Google Earth Engine Platform Research Articles

Monitoring small-scale irrigation performance using remote sensing in the Upper Blue Nile Basin, Ethiopia

Temporal and spatial irrigation performance indicators are crucial in informing decisions for improving the efficiency and sustainability of water and land resources. However, evaluating these indicators requires reliable and cost-effective data, which is challenging to obtain, particularly for small-scale irrigation schemes. This study aimed to assess the performance of a small-scale irrigation scheme using remote sensing and ground truth data for the 2021/22 and 2022/2023 irrigation seasons employing the Shimburit irrigation scheme in Northwestern Ethiopia, predominantly cultivated with wheat, as a case study. The performance indicators, including equity, adequacy, overall consumed ratio (OCR), and productivity, were assessed. The actual evapotranspiration (ET), the main input for performance assessment, was estimated using the surface energy balance for land – improved (SEBALI) model in the Google Earth Engine (GEE) platform. The results revealed good equity within the scheme, with a coefficient of variation of ETa value per field inside the scheme are 1.90 and 1.63 for the respective seasons. The water use adequacy across the fields was assessed to be very good in the two seasons. The scheme's overall consumed ratio (OCR) was 0.54 and 0.43 during the two subsequent seasons. Water productivity of wheat is 3.03 kg/m3 and 3.06 kg/m3 in the two seasons. However, due to untimely rainfall during harvest, land productivity declined from 3.25 tons/ha in the first season to 2.08 tons/ha in the second season. The study demonstrates the potential of using remote sensing to evaluate irrigation performance indicators and water productivity in smallholder irrigated fields.

Application of MNDWI index for flood damage area calculation in Lam river basin using google earth engine platform

Application of MNDWI index for flood damage area calculation in Lam river basin using google earth engine platform

Reconnaissance of spatio-temporal variability in ecological stability with local adaptability based on multi-temporal LANDSAT archive in ganga river basin

Assessment of ecological environment is an indispensable part of the eco-environment protection and restoration. This study utilizes a remote sensing-based ecological index (RSEI) to better understand the environmental scenario in the Ganga basin. RSEI has been computed using five parameters: Wetness, Dryness, Greenness, Heat, and a newly incorporated parameter Albedo representative of land degradation. Median-based RSEI maps have been constructed using LANDSAT archives in Google Earth Engine (GEE) platform, covering three decades (1990–2021). The Ganga basin has been divided into five agro-climatic zones. For each zone and time frame (1990–99, 2000–09, 2010–19, and 2020–21), a median-based RSEI map has been generated. The analysis reveals that RSEI becomes poorer for sub-basin 1 (SB1), sub-basin 2 (SB2), and sub-basin 5 (SB5) in the 2010–19 period compared to the 1990–99 and 2000–09 periods. On the other hand, RSEI for sub-basin 3 (SB3) improved in the 2010–19 period compared to the previously mentioned periods. Sub-basin 4 (SB4) remained the least fluctuated region compared to the other sub-basins. The Global Moran's I value is highest for SB3 for the 1990–99 and 2000–09 periods, while for the 2010–19 and 2020–21 periods, SB2 has the highest Global Moran's I. This study incorporates big data analysis and can be indispensable in exploring the interactions between ecosystem services and anthropogenic activities in river basin systems.

Examining chlorophyll-a concentrations in tropical reservoirs under various land use changes using Sentinel – 2 and Google Earth engine – Bhadra and Tungabhadra, India

The understanding of spatio-temporal variation in land use and land cover (LULC) patterns is crucial for managing catchment land use planning, as it directly influences of tropical reservoir water quality and the subsequent Nutrient Contamination (NC) of unmonitored water bodies. The current research attempts to accurately measure the influence of LULC and its associated determinants on the quantities of NC loads by using Chl-a as a proxy, within tropical reservoirs, i.e. Bhadra and Tungabhadra, located in same river catchment. This Chl-a spread calculated by the Maximum Chlorophyll Index (MCI) derived from Sentinel 2 satellite data products covering the period from July 2016 to June 2021 were done using Google Earth Engine (GEE) platform. The validation analysis confirms the robustness of the methodology with a strong correlation between MCI-calculated values and EOMAP (Earth Observation and Environmental Services Mapping) Chl-a (μg/L) data points for both reservoirs, Bhadra (R2 = 0.64) and Tungabhadra (R2 = 0.68). The findings reveal that, Tungabhadra reservoir consistently exhibits an excessive spatial distribution of Chl-a spread area (17 km2 to 335 km2), reflecting nutrient-rich water inflows, particularly evident during the post-monsoon period. This notable rise could be linked to harvesting the Kharif crop, resulting in elevated nutrient concentrations. In contrast Bhadra reservoir, dominated by forested areas, maintains relatively lower Chl-a spread areas (<20 km2), highlighting its pivotal role in maintaining water cleanliness and serves as a riparian boundary. In addition, the changes in LULC classes show a strong relationship with variation in Chl-a during the studied period, for the Bhadra Reservoir R2 = 0.51 (F- statistics = 3.983, p = 0.021), and the Tungabhadra Reservoir R2 = 0.802 (F- statistics = 7.489, p = 0.0143). This highlights how changes in land use significantly shape contamination dynamics, deepening our understanding of nutrient inputs and contamination drivers in tropical reservoirs.

Sentinel 2 based burn severity mapping and assessing post-fire impacts on forests and buildings in the Mizoram, a north-eastern Himalayan region

The Increasing frequency and severity of forest fires worldwide highlights the need for more effective Burnt area mapping. Finding the effects of fire on vegetation and putting mitigation methods in place, depends on post-fire evaluation. In this study, the location of the burned regions and the severity of the fire were determined using high-resolution multi-spectral images from Sentinel 2 on Google Earth Engine (GEE) platform. Three widely used fire severity indices—differenced Normalized Burn Ratio (dNBR), Relativized Burn Ratio (RBR), and Relativized dNBR (RdNBR)—based on pre-fire Normalized Burn Ratio (NBR) and post-fire NBR—were computed and compared based on their accuracy using very high-resolution planet imagery fire points and equal number of random non fire points. Maps also validated with active fires, ground based photos and crowdsourced images. The accuracy (AUC) of the RdNBR map was 85%, RBR - 84% and dNBR −82%. The RdNBR index demonstrated highest level of accuracy. Then the loss to vegetation using pre-fire and post-fire NDVI was analysed. The analysis of pre-fire and post-fire NDVI provided insights into the extent of vegetation loss. The analysis of vegetation loss offered valuable information regarding the impact of fire on the affected areas. Google building dataset was used to monitor the percent of buildings under threat due to these fires. Around 8.77% of buildings were found in high severity region. Accurate mapping aids post-fire evaluation, guided mitigation strategies, and enhanced forest management and ecological restoration.

Drought Monitoring Using MODIS Derived Indices and Google Earth Engine Platform for Vadodara District, Gujarat

Drought Monitoring Using MODIS Derived Indices and Google Earth Engine Platform for Vadodara District, Gujarat

Analysis and visualization of spatio-temporal variations of ecological vulnerability in Pakistan using satellite observation datasets

Pakistan is the fifth most populous country in the world. Its ecological environment is facing numerous stresses such as climate change, rapid urbanization, natural disasters, and a decline in air quality. Thus, the scientific understanding of spatial and temporal changes in Pakistan's ecological environment is crucial for formulating an informed strategy for regional sustainability. This study used the Google Earth Engine platform and the Remote Sensing Ecological Index (RSEI) to investigate ecological vulnerability in three provinces of Pakistan for 1990, 2000, 2010, and 2020. Landsat 5 and Landsat 8 datasets are used to construct RSEI indicators and Principal Component Analysis (PCA) is adopted to objectively compute RSEI for the past three decades. The results indicated that (1) the ecological vulnerability of the Punjab province exhibited a slightly improved trend from 1990 to 2020 with overall dominance of ‘moderate’ level vulnerability in all four years; (2) The Sindh province has exhibited a declining trend of the ecological environment with ‘poor’ ecological vulnerability contributing to 28.6% of the total area in 2020 as compared to 1.04% of the total area in 1990; and (3) The ecological environment of Balochistan province has shown resilience to some extent during 1900–2010 with the dominance of a ‘moderate’ level of ecological vulnerability. However, a decline is observed between 2010 and 2020. These research results can provide support for the Punjab, Sindh, and Balochistan provinces in achieving sustainable development while conserving the regional ecological environment.

