Cover Classification Research Articles

Comparative analysis of different supervised methods for satellite-based land-use classification: a case study of Reyhanlı

Satellite-based land-use classification plays a crucial role in various Earth observation applications, ranging from environmental monitoring to disaster management. This study presents a comparative analysis of machine learning techniques applied to land cover classification using Landsat-9 and Sentinel-2 satellite imagery in the Reyhanlı district in southern Türkiye. Three different classification algorithms, Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classification (MLC), were evaluated for their ability to distinguish different land cover classes. High resolution multispectral satellite imagery processed under the same conditions using Geographic Information System (GIS) software was utilized in this study. Visual inspection and statistical evaluation, including overall accuracy and kappa coefficient, were employed to assess classification performance. The classification of Sentinel-2 and Landsat-9 satellite imagery using different machine learning algorithms resulted in the highest overall accuracy (OA = 0.911, Kappa = 0.879) for Sentinel 2 imagery with the RF algorithm. These findings highlight the importance of satellite image selection and algorithm optimization for accurate land cover mapping. This study provides valuable insights for local planners and authorities and underscores the potential of Sentinel-2 imagery combined with machine learning techniques for effective land-use classification and monitoring.

Assessing interpreter’s disagreements in land cover reference data collection from historical Landsat time series in Amazon

ABSTRACT Land cover information, derived from the classification of Remote Sensing images, is only useful if accompanied by a rigorous accuracy assessment, usually dependent on reference samples. As field data can be very rare for multi-temporal analysis, many studies use samples visually interpreted from Remote Sensing images. This subjective process is prone to errors in interpretation, leading to uncertainties not fully quantified in the reference sample collection of historical time series. We evaluated the agreement rate among independent interpreters in the identification of land cover classes assigned to pixels for yearly Landsat observations from 1984 to 2020, in the Lower Tapajós Basin region (within the Brazilian Amazon). Considering 10 classes, we found that sets of three interpreters completely disagreed on the label of 14.8% of the pixels for each year, and completely agreed in less than half (39.6%). These values change to 2.7% and 68.8% when we consider only five classes in the analysis. We observed time-dependent variations in agreement for specific land cover classes: whereas forest areas tend to present an increase in the disagreement rate over time, land cover types that happen only in previously deforested areas tend to present a higher proportion of pixels with better agreement rates. Disagreements tend to be higher in pixels identified as borders or near borders between targets. However, there is a non-negligible amount of disagreements in pixels identified as not borders caused by limitations derived from the unit of analysis, image composition techniques, and intrinsic similarities among classes. We highlight problems with the identification of classes that happen in complex spatiotemporal patterns (Secondary Vegetation, Small-scale Agriculture, and Degraded Forest). These results alert to possible inconsistencies in reference samples collected for the accuracy assessment of land cover time series and the correspondent values of the calculated accuracy indexes.

Examining the effect of urbanization on various land cover classes and environmental quality using remote sensing and GIS methods

It is vital for public awareness and decision-makers to investigate the impact caused by changes in urban land use and land cover on ecosystem service values (ESVs) in order to promote sustainable urban development, protect the environment, protect public health, and ensure communities’ long-term well-being. Changes in ecosystem services brought on by changes in land use and cover (LULC) are a crucial early indicator and warning sign of ecological shifts. Using remote sensing and GIS tools, this study examined the shifting dynamics of ESVs in the Haridwar district in Uttarakhand state, India. The evaluation of land use land cover (LULC) changes was carried out by analyzing satellite images of the research region from 2001 to 2021. In addition, we examined changes in ecosystem services according to the study area’s LULC classifications. Using a random forest machine learning classifier, satellite images were classified into five categories of land cover: water bodies, forests, built-up areas, agricultural land, and bare land. The findings showed that from 2001 to 2021, forest cover and water bodies fell by 15.35% and 41.50%, respectively, while urban area and agricultural area rose by 69.24% and 12.31%, respectively. Due to increased urbanization and degradation of water bodies and forest areas, ESV fell from 103.19 USD ha −1 year −1 in 2001 to 70.53 USD ha −1 year −1 in 2021. The combination of LULC with the value of ecosystem services may improve our knowledge of several difficulties in an urban ecosystem. As a result, we advocate for the incorporation of LULC and ESVs as a tool that might be useful to urban planners and land managers in the future for sustainable development of natural resources.

Mapping built-up area expansion in landslide susceptible zones using automatic land use/land cover classification

Mapping built-up area expansion in landslide susceptible zones using automatic land use/land cover classification

Optimizing Mobile Vision Transformers for Land Cover Classification

Image classification in remote sensing and geographic information system (GIS) data containing various land cover classes is essential for efficient and sustainable land use estimation and other tasks like object detection, localization, and segmentation. Deep learning (DL) techniques have shown tremendous potential in the GIS domain. While convolutional neural networks (CNNs) have dominated image analysis, transformers have proven to be a unifying solution for several AI-based processing pipelines. Vision transformers (ViTs) can have comparable and, in some cases, better accuracy than a CNN. However, they suffer from a significant drawback associated with the excessive use of training parameters. Using trainable parameters generously can have multiple advantages ranging from addressing model scalability to explainability. This can have a significant impact on model deployment in edge devices with limited resources, such as drones. In this research, we explore, without using pre-trained weights, how the inherent structure of vision transformers behaves with custom modifications. To verify our proposed approach, these architectures are trained on multiple land cover datasets. Experiments reveal that a combination of lightweight convolutional layers, including ShuffleNet, along with depthwise separable convolutions and average pooling can reduce the trainable parameters by 17.85% and yet achieve higher accuracy than the base mobile vision transformer (MViT). It is also observed that utilizing a combination of convolution layers along with multi-headed self-attention layers in MViT variants provides better performance for capturing local and global features, unlike the standalone ViT architecture, which utilizes almost 95% more parameters than the proposed MViT variant.

Hierarchical-modular framework for habitat mapping through systematic and informed integration of remote sensing data with contextual information

Accurate and up-to-date habitat maps at national or regional levels are critical for informing conservation and restoration actions. Land cover maps generated from Earth Observation (EO) data can, to varying degrees, indicate the extent of some habitat categories but these are often insufficient in terