Using google earth engine to detect the land use changes, climate change and vegetation dynamics

Estimation of land surface temperature and LULC changes impact on groundwater resources in the semi-arid region of Madhya Pradesh, India

Land use and land cover (LULC) changes are one of the main factors contributing to ecosystem degradation and global climate change. This study used the Gontougo Region as a study area, which is fast changing in land occupation and most vulnerable to climate change. The machine learning (ML) method through Google Earth Engine (GEE) is a widely used technique for the spatiotemporal evaluation of LULC changes and their effects on land surface temperature (LST). Using Landsat 8 OLI and TIRS images from 2015 to 2022, we analyzed vegetation cover using the Normalized Difference Vegetation Index (NDVI) and computed LST. Their correlation was significant, and the Pearson correlation (r) was negative for each correlation over the year. The correspondence of the NDVI and LST reclassifications has also shown that non-vegetation land corresponds to very high temperatures (34.33°C–45.22°C in 2015 and 34.26°C–45.81°C in 2022) and that high vegetation land corresponds to low temperatures (17.33°C–28.77°C in 2015 and 16.53 29.11°C in 2022). Moreover, using a random forest algorithm (RFA) and Sentinel-2 images for 2015 and 2022, we obtained six LULC classes: bareland and settlement, forest, waterbody, savannah, annual crops, and perennial crops. The overall accuracy (OA) of each LULC map was 93.77% and 96.01%, respectively. Similarly, the kappa was 0.87 in 2015 and 0.92 in 2022. The LULC classes forest and annual crops lost 48.13% and 65.14%, respectively, of their areas for the benefit of perennial crops from 2015 to 2022. The correlation between LULC and LST showed that the forest class registered the low mean temperature (28.69°C in 2015 and 28.46°C in 2022), and the bareland/settlement registered the highest mean temperature (35.18°C in 2015 and 35.41°C in 2022). The results show that high-resolution images can be used for monitoring biophysical parameters in vegetation and surface temperature and showed benefits for evaluating food security.

Rapid urbanization and industrialization cause land use changes, reduce green spaces, and increase the land surface temperature. Green spaces of a city area maintain environmental quality by absorbing air pollutants and reducing land surface temperature. The present study aimed to detect the changes in land use and land cover (LULC), normalized difference vegetation index (NDVI), and land surface temperature (LST) in the Narsingdi district including six Upazilas from 2001 to 2021. The Landsat 7- Enhanced Thematic Mapper Plus (ETM+), the Landsat 8- Operational Land Imager (OLI) imageries and the Moderate Resolution Imaging Spectroradiometer (MODIS) data were used to analyze the LULC, NDVI, and LST by using Google Earth Engine (GEE) and ArcGIS 10.8.2. The images were analyzed into four land use classifications – agricultural land, built-up area, forest vegetation, and water body. Among all the Upazilas, Narsingdi Sadar was the vulnerable area, where agricultural land, forest coverage, and water body decreased significantly by 6.67%, 2.2%, and 4.66%, respectively. The built-up area increased by a considerable amount of 13.53% during the last twenty years. The forest coverage of Narsingdi Sadar Upazila was calculated at only 8.91% in 2021 and decreased from 11.11% in 2001. The NDVI values surprisingly increased in all the Upazilas, but in Narsingdi Sadar, it is comparatively low (0.08) than in other Upazilas. The increasing trend in LST in the Narsingdi Sadar Upazila is alarming, 1.14oC from 2001 to 2021 (0.57oC/decade). The significant changes in LULC, NDVI, and LST made the Narsingdi Sadar a more critical area in the Narsingdi district. The findings of the study will be helpful to policymakers in making appropriate decisions in future city development. J. of Sci. and Tech. Res. 5(1): 93-118, 2023

Assessment of LULC change dynamics and its relationship with LST and spectral indices in a rural area of Bengaluru district, Karnataka India

The changes in land use and land cover (LULC) determine the change of the normalised difference vegetation index (NDVI) and of the land surface temperature (LST) which characterise the environment at a given moment. This study examines the LULC changes affecting the LST-NDVI relationship, using Landsat 5 Thematic Mapper (TM) and 7 Enhanced Thematic Mapper Plus (ETM+) images acquired in 1987, 2000, and 2009 in the metropolitan area of Brasov, Romania. The images were classified into seven LULC classes through the supervised classification method. NDVI maps and LST maps were obtained on the basis of the three images, atmospherically and radiometrically corrected. The relationship between LST and NDVI was analysed by linear regression for each image and for each LULC class. The results obtained show that there is a negative correlation between LST and NDVI for all the LULC classes considered together as well as for each class considered separately.

Rapid changes in land use and land cover (LULC) have ecological and environmental effects in metropolitan areas. Since the 1990s, Saudi Arabia's cities have undergone tremendous urban growth, causing urban heat islands, groundwater depletion, air pollution, loss of ecosystem services, etc. This study evaluates the variance and heterogeneity in land surface temperature (LST) because of LULC changes in Abha-Khamis Mushyet, Saudi Arabia, from 1990 to 2020. The research aims to determine the impact of urban biophysical parameters on the High-High (H-H) LST cluster using geospatial, statistical, and machine learning techniques. The support vector machine (SVM) was used to map LULC. The land surface temperature (LST) has been derived using the mono-window algorithm (MWA). The local indicator of spatial associations (LISA) model was implemented on the spatiotemporal LST maps to identify LST clusters. Also, the parallel coordinate plot (PCP) approach was employed to examine the relationship between LST clusters and urban biophysical variables as a proxy of LULC. LULC maps show that urban areas rose by > 330% between 1990 and 2020. Built-up areas had an 83.6% transitional probability between 1990 and 2020. In addition, vegetation and agricultural land have been transformed into built-up areas by 17.9% and 21.8% respectively between 1990 and 2020. Uneven LULC changes in terms of built-up areas lead to increased LST hotspots. High normalized difference built-up index (NDBI) was linked to LST hotspots but not normalized difference water index (NDWI) or normalized difference vegetation index (NDVI). This research could help policymakers develop mitigation strategies for urban heat islands.

The main objective of this study is to understand the effects of climate change on the environment and natural resources in the Chhatarpur district of Madhya Pradesh, India. This paper focuses on the changes in land use and land cover (LULC) for 20 years and its effect on land surface temperature (LST), the normalized difference vegetation index (NDVI), and groundwater level in the Chhatarpur district of Madhya Pradesh. The study places a significant emphasis on the role of the urban thermal field variance index (UTFVI) in understanding the effect of the urban heat index (UHI) on the groundwater level. A random forest (RF) model is used for LULC mapping with the help of Landsat 8 OLI/TIRS in the Google Earth Engine (GEE) platform. The results showed that the LST and UHI indexes directly affect the LULC classes and groundwater in the Chhatarpur district. This study found that in 2021, the urban area will increase, impacting the LST of metropolitan areas and nearby areas. Similarly, agriculture and land waste decreased in 2021. The results of this study, which can help understand the environmental and LULC changes, have the potential to significantly influence policy and development activities in the study area.

Time series analysis of land use and land cover changes related to urban heat island intensity: Case of Bangkok Metropolitan Area in Thailand

Studies on land use and land cover (LULC) changes and subsequent effects on environment are not satisfactory in Bangladesh because of the lack of geospatial data and time-series information. By using the open-source Landsat 7 and Landsat 8 imagery data coupled with GIS technology and other ancillary data, the main purpose of this study is to analyze the dynamic changes in LULC in Jashore district of Bangladesh over a 20-year period between 2002 and 2022. Including pre-classification and post-classification identification scenarios, Normalized Difference Vegetation Index (NDVI) analysis was employed to examine the vegetation changes over the period. ArcGIS 10.8 software was employed for analyzing satellite images, and maximum likelihood classification was utilized to create supervised land cover category (water bodies, vegetation, built-up area, and bare soil). Microsoft Excel was used for data analysis and visualization. The findings of this present study indicate notable changes with an increase of 20.77% in urban areas and 14.53% in bare soil. Additionally, there has been a decline of 2.93% in water bodies and 32.37% in vegetation land cover including both natural and anthropogenically modified vegetation such as forests, croplands, grasslands and others. Accuracy evaluations on the land use classification's trustworthiness include Kappa statistics of 0.80 for the year 2022 and 0.65 for the year 2002. A decrease in land surface temperature (LST) in Jashore district over 20 years from 2002 to 2022 has been reported in this study. Although the proportion of vegetation cover has been reduced in 2022, we found a negative correlation between LST and NDVI. Along with LULC, the LST is influenced by many atmospheric and ecological parameters. NDVI is dependent on vegetation canopy type, color and density, which could affect the relationship with LST. The findings of this study provide insightful information to ecologists, environmentalists, urban planners, and lawmakers for developing sustainable land management plans and environmental conservation initiatives.