Identifying clusters of precipitation for the Brazilian Legal Amazon based on magnitude of trends and its correlation with sea surface temperature

Prioritizing watershed management interventions relies on delineating homogeneous precipitation regions. In this study, we identify these regions in the Brazilian Legal Amazon based on the magnitude of Sen’s Slope trends using annual precipitation data from September to August, employing the Google Earth Engine platform. Utilizing the silhouette method, we determine four distinct clusters representing zones of homogeneous precipitation patterns. Cluster 0 exhibits a significant median increase in precipitation of 3.20 mm year−1 over the period from 1981 to 2020. Cluster 1 shows a notable increase of 8.13 mm year−1, while Clusters 2 and 3 demonstrate reductions in precipitation of − 1.61 mm year−1 and − 3.87 mm year−1, respectively, all statistically significant. Notably, the region known as the arc of deforestation falls within Cluster 2, indicating a concerning trend of reduced precipitation. Additionally, our analysis reveals significant correlations between Sea Surface Temperature (SST) in various oceanic regions and precipitation patterns over the Brazilian Legal Amazon. Particularly noteworthy is the strong positive correlation with SST in the South Atlantic, while negative correlations are observed with SST in the South Pacific and North Atlantic. These findings provide valuable insights for enhancing climate adaptation strategies in the Brazilian Legal Amazon region.

Using cloud computing techniques to map the geographic extent of informal settlements in the greater Cape Town Metropolitan Area

Although remote sensing approaches offer unprecedented opportunities to understand urban land cover dynamics including informal settlements areal extent, challenges such as spectral confusions still persist, particularly when segregating land cover types like informal settlements from planned formal settlements. The improvements in Earth Observation (EO) data analytic tools such as introduction of Google Earth Engine (GEE) cloud computing platform, provide prospects to improve separability of these settlements from other urban land cover classes, via their advanced data processing and filtering algorithm, which allows for the synergic use of multisource and multi-temporal data, thus improving detection and monitoring of these settlements. This study harnessed the advance data analytic powers of GEE cloud computing platform coupled with higher resolution Sentinel-2 data to map the geographical extent of informal settlement in the Cape Town Metropolitan Area. The classification yielded six land cover classes: formal settlements, informal settlements, water, bare or built-up areas, vegetated lands, and croplands. Built-up formal settlement was the most dominant class, accounting for 70% of the total Cape Town surface area, while open water was the least dominant, accounting for 2%. Informal settlements accounted for approximately 7% of all settlements. Although overall accuracy was within acceptable limits (68%), some classes, such as vegetated lands and formal settlements, reported low class accuracies due to spectral similarities with other classes. The findings highlight the importance of the GEE platform, as well as the interaction of contextual and spectral characteristics, as well as various sentinel-2 derived water, built up, and vegetation indices in mapping informal settlements. These findings are critical for the facilitation of improved urban planning, provision of services and assisting in alleviating social as well as environmental issues within the Cape Town Metropolitan area.

Remote Monitoring of Coffee Leaf Miner Infestation Using Machine Learning

The coffee leaf miner (Leucoptera coffeella) is a key pest in coffee-producing regions in Brazil. The objective of this work was to evaluate the potential of machine learning algorithms to identify coffee leaf miner infestation by considering the assessment period and Sentinel-2 satellite images generated on the Google Earth Engine platform. Coffee leaf miner infestation in the field was measured monthly from 2019 to 2023. Images were selected from the Sentinel-2 satellite to determine 13 vegetative indices. The selection of images and calculations of the vegetation indices were carried out using the Google Earth Engine platform. A database was generated with information on coffee leaf miner infestation, vegetation indices, and assessment times. The database was separated into training data and testing data. Nine machine learning algorithms were used, including Linear Discriminant Analysis, Random Forest, Support Vector Machine, k-nearest neighbors, and Logistic Regression, and a principal component analysis was conducted for each algorithm. After optimizing the hyperparameters, the testing data were used to validate the model. The best model to estimate miner infestation was RF, which had an accuracy of 0.86, a kappa index of 0.64, and a precision of 0.87. The developed models were capable of monitoring coffee leaf miner infestation.

Analysis of Changes in Water Body Area in Southwest, China Based on GEE

It is of great significance for policymakers to develop management strategies for water resource regulation, habitat protection and wetland restoration. Based on the Google Earth Engine platform, this study extracted remote sensing data of water quality change in Southwest China in the past 20 years, combined with ArcGIS for spatial analysis, and used M-K trend test and mutation test to analyze the long-term temporal variation of water bodies in Southwest China. The analysis shows that the water area in Southwest China increased every five years from 2000 to 2020, but the growth rate changed, while the growth rate slowed down from 2010 to 2020, and the increase mainly occurred in the central and western regions. The results show that in the past 20 years, the water surface area in Southwest China has shown a statistically significant increasing trend, especially after 2020, this trend is more statistically significant. This study can provide a theoretical basis for the protection of water environment in Southwest China.

Algorithm, Progresses, Datasets and Validation of GLC_FCS30D: the first global 30 m land-cover dynamic product with fine classification system from 1985 to 2022

Abstract. Land cover change information plays an indispensable role in environmental monitoring, climate change research, agricultural planning, urban development, biodiversity conservation, and natural disaster risk assessment. Recently, the free access of Landsat imagery and improvement of computation capacity especially supported by Google Earth Engine platform provides great chance in time-series land-cover change monitoring. We used the stratified land-cover monitoring strategy and time-series Landsat imagery to develop a novel global 30 m land-cover dynamic product with fine classification system from 1985 to 2022 (GLC_FCS30D). Firstly, we used the multitemporal classification to generate the time-series impervious surfaces, wetlands and tidal flat products. Then, we proposed to combine the continuous change detection algorithm and local adaptive updating model to capture the land-cover changes, and to generate a new global 30 m land-cover dynamic product (impervious surfaces, wetlands and tidal flat types were excluded in this step). Next, after overlapping the three multitemporal classification products and the time-series dynamical land-cover dataset, the novel GLC_FCS30D was developed, which contained 35 fine land-cover types. Lastly, using the global 84526 validation points in 2020, the GLC_FCS30D was validated to show the great performance with an overall accuracy of 80.88%, and had obvious advantages over other global land-cover products in diversity of land-cover types and mapping accuracy.

Mapping the paleo-landscape features and middle or/and later Stone Age settlements of Tokar region, North-eastern Sudan using Radar Sentinel-1 (GRD) imagery

Along the western coastal plain of the Red Sea, the discovery of lithic tools proved that the occurrence of archaeological remains belonged to the Stone Age era. Unfortunately, until recently, most of the Stone Age site plans in the western Red Sea periphery have been unknown because of change in climate in addition to covering these sites with a large layer of sand. Recently, remote sensing (RS) data have proven to be effective at identifying buried archaeological sites using radar satellite imagery due to their ability to penetrate the land surface. This paper aims to identify and reconstruct several potential Stone Age sites using radar satellite images in the Tokar region, North-Eastern Sudan, on the western plain of the Red Sea. Radar (Sentinel-1 SAR GRD: C-band) data were processed utilizing the advantages of the Google Earth Engine platform and Snap software. The results of this research showed that some potential settlements belonging to the Stone Age era (expectedly dating back to the end of the Pleistocene and/or the initial phase of the Holocene) have subcircular shapes with some interior subcircles. These results shed new light on the potential construction technique, size, and function of the settlement in the Stone Age era and can provide some initial insights into the ancient lifestyle in this region. Additionally, this study can aid in future archaeological surveys and excavation missions in this region.

Google Earth Engine and Machine Learning for Flash Flood Exposure Mapping—Case Study: Tetouan, Morocco

Recently, the earth’s climate has changed considerably, leading to several hazards, including flash floods (FFs). This study aims to introduce an innovative approach to mapping and identifying FF exposure in the city of Tetouan, Morocco. To address this problem, the study uses different machine learning methods applied to remote sensing imagery within the Google Earth Engine (GEE) platform. To achieve this, the first phase of this study was to map land use and land cover (LULC) using Random Forest (RF), a Support Vector Machine (SVM), and Classification and Regression Trees (CART). By comparing the results of five composite methods (mode, maximum, minimum, mean, and median) based on Sentinel images, LULC was generated for each method. In the second phase, the precise LULC was used as a related factor to others (Stream Power Index (SPI), Topographic Position Index (TPI), Slope, Profile Curvature, Plan Curvature, Aspect, Elevation, and Topographic Wetness Index (TWI)). In addition to 2024 non-flood and flood points to predict and detect FF susceptibility, 70% of the dataset was used to train the model by comparing different algorithms (RF, SVM, Logistic Regression (LR), Multilayer Perceptron (MLP), and Naive Bayes (NB)); the rest of the dataset (30%) was used for evaluation. Model performance was evaluated by five-fold cross-validation to assess the model’s ability on new data using metrics such as precision, score, kappa index, recall, and the receiver operating characteristic (ROC) curve. In the third phase, the high FF susceptibility areas were analyzed for two-way validation with inundated areas generated from Sentinel-1 SAR imagery with coherent change detection (CDD). Finally, the validated inundation map was intersected with the LULC areas and population density for FF exposure and assessment. The initial results of this study in terms of LULC mapping showed that the most appropriate method in this research region is the use of an SVM trained on a mean composite. Similarly, the results of the FF susceptibility assessment showed that the RF algorithm performed best with an accuracy of 96%. In the final analysis, the FF exposure map showed that 2465 hectares were affected and 198,913 inhabitants were at risk. In conclusion, the proposed approach not only allows us to assess the impact of FF in this study area but also provides a versatile approach that can be applied in different regions around the world and can help decision-makers plan FF mitigation strategies.

