Google Earth Images Research Articles

Identifying land use land cover dynamics using machine learning method and GIS approach in Karaivetti, Tamil Nadu

<p>An important analytical tool for tracking, mapping, and quantifying changes in land use and land cover (LULC) across time serves as the use of machine learning techniques. The environment and human activities both have the potential to change how land is used and covered. Classifying LULC types at different spatial scales has been effectively achieved by models like classification and regression trees (CART), support vector machines (SVM), extreme gradient boosting (XGBoost), and random forests (RF). To prepare images from Landsat before sending and analysis for an aspect of our research, we employed the Google Earth Engine. High-resolution imagery from Google Earth images were used to assess each kind of method and field data collection. Utilizing Geographic Information System (GIS) techniques, LULC fluctuations between 2015 and 2020 were assessed. According to our results, XGBoost, SVM, and CART models proved superior by the RF model regarding categorization precision. Considering the data, we collected between 2015 and 2020, from 11.57 hectares (1.74%) in 2015 to 184.19 hectares (27.65%) in 2020, the barren land experienced the greatest variation, that made an immense effect. Utilizing the support of satellite imagery from the Karaivetti Wetland, our work combines novel GIS techniques and machine learning strategies to LULC monitoring. The created land cover maps provide a vital benchmark that will be useful to authorities in formulating policies, managing for sustainability, and keeping track of degradation.</p>

Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods

Abstract. Remote sensing extraction of glacial lakes is an effective way of monitoring water body distribution and outburst events. At present, the lack of glacial lake datasets and the edge recognition problem of semantic segmentation networks lead to poor accuracy and inaccurate outlines of glacial lakes. Therefore, this study constructed a high-resolution dataset containing seven types of glacial lakes and proposed a refined glacial lake extraction method, which combines the LinkNet50 network for rough extraction and simple linear iterative clustering (SLIC) dense conditional random field (DenseCRF) for optimization. The results show that (1) with Google Earth images of 0.52 m resolution in the study area, the recall, precision, F1 score, and intersection over union (IoU) of glacial lake extraction based on the proposed method are 96.52 %, 92.49 %, 94.46 %, and 90.69 %, respectively, and (2) with the Google Earth images of 2.11 m resolution in the Qomolangma National Nature Reserve, 2300 glacial lakes with a total area of 65.17 km2 were detected by the proposed method. The area of the minimum glacial lake that can be extracted is 160 m2 (less than 6×6 pixels). This method has advantages in small glacial lake extraction and refined outline detection, which can be applied to extracting glacial lakes in the high-Asia region with high-resolution images.

Framework for assessing bridges construction impact on work zone traffic using BrIM

This research presents a framework for visualizing bridge construction impact on work zone traffic using Bridge Information Modelling (BrIM) and Google Maps API. The framework consists of four modules. The first module contains the construction data of the bridge by reporting the construction's daily progress. The second module is designated to model traffic data of the work zone using Google Maps API, traffic Survey counting, and Google Earth Images. The third module performs a traffic simulation for the work zone, and calculating the user cost of different stages. The fourth module visualizes the bridge's construction using Bridge Information Modelling (BrIM) and virtual reality in the Twinmotion engine to demonstrate the construction stages and the corresponding traffic states. An actual case study of El-Nahas Bridge in Cairo city-Egypt is presented to demonstrate the main features of the developed framework and its practical aspects. The case study results reveal that the impact of the construction stages varies on work zone traffic throughout the project period. The impact greatly influences the traffic status at the beginning of the project associated with high user costs. Then, the impact declines in later stages depending on the type of construction activities in each stage.

Vulnerability to Risk of Gully Erosion on Transportation routes and Landed Properties in Benin City Nigeria

The Edo State Ministry of Environment registered 25 gully erosion sites in Benin City. The impacts of some of them have been very detrimental to lives, destroying roads and properties worth billions of Naira. Despite the treat to lives, properties, and accessibility, many are still living around the gullies. The study examined the perceptions of the population at risk and their preparedness to relocate. Questionnaire, GPS, Field measurement, and Google Earth Image were used as data sources to accomplish the objective of the paper. The result indicates that there is a high level of perception among the population at risk. Residents’ perceived vulnerability to gully hazards is directly related to their proximity to the hazard point, while the level of residents’ preparedness to vacate the gully environment is directly related to perceived vulnerability and financial capability. The study result was depicted in map form. Though managing the gully erosion hazard is beyond the capability of the residents within the neighbourhoods, government intervention has been very poor. The study recommended the relocation of populations at risk, while advance drainage designs and construction be executed in order to put an end to the gully.

Vegetation and Non-Vegetation Classification Using Object Detection Techniques and Deep Learning from Low/Mixed Resolution Satellite Images

Vegetation cover classification using mixed or low-resolution scalar images is challenging. Fortunately, recently deep learning object detection methods have emerged as a replacement to the conventional machine learning methods for the detection and classification of land use and land cover. This paper presents a deep learning object detection approach for land use and land cover detection using low/mixed resolution satellite images acquired from Google Earth satellite images. Google Earth images are accessible freely using the Google Earth Pro desktop application. Our dataset consists of two (02) classes (vegetation and non-vegetation) with a total of 450 labeled images captured from different parts of Pakistan. We present a comparison of the recent anchor-free object detection model YOLOX with the anchor-based object detection model YOLOR for solving real-time problems. The end-to-end differentiability, efficient GPU utilization, and absence of hand-crafted parameters make anchor-free models a compelling choice in object detection, and yet not been explored on Land cover classification using satellite images. Our experimental study shows that YOLOX delivers an overall accuracy of 83.50% on Vegetation and 86% on Non-Vegetation classes, which outperformed YOLOR by 30% on Vegetation classes and 34% on non-Vegetation classes for our dataset. We also show how an object detection system can be used for Vegetation and Non-Vegetation classification tasks, which can then be used for change monitoring and assisting in developing geographical maps using low/mixed resolution freely available satellite images.

Leveraging Geospatial Technology for Enhanced Utility Management: A Case Study in Electrical Distribution Power Systems

Over the years, electricity has developed into a crucial commodity for any nation. The need to evaluate the rate of electricity consumption in regard to utility management and the spatial distribution of major devices to facilitate appropriate planning within the estate is the motivation for this research. This study used geospatial technology to evaluate the electricity distribution to support planning and management in Omole Estate (Phase One) and environs within the city of Lagos, Nigeria. The focus was on determining the land use in study area, geolocations of the transformers, along with the cost of energy consumed per household. Spatial data for the research area was collected through a Hand-held GPS. Google Earth images were downloaded to supplement the data, and a comprehensive analysis of administered and recovered questionnaires was conducted to enrich the dataset. ArcGIS 10.6.1 software was employed to create the database and depict the area, whilst modifying all of the details required within. The result confirms that 72% of the respondents use electricity for domestic use, 18% for commercial use while 10% utilise it for domestic and commercial use. A significant portion of homes (33%) still use outdated postpaid meters and 35% of respondents do not know how much power they use at home each month or the cost per unit of that electricity. Regarding the respondents, 67% have a prepaid card/electrical meter installed (per kilowatt). Concerning cost, 10% of the respondents spends between N1000-N5000 for their monthly electricity consumption, 27% of the respondents between N5,000 and N10,000, 38% between N10,000 and N17,000, 24% between N17,000 and N25,000 and 2% above N25,000 per month on electricity. These findings will assist effective power distribution within the estate and provide guidance on charge rates for commercial power users which is approximately 28% overall.

Scalable Retrieval of Similar Landscapes in Optical Satellite Imagery Using Unsupervised Representation Learning

Global Earth observation is becoming increasingly important in understanding and addressing critical aspects of life on our planet, including environmental issues, natural disasters, sustainable development, and others. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, by making similar decisions or learning from best practices for events and occurrences that previously occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by a moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim to identify individual concepts inherent to satellite images. Our approach relies on several models trained using unsupervised representation learning on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for retrieving landscape(s) similar to a user-selected satellite image of the geographical territory of the Republic of Cyprus. Our results demonstrate the benefits of breaking up the landscape similarity task into individual concepts closely related to remote sensing, instead of applying a single model targeting all underlying concepts.

Scale dependence of forest fragmentation and its climate sensitivity in a semi-arid mountain: Comparing Landsat, Sentinel and Google Earth data

Landscape fragmentation is generally viewed as an indicator of environmental stresses or risks, but the fragmentation intensity assessment also depends on the scale of data and the definition of spatial unit. This study aimed to explore the scale-dependence of forest fragmentation intensity along a moisture gradient in Yinshan Mountain of North China, and to estimate environmental sensitivity of forest fragmentation in this semi-arid landscape. We developed an automatic classification algorithm using simple linear iterative clustering (SLIC) and Gaussian mixture model (GMM), and extracted tree canopy patches from Google Earth images (GEI), with an accuracy of 89.2% in the study area. Then we convert the tree canopy patches to forest category according to definition of forest that tree density greater than 10%, and compared it with forest categories from global land use datasets, FROM-GLC10 and GlobeLand30, with spatial resolutions of 10 m and 30 m, respectively. We found that the FROM-GLC10 and GlobeLand30 datasets underestimated the forest area in Yinshan Mountain by 16.88% and 21.06%, respectively; and the ratio of open forest (OF, 10% < tree coverage < 40%) to closed forest (CF, tree coverage > 40%) areas in the underestimated part was 2:1. The underestimations concentrated in warmer and drier areas occupied mostly by large coverage of OFs with severely fragmented canopies. Fragmentation intensity of canopies positively correlated with spring temperature while negatively correlated with summer precipitation and terrain slope. When summer precipitation was less than 300 mm or spring temperature higher than 4 °C, canopy fragmentation intensity rose drastically, while the forest area percentage kept stable. Our study suggested that the spatial configuration, e.g., sparseness, is more sensitive to drought stress than area percentage. This highlights the importance of data resolution and proper fragmentation measurements for forest patterns and environmental interpretation, which is the base of reliable ecosystem predictions with regard to the future climate scenarios.

Landslide Occurrences under Diverse Landuse/cover in Lower Kosi Watershed, Central Himalaya

Abstract Present study was related to land degradation after landslide and risk analysis of Lower Kosi watershed in Central Himalaya using RS and GIS. The study was aimed to identifying the relation of land use with landslide activity in Himalayan terrain and landslide management. The landslide inventory map was prepared for the detailed study with the help of Google Earth Image and field verifications. Landslide had been sub-categorized into two categories; natural and road induced. The land use map was prepared from Google Earth image followed by toposheets. Statistical analysis of landslide frequency and density as well as frequency and density ratios were applied. The collected data was evaluated in combination with GIS. The relationship between land use categories and landslide occurrences was determined. The landslide frequency ratio (FR) and density ratio (DR) were analyzed. The FR and DR value of 1 is an average value. Hence, the value of ratio more than 1 signifies a strong relationship between landslides and the given factor while ratio values less than 1 registers a poor relationship. The FR and DR values were &amp;gt;1.0 in the areas of fallow land, barren/rocky land, agricultural land and open forest revealing a strong relation to landslide processes while the lesser values of FR and DR in ‘dense forest’ area determines the impact of sufficient vegetation cover on the least occurrence of landslides. This study may be applicable for new and existing land use planning projects as the adopted methodology provides rapid estimation of landslide vulnerability of the area.

The outer ring of a circular structure in the Marche Region, Central Italy: Evidence of a non-extraterrestrial origin

Google Earth images in the Marche Region of Central Italy revealed a circular structure consisting of a ring system made up of concentric hills and valleys. Cartography, DEM, geological, and available geophysical data were used to constrain the possible origin of the structure. Located in the Messinian foredeep deposits of the Central Apennines, it has a rim diameter of 3.75 km and a central uplift connected to its southernmost part. As it was formed in the clays of the Lower Pliocene, and clays are believed to have emerged definitively after the Upper Pliocene, its age might be constrained to the Lower Pleistocene. Similar concentric structures are usually found in impact craters, sedimentary domes, and volcanic landforms. As salt domes and magmatic activity are not found in this region, this study seeks to validate the results of previous work that it was the result of an ancient impact crater, of hydrological, brachy anticline, or clayey diapiric origins. Specifically, an observed second ring portion, with a curvature radius about double the first in size, will be investigated in this work. This second ring portion appears to be concentric to the first one and is visible along the its northern and western parts. Although double concentric rings are usually due to impact craters, the absence of the ring portion in the other two directions, and the probable deviation of a river, deduced by studying hydrography, supports the hypothesis that it might be of a clay diapir origin.

Using river restoration model to control riverbank erosion in the Old Brahmaputra river of Bengal Basin, Bangladesh

River meandering causes riverbank erosion, which triggers socioeconomic and environmental issues in the riparian region and raises river sedimentation, thus, needing river restoration. This research depicts a channel restoration model to control river bank erosion and susceptible resource management along the Old Brahmaputra River course based on channel characteristics from 1980 to 2021. The secondary data of Landsat satellite time series and SRTM images were collected from the USGS website, while we used Google Earth images to verify the morphological features. Satellite images were on-screen visualized by ArcMap (10.3) to extract the river channels and measure the erosion and accretion areas. Results showed that the Old Brahmaputra River channel shifted its position due to erosion and accretion. Over the last forty-one years, ∼ 52 km2 area was eroded while ∼ 49 km2 area was accreted, and the average shifting of the river channel was 1.3 km2 per year. Accordingly, the river channel has become more sinuous decade by decade and threatens nearby settlements. Hence, this study proposed a river channel based on previous river channels, where the base channel is from the 2000s, which was more stable and flowed through the middle of the floodplain. Parts of the 1980, 2000, and 2021 river channels were also selected, which are relatively far from the susceptible settlements, to draw the proposed restoring channel. This model is likely to aid in developing government strategies for protecting riverbank erosion and river restoration in the forthcoming period. Finally, this study recommends that this newly proposed channel will be conducive to reducing riverbank erosion and the extreme threat to the settlements and their livelihoods.

PEMETAAN PRASARANA DAN KONTUR KAMPUS UNIVERSITAS WIRARAJA BERDASARKAN CITRA PENGINDRAAN JAUH

Wiraraja University campus from its establishment in 1986 to 2023 has a period of 37 years which has experienced many developments, especially learning infrastructure. The development of infrastructure needs to be mapped to determine the distribution of learning infrastructure on the Wiraraja University campus. The utilization of geographic information system (GIS) technology and the development of infrastructure on the Wiraraja University campus, it is necessary to map the infrastructure and contours on the Wiraraja University campus which will later obtain an overview of the infrastructure. The purpose of the study was to determine the infrastructure map and the percentage of infrastructure to the overall land and contour map of Wiraraja University campus. The research used Google Earth and ArcMap. The research data collection was carried out by field survey and data collection of infrastructure on the campus of Wiraraja University and the research data was carried out by frequency analysis.&#x0D; Land use on the campus of Wiraraja University is divided into the categories of buildings, sports fields, covered and open parking, parks, roads and vacant land. The land area of Wiraraja University campus based on Google Earth images with the digitization method is 22,711.86 m2. The largest land use is used as a building at 37.54%, while the smallest land use is used as a covered parking lot at 1.78%. The elevation of the Wiraraja University campus is between 3.67 - 5.94 m elevation and the highest elevation is 5.94 meters and the lowest elevation is 3.67 meters above mean sea level.

Implications of Accuracy of Global Glacier Inventories in Hydrological Modeling: A Case Study of the Western Himalayan Mountain Range

Alpine glaciers are a fundamental component of the cryosphere and are significantly sensitive to climate change. One such region is the Hindukush Karakoram Himalaya (HKH) and Tibetan Plateau (TP) region, which contains more than 40,000 glaciers. There are more than 12 glacier inventories available covering parts of (or the entire) HKH region, but these show significant uncertainties regarding the extent of glaciers. Researchers have used different glacier inventories without assessing their accuracy. This study, therefore, assessed the implications of the accuracy of global glacier inventories in hydrological modeling and future water resource planning. The accuracy assessment of most commonly used two global glacier inventories (Global Land Ice Monitoring from Space-GLIMS v 2.0 and Randolph Glacier Inventory-RGI v 6.0) has been carried out for three sub-basins of the Upper Indus Basin—the Swat, the Chitral, and the Kabul River basins (combined, this is referred to as the Great Kabul River Basin)—with a total basin area of 94,552.86 km2. Glacier outlines have been compared with various Landsat 7 ETM+, Landsat 8, high-resolution Google Earth images, and manually digitized debris-covered glacier outlines during different years. The total glacier area for the Great Kabul River Basin derived from RGI and GLIMS is estimated to be 2120.35 km2 and 1789.94 km2, respectively, which was a difference of 16.9%. Despite being sub-basins of the Great Kabul River Basin, the Swat, and the Chitral River basins were different by 54.74% and 19.71%, respectively, between the two inventories, with a greater glacierized area provided by RGI, whereas the Kabul River basin was different by 54.72%, with greater glacierized area provided by GLIMS. The results and analysis show that GLIMS underestimates glacier outlines in the Swat and the Chitral basins and overestimates glacier extents in the Kabul River basin. The underestimation is mainly due to the non-representation of debris-covered glaciers. The overestimation in GLIMS data is due to the digitization of seasonal snow as part of the glaciers. The use of underestimated GLIMS outlines may result in 5–10% underestimation of glacier-melt contribution to flows in the Swat River basin, while an underestimation of 7% to 15% is expected in the Chitral River Basin, all compared to RGI v 6.0 outlines. The overestimation of glacier-melt contribution to flows in the Kabul River basin is insignificant (1% to 2%) using GLIMS data. In summary, the use of the GLIMS inventory will lead to underestimated flows and show that the Great Kabul River Basin (particularly the Chitral River Basin) is less sensitive to climate change effects. Thus, the current study recommends the use of RGI v 6.0 (best glacier inventory) to revisit the existing biased hydro-climate studies and to improve future hydro-climate studies with the concomitant rectification of the MODIS snow coverage data. The use of the best glacier inventory will provide the best estimates of flow sensitivity to climate change and will result in well-informed decision-making, precise and accurate policies, and sustainable water resource management in the study area. The methodology adopted in the current study may also be used in nearby areas with similar hydro-climate conditions, as well as for the most recently released RGI v 7.0 data.

Automatic Identification for the Boundaries of InSAR Anomalous Deformation Areas Based on Semantic Segmentation Model

Interferometric synthetic aperture radar (InSAR) technology has become one of the mainstream techniques for active landslide identification over a large area. However, the method for interpreting anomalous deformation areas derived from InSAR data is still mainly manual delineation through human–computer interaction. This study focuses on using a deep learning semantic segmentation model to identify the boundaries of anomalous deformation areas automatically. We experimented with the delineation results based on an InSAR deformation map, hot spot map, and different combinations of topographic datasets to build the optimal model. The result indicates that the hot spot map, aspect, and Google Earth image as input features based on the U-Net model can achieve the best performance, with the precision, recall, F1 score, and intersection over union (IoU) being 0.822, 0.835, 0.823, and 0.705, respectively. Our method promotes the development of identifying active landslides using InSAR technology automatically and rapidly at a regional scale. Moreover, applying a new method for automatically and rapidly identifying potential landslides in susceptible areas is necessary for landslide hazard mitigation and risk management.

Quantifying the contribution of industrial zones to urban heat islands: Relevance and direct impact

Industrial production activities are an important source of urban heat emissions. Quantifying the contribution of industrial zones to urban heat islands (UHIs) is crucial for urban planning and management. However, few studies have explored the quantitative relationship between land surface temperature (LST) and urban industrial zones (UIZs) at the urban scale, especially the direct impact of industrial expansion or contraction on LST. Linyi City, the largest city in Shandong Province, was selected as the study area. This study aims to analyze the spatial-temporal variation in the UIZs in Linyi City from 2013 to 2022, focusing on the quantitative relationship between LST and UIZs. Using remote sensing images, a novel spectral index (called the BCCSI) was constructed to identify factory buildings. The performance of the BCCSI was validated using five existing indices and Google Earth images. Over the past 10 years, the UIZ area of Linyi has increased by 137.16 km2. The UIZs in Linyi are mainly distributed in counties near the urban center, and counties with large UIZ areas are also hotspots for UIZ changes. Moreover, we found that the contraction or expansion of UIZs has obvious effects on LST. After the contraction (or expansion) of UIZs, the LST decreased (or increased) by 0.48 °C (0.39 °C). In addition, we found that there is an exponential relationship between LST and the industrial unit area (P value less than 0.01). This research is valuable for environmental assessment and fine management of industrial cities.

Effect of urban morphology on wind flow distribution in dense urban areas

Environmental flow modelling can be achieved either by using wind-tunnel studies or via the utilization of Computational Fluid Dynamics (CFD) techniques. Conducting wind-tunnel studies may be expensive and time consuming, particularly in the event of additional test requirements with modified building and/or environmental configurations. On the other hand, CFD can provide significant cost benefits for assessing and optimizing engineering design solutions related to environmental concerns and appear attractive as a potential alternative tool. By using CFD in this manner it is anticipated that these types of advanced performance-based studies will be a useful tool and essential aid for urban designers and environmental planners. This paper discusses ongoing development and application of CFD simulations through a case study using CFD software for simulating air flow around a specific vernacular urban fabric of Ghardaïa. The potential of CFD for prediction of wind speeds around a complicated urban environment and a complex fabric structures is investigated. As the 3D solid model of the geometry was not available a captured Google Earth image of the fabric structure was used as a backdrop in the AC3D software, supplied as a utility to Phoenics. The outlines of the buildings were then traced to create polygons, which were then extruded to produce the individual buildings. Finally, the entire scene was exported to the VR-Editor as a single Phoenics object.

A benchmark dataset for deep learning-based airplane detection: HRPlanes

Airplane detection from satellite imagery is a challenging task due to the complex backgrounds in the images and differences in data acquisition conditions caused by the sensor geometry and atmospheric effects. Deep learning methods provide reliable and accurate solutions for automatic detection of airplanes; however, huge amount of training data is required to obtain promising results. In this study, we create a novel airplane detection dataset called High Resolution Planes (HRPlanes) by using images from Google Earth (GE) and labeling the bounding box of each plane on the images. HRPlanes include GE images of several different airports across the world to represent a variety of landscape, seasonal and satellite geometry conditions obtained from different satellites. We evaluated our dataset with two widely used object detection methods namely YOLOv4 and Faster R-CNN. Our preliminary results show that the proposed dataset can be a valuable data source and benchmark data set for future applications. Moreover, proposed architectures and results of this study could be used for transfer learning of different datasets and models for airplane detection.

Landsat archive for detection of change in Mediterranean ecosystems: The case of Northern Morocco

The study of changes in land cover provides a better understanding of the interactions between humans and natural ecosystems. In this context, the present study focused on the dynamics of natural ecosystems in the Rif region of Northern Morocco. The methodology was based on the inspection and visual interpretation of Landsat and Google Earth image captures, the time series of five Landsat 4-8 image bands, and the Tasseled Cap indices for a random sample of 500 points from 1984 to 2022. The study found that changes affected practically the whole study region over the study period, with around a third of them being ignored due to their very tiny magnitudes or being false positives. The findings demonstrated a general declining trend in the measured changes, indicating a reduction in pressure on different ecosystems. Furthermore, this tendency may be due in part to the availability of Google Earth images during the 2000s, which has significantly reduced the number of false positives. In terms of the year of first change, only 5.7% of pixels experienced their first events after the year 2000, implying that these pixels underwent no change for at least the first 16 years of the study period. On the other hand, 2.5% of the pixels had their last events during the first ten years and have thus remained unmodified for at least 27 years. For the year 2020, the confidence rating of the visual land cover categorization is medium to high for 88.9% of pixels using high-resolution Google Earth photos, whereas the classification quality was inadequate for 64% of pixels in 1984. Despite the stresses on the ecosystems structured by shrubs/shrubs, forests, and herbaceous/shrubs caused by the different disturbances identified, the majority of these ecosystems have not been converted to new land cover classes. According to the study, agriculture is the primary driving force underlying the conversion of forests, herbaceous/shrublands, and even shrublands/shrublands. The area increases for the latter three ecosystems represent, on the one hand, their ability to regenerate themselves and, on the other, Morocco's restoration efforts.

Accuracy Assessment of different classifiers for Sustainable Development in Landuse and Landcover mapping using Sentinel SAR and Landsat-8 data

Sentinel satellites make use of Synthetic Aperture Radar (SAR) which produces images with backscattered signals at fine spatial resolution from 10 m to 50 m. This study is mainly focused on evaluating and assessing the accuracy of various supervised classifiers like Random Forest classifier, Minimum Distance to mean classifier, KDTree KNN classifier, and Maximum Likelihood classifier for landuse / landcover mapping in Maduranthakam Taluk, Kancheepuram district, Tamilnadu, India. These classifiers are widely used for classifying the Sentinel SAR images. The SAR images were processed using speckle and terrain correction and converted to backscattered energy. The training datasets for the landcover classes, such as vegetation, waterbodies, settlement, and barren land, were collected from Google Earth images in high-resolution mode. These collected training datasets were given as input for the various classifiers during the classification. The obtained classified output results of various classifiers were analyzed and compared using the overall classification accuracy. The overall accuracy achieved by the Random Forest classifier for the polarization VV and VH was 92.86%, whereas the classified accuracy of various classifiers such as KDTree KNN, Minimum distance to mean, and Maximum Likelihood are found to be 81.68%, 83.17%, and 85.64% respectively. The random forest classifier yields a higher classification accuracy value due to its greater stability in allocating the pixels to the right landuse class. In order to compare and validate the results with sentinel data, the random classifier is applied with optical Landsat-8 satellite data. The classification accuracy obtained for Landsat-8 data is 84.61%. It is clearly proved that the random forest classifier with sentinel data gives the best classification accuracy results due to its high spatial resolution and spectral sensitivity. Thus accurate landuse and landcover mapping promote sustainable development by supporting decision-making at local, regional, and national levels.

Integration of RS/GIS in Assessing the National Great Green Wall Woodlots/Orchards in Katagum LGA, Bauchi State, Nigeria

The study is based on the premise that climate change and desertification have strong connection in the ecosystem. Because desertification affects climate change through the loss of fertile soil and corresponding vegetation, it also has important repercussions for the global climate system. Through the Great Green Wall (GGW) tree planting project initiatives, a lot has been achieved elsewhere hence this study. In Nigeria, the programme was introduced in Bauchi State (northern Nigeria) as one of the 11 front line states where desertification is observed. The study was conducted under the hypothetical assumption that the planting of Woodlots and Orchards can help checkmate and control the seeming desertification in the Katagum Local Government Area of Bauchi State, Nigeria. Six woodlots and Orchards were identified and mapped using the Google Earth image visualization platform and the spatial extent of change were determined in hectare (Ha) using the digitizing tool in the software. Except Dugunde (which reduced from 2,499.65 to 2,265.96 Ha), the rest increased within the period under review. Dagoro increased from 371.45 Ha to 372.91 Ha, followed by Dangazau (324.02 to 328.05 Ha), Gambaki (1,154.04 to 1.167.07 Ha), Dugunde 2 (469.42 to 537.74 Ha), and Dugunde 3 (719.58 to 749.61). The Orchard and Woodlots’ growth is understandable because of continuous watering and tending of the vegetation over the years. From sampled questionnaires, the study further reveals that the Woodlots and Orchards are very effective mechanism in controlling desertification in the Northern State. The study shows that the locals are satisfied with the project and are ready to support the programme because it provided employment for them, and also helps to preserve the environment and tree species. The satisfaction with the use of woodlots and orchards