Anthropogenic land alterations in Maun village have transformed natural vegetation into urban infrastructure, including pavements, and residential and commercial areas, leading to elevated Land Surface Temperature (LST). This urban expansion resulted from economic growth driven by population increase and tourism-related development. This study aims to evaluate the relationship between Land Use and Land Cover Changes (LULCCs) and LST. Utilising Landsat 5-TM and Landsat-8 data from 1990, 2000, and 2020, we employed a random forest algorithm for supervised classification, generating Land Use and Land Cover (LULC) maps. The mono-window algorithm was used to extract LST data from Landsat 5 and 8 images, alongside Normalised Difference Vegetation Index (NDVI) maps. s regression analysis assessed the LST-NDVI correlation. Results indicate that urban LULCCs significantly contribute to rising LST. Minimum and maximum LST values for 1990, 2000, and 2020 were 18.6°C, 22.8°C, 22.6°C, and 26.7°C, 34.5°C, and 42.1°C, respectively. NDVI values ranged from −0.2 to 0.56 in 1990, −0.17 to 0.58 in 2000, and 0.07 to 0.46 in 2020. Roads, pavements, barren land, and built-up areas displayed the highest LST (44.6°C), while water bodies and healthy vegetation exhibited the lowest (16.1°C). Additionally, NDVI exhibited a negative correlation with LST. Our findings emphasise the role of human activities in exacerbating LST. They highlight the need for regulated urban growth patterns to ensure sustainable development. Moreover, quantifying spatiotemporal variations in LULC, LST, and NDVI holds importance for conserving land resources and enhancing land use planning policies. Policymakers and city planners can utilise this research to mitigate heat stress effects and promote sustainable urban environments by evaluating distribution maps of LULC, NDVI, and LST.

In this study, three multi-temporal remotely sensed data acquired from Landsat-5 Thematic Mapper (TM) and Landsat -8 Operational Land Imager/Thermal Infrared Sensor (OLI/TIRS) in 1990, 2005, and 2020 were used. The maximum likelihood classifier (MLC) was opted to classify land use and land cover (LULC). Land surface temperature (LST) and LULC spectral indices i.e., Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Latent Heat Index (NDLI) and Bare Soil Index (BSI) have been computed and their relationships were examined. The overall accuracy of LULC was more than 93%. The analyses showed a notable transformation in LULC over the study period. For instance, built-up areas increased 103.7% with a rate of 45.5 ha/year and agriculture land increased by 28.9% with a rate of 186.4 ha/year. Whereas, bare soil was sharply decreased by 36.4% at a rate of 227.7ha/year. The minimum and maximum LST values increased by 2.9°C and 4.9°C, respectively, from 1990 to 2020. Furthermore, LST has a negative relationship with NDVI and NDLI (NDVI: 1990: r2 = 0.62; 2005: r2 = 0.62; 2020: r2 = 0.65. NDLI: 1990: r2 = 0.79; 2005: r2 = 0.78; 2020: r2 = 0.61) and a positive relationship with NDBI and BSI (NDBI: 1990: r2 = 0.68; 2005: r2 = 0.73; 2020: r2 = 0.44. BSI: 1990: r2 = 0.77; 2005: r2 = 0.78; 2020: r2 = 0.53). These results provided useful information about LULC changes and its impact on LST, which are necessary for experts and land-use planners to formulate sustainable LST mitigation policies, create an environmental comfort in Nag-Hammadi district, and other geographical locations with similar conditions.

Due to expanding populations and thriving economies, studies into the built environment’s thermal characteristics have increased. This research tracks and predicts how land use and land cover (LULC) changes may affect ground temperatures, urban heat islands, and city thermal fields (UTFVI). The current study examines land surface temperature (LST), urban thermal field variance index (UTFVI), normalized difference built-up index (NDBI), normalized difference vegetation index (NDVI), and land use land cover (LULC) on a kilometer scale. According to the comparative study, the mean LST decreases by 3 °C and the NDVI increases considerably. Correlation analysis showed that LST and NDVI are inversely connected, while LST and NDBI are positively correlated. NDVI and NDBI have a strong negative association, while LST and UTFVI have a positive correlation. Urban planners and environmentalists can study the LST’s effects on land surface parameters in different environmental contexts during the lockout period. The urban heat island (UHI) phenomenon, in which the land surface qualities of an urban region cause a change in the urban thermal environment, forms and intensifies over an urban area. The minimum and maximum LST in grid number 1 in 2009 was 20.30 °C and 29.91 °C, respectively, with a mean LST of 25.1 °C. There was a decline in the minimum and maximum LST in grid number 1 in 2020 with a minimum and maximum LST of 17.31 °C and 25.35 °C, respectively, with a mean LST of 21.33 °C. There was a 3.8 °C drop in the LST of this grid. The minimum and maximum NDVI were also − 0.16 and 0.59, respectively, with an average NDVI value of 0.21. Therefore, it is essential to evaluate and foresee the impact of LULC change on the thermal environment and examines the connection between LULC shifts with subsequent changes in land surface temperature (LST) along with the UHI phenomenon. Maps of the UTFVI reveal positive UHI phenomena, with the highest UTFVI zones occurring over the developed area and none over the adjacent rural territory. During the summer months, the urban area with the strongest UTFVI zone grows noticeably larger than it does during the winter months during the forecasted years. Future policymakers and city planners can mitigate the effects of heat stress and create more sustainable urban environments by evaluating the expected distribution maps of LULC, LST, UHI, and UTFVI.

Analysis and prediction of land surface temperature with increasing urbanisation using satellite imagery

Growth in urban areas contributes to environmental degradation through increased land surface temperature (LST), exacerbating the urban heat island (UHI) effect. This study examined how land use and land cover (LULC) characteristics of Shillong City are linked to the UHI phenomenon. The LULC was classified into five broad categories: agricultural land, barren land, settlement, vegetation, and water bodies. The results show that the study area experienced notable changes in the LULC pattern from 1993 to 2023, with settlement areas increasing by 10.96%, transforming previously barren lands. The emergence and growth of settlements (and/or built-up areas) and impervious surfaces have led to a steady increase in LST. The settlement land use class had an average LST of 17.45 °C in 1993, 21.56 °C in 2003, 21.37 °C in 2013, and 21.75 °C in 2023. From 1993 to 2023, surface temperatures in settlement areas rose by a maximum of 4.3 °C, while barren land and vegetated areas also saw an increase of 4.9 °C and 4.0 °C, respectively. The relationship between LULC and the LST has been evaluated to identify hotspot areas. The highest temperatures are found in crowded and dense built-up areas, while the lowest temperatures are found in vegetated areas and water bodies. The findings also reveal a clear warming trend over the 30-year period, marked by a substantial decrease in areas with LST below 12 °C and between 12–17 °C, highlighting a shift towards warmer temperatures. Projected LULC changes indicate that urban areas will experience significant growth, increasing from 17.36% of the total area in 2023 to 21.39% in 2030, and further to 28.56% by 2050. The results suggest that the settlement land use class will increase by 11.2%, accompanied by a decrease in agricultural lands, vegetation, and water bodies.

Land surface temperature (LST) analysis of satellite data is critical for studying the environmental land degradation impacts. However, challenges arise to correlate the LST and field data due to the constant development in land use and land cover (LULC). This study aims to monitor, analyze, assess, and map the environmental land degradation impacts utilizing image processing and GIS tools of satellite data and fieldwork. Two thermal and optical sets of Landsat TM + 5 and TIRS + 8 data dated 1984 and 2018 were used to map the thermal and LULC changes in the Suez Canal region (SCR). The LULC classification was categorized into water bodies, urban areas, vegetation, baren areas, wetland, clay, and salt. LULC and LST change detection results revealed that vegetation and urban areas increased in their areas in 34 years. Moreover, 97% of the SCR witnessed LST rise during this period with an average rise rate of 0.352 °C per year. The most effective LULC class changes on LST were the conversions from or to baren areas, where baren areas were converted to 630.5 km2 vegetation and 104 km2 urban areas rising the LST to 43.57 °C and 45 °C, respectively. The spectral reflectance (LSR), LST profiles, and statistical analyses examined the association between LST and LULC deriving factors. In combination with field observations, five hotspots were chosen to detect and monitor natural and human land degradation impacts on LST of the SCR environment. Land degradations detected include water pollution, groundwater rising, salinity increase, sand dune migration, and seismic activity.