Remotely Sensed Changes in Qinghai–Tibet Plateau Wetland Ecosystems and Their Response to Drought

Wetland ecosystems in the Qinghai–Tibet Plateau are pivotal for global ecology and regional sustainability. This study investigates the dynamic changes in wetland ecosystems within the Chaidamu Basin and their response to drought, aiming to foster sustainable wetland utilization in the Qinghai–Tibet Plateau. Using Landsat TM/ETM/OLI data on the Google Earth Engine platform, we employed a random forest (RF) method for annual long-term land cover classification. Standardized precipitation evapotranspiration indices (SPEI3, SPEI6, SPEI9, and SPEI12) on different time scales were used to assess meteorological drought conditions. We employed a Pearson correlation analysis to examine the relationship between wetland changes and various SPEI scales. The BFASAT method was used to evaluate the impact of SPEI12 trends on the wetlands, while a cross-wavelet analysis explored teleconnections between SPEI12 and atmospheric circulation factors. Our conclusion is as follows: The wetlands, including lake, glacier, and marsh wetlands, exhibited a noticeable increasing trend. Wetland expansion occurred during specific periods (1990–1997, 1998–2007, and 2008–2020), featuring extensive conversions between wetlands and other types, notably the conversion from other types to wetlands. Spatially, lake and marsh wetlands predominated in the low-latitude basin, while glacier wetlands were situated at higher altitudes. There were significant negative correlations between the SPEI at various scales and the total wetland area and types. SPEI12 displayed a decreasing trend with non-stationarity and distinct breakpoints in 1996, 2002, and 2011, indicating heightened drought severity. Atmospheric circulation indices (ENSO, NAO, PDO, AO, and WP) exhibited varying degrees of resonance with SPEI12, with NAO, PDO, AO, and WP demonstrating longer resonance times and pronounced responses. These findings underscore the significance of comprehending wetland changes and drought dynamics for effective ecological management in the Chaidamu Basin of the Qinghai–Tibet Plateau.

Soil erosion assessment and identification of erosion hotspot areas in the upper Tekeze Basin, Northern Ethiopia

Soil erosion is a major environmental problem in Ethiopia, reducing topsoil and agricultural land productivity. Soil loss estimation is a critical component of sustainable land management practices because it provides important information about soil erosion hotspot areas and prioritizes areas that require immediate management interventions. This study integrates the Revised Universal Soil Loss Equation (RUSLE) with Google Earth Engine (GEE) to estimate soil erosion rates and map soil erosion in the Upper Tekeze Basin, Northern Ethiopia. SoilGrids250 m, CHIRPS-V2, SRTM-V3, MERIT Hydrograph, NDVI from sentinel collections and land use land cover (LULC) data were accessed and processed in the GEE Platform. LULC was classified using Random forest (RF) classification algorithm in the GEE platform. Landsat surface reflectance images from Landsat 8 Operational land imager (OLI) sensors (2021) was used for LULC classification. Besides, different auxiliary data were utilized to improve the classification accuracy. Using the RUSLE-GEE framework, we analyzed the soil loss rate in different agroecologies and LULC types in the upper Tekeze basin in Waghimra zone. The results showed that the average soil loss rate in the Upper Tekeze basin is 25.5 t ha−1 yr−1. About 63 % of the basin is experiencing soil erosion above the maximum tolerable rate, which should be targeted for land management interventions. Specifically, 55 % of the study area, which is covered by unprotected shrubland is experiencing mean annual soil loss of 34.75 t ha−1 yr−1 indicating the need for immediate soil conservation intervention. The study also revealed evidence that this high mean soil loss rate of the basin can be reduced to a tolerable rate by implementing integrative watershed management and exclosures. Furthermore, this study demonstrated that GEE could be a good source of datasets and a computing platform for RUSLE, in particular for data scarce semi-arid and arid environments. The results from this study are reliable for decision-making for rapid soil erosion assessment and intervention prioritization.

