness Index, NDBaI), retrieval of land surface temperature (LST) and Urban Thermal Field Variance Index (UTFVI) as well as identification of UHI from 2000 to 2022. The relationship among LST and LULC spectral indices was estimated using Pearson's correlation coefficient. The Landsat-5 (TM) and Landsat-8 (OLI/TIRS) satellite data have been used, and all tasks were completed through various geospatial tools like ArcGIS 10.8, Google Earth Engine (GEE), Erdas Imagine 2014 and R-Programming. The result of this study depicts over the period that built-up area and water bodies increased by 119.78 and 35.70%, respectively. On the contrary, fallow and barren decreased by 55.33 and 32.31% respectively over the period. The mean and maximum LST increased by 3.61 °C and 2.62 °C, and the study reveals that a high concentration of UTFVI and UHI in industrial areas, coal mining sites and their surroundings, but the core urban area has observed low LST and intensity of UHI than the peripheral areas due to maintained vegetation cover and water bodies. An inverse relationship has been found among LST, NDVI and NDWI, while adverse relationships were observed among LST, NDBI and NDBaI throughout the period. Sustainable environment planning is needful for the urban area, as well as the periphery region and plantation is one of the controlling measures of LST and UHI increment. This work provides the scientific base for the study of the thermal environment which can be one of the variables for planning of Asansol City and likewise other cities of the country as well as the world.

Geospatial Assessment of Oil Spill’s Impact in Obio/Akpor Local Government Area Rivers State, Nigeria

Environmental degradation resulting from oil spills has emerged as a critical issue requiring immediate attention. This study uses geospatial techniques to investigate the impact of oil spills in Obio/Akpor Local Government Area of Rivers State. Landsat images, administrative map of the study area and historical oil spill data were data used in carrying out this study. The images were pre-processed through atmospheric and geometric corrections. Spatial analysis of four remote sensing indices-Normalized Difference Vegetation Index (NDVI) for assessing vegetation health, Normalized Difference Water Index (NDWI) for detecting water bodies, Land Surface Temperature (LST) for measuring surface temperature, and Normalized Difference Built-Up Index (NDBI) for identifying built-up areas-was conducted using the raster calculator in ArcGIS. The study employed the Analytical Hierarchy Process (AHP) to assign weights to these indices based their relative significance regarding oil spill impact. Subsequently, reclassification and integration of this information were done to generate Oil Spill Index (OSI) maps for 2003, 2013, and 2023. Validation of the Oil Spill Index (OSI) of various points before and after an oil spill incident was performed, specifically contrasting 2003 with 2013 and 2023 OSI values. This was to affirm the accuracy and predictive capability of the OSI maps in identifying oil spill-prone areas. Findings revealed OSI values for 2003 and 2013, indicating a range of 1.04 to 3.48 for 2003, with a noticeable increase observed in 2013, expanding the range to 3.08 to 4.72. Similarly, a comparison of OSI values between 2003 and 2023 indicates OSI values, ranging from 1.64 to 3.92 in 2003, then in 2023 after the oil spill incidents, there were notable changes in the OSI values, with the range shifting to 3.2 to 4.84. This suggests a significant increase in the impact of oil spill on the affected areas over the two-decade. This comprehensive index map serves as a tool for monitoring and assessing the effects of oil spills on the study area, thereby achieving the research objectives effectively.