Application of Multi-Temporal and Multisource Satellite Imagery in the Study of Irrigated Landscapes in Arid Climates

The study of ancient irrigation is crucial in the archaeological research of arid regions. It covers a wide range of topics, with the Near East being the focus for decades. However, political instability and limited data have posed challenges to these studies. The primary objective is to establish a standardised method applicable to different arid environments using the Google Earth Engine platform, considering local relief of terrain and seasonal differences in vegetation. This study integrates multispectral data from LANDSAT 5, Sentinel-2, SAR imagery from Sentinel 1, and TanDEM-X (12 m and 30 m) DSMs. Using these datasets, calculations of selected vegetation indices such as the SMTVI and NDVSI, spectral decomposition methods such as TCT and PCA, and topography-based methods such as the MSRM contribute to a comprehensive understanding of landscape irrigation. This paper investigates the influence of modern environmental conditions on the visibility of features like levees and palaeo-channels by testing different methods and parameters. This study aims to identify the most effective approach for each case study and explore the possibility of applying a consistent method across all areas. Optimal results are achieved by combining several methods, adjusting seasonal parameters, and conducting a comparative analysis of visible features.

Modeling Flood Hazards in Ambon City Watersheds: Case Studies of Wai Batu Gantung

Flood hazard modeling in watersheds is an important step in natural disaster risk mitigation, especially in vulnerable areas such as Ambon City. This research focused on the Wai Batu Gantung, Wai Batu Gajah, Wai Tomu, Wai Batu Merah, and Wai Ruhu watersheds, using JRC Global Surface Water Mapping Layers data, NASA SRTM Digital Elevation 30 m data, and USGS Landsat 8 Level 2, Collection 2, Tier 1 data analyzed on the Google Earth Engine (GEE) platform. Prediction of built-up land in flood-prone areas was conducted by utilizing flood history analysis, hydrological modeling, and flood zone mapping. The results show that flood hazard modeling provides a better understanding of flood risk, assists in the development of safer land use planning, and increases public awareness of flood risk in Ambon City. It is hoped that the results of this research can contribute to flood risk management and sustainable regional development in the future.

Study on the Spatial and Temporal Trends of Ecological Environment Quality and Influencing Factors in Xinjiang Oasis

Human activities and climate change have profound impacts on the ecological environment of oases in Xinjiang, and it is of great significance to explore the spatial and temporal evolution patterns of ecological environment quality in this region for the sustainable development of Xinjiang. The remote sensing ecological index (RSEI) was extracted from the Google Earth Engine (GEE) platform from 2000 to 2020, and the coefficient of variation and Hurst index were used to reveal the spatial and temporal characteristics and stability of the ecological environment quality of the artificial oasis and natural oasis in Xinjiang. The key factors affecting the ecological environment quality are explored through correlation analysis and geoprobes. The results show that the distribution of the ecological environment in Xinjiang oases is high in the north and low in the south, and the overall quality shows a fluctuating downward trend from 0.210 to 0.189. Artificial oases have higher RSEI values, stability, and sustainability than natural oases. The RSEI in the study area was mainly influenced by humidity, followed by greenness and heat, and dryness had the least influence on the RSEI model. Based on the geodetector, the top three highest contributors were found to be precipitation (PRE) (0.83) &gt; relative humidity (RHU) (0.82) &gt; evapotranspiration (ET) (0.57). Climate is the main factor affecting the ecological quality of oases, and the RSEI can be improved by increasing the proportion of artificial oases. The study aims to provide a scientific basis for the sustainable development of oases in arid zones.

Spatiotemporal analysis of land cover change, projection, and fragmentation: an application of Google earth engine and machine learning approach on Baraitali forest, Bangladesh

ABSTRACT Understanding the spatiotemporal dynamics of land cover/use change and forest fragmentation from 1981 to 2021 across the Baraitali Forest was very crucial for modeling future land cover, formulation of sustainable and robust forest/land-management strategies, and policy. The study adopted a mixed modern tool of Google Earth Engine platform, Machine Learning Algorithms, ArcGIS software, Land Change Modeller of TerrSet software, and FRAGSTATS programs. The study revealed that total land cover from 1981 to 2021 found a negative change in vegetative coverage, and a positive change in settlement which was more visible within the 6 land cover classes. Projections of future land cover for the next 10 years anticipate that vegetation coverage will be reduced by 65.96 ha, while settlement will be enhanced by 41.91 ha in 2031. The study also found conversions/transition of land cover throughout the research area. Overall change of spatiotemporal patterns was leading to substantial forest fragmentation. The overall accuracy and Kappa statistics for all the supervised land cover classifications were satisfactory. The study will fill an information gap by providing the revealed information at national and regional scales and may contribute to understanding of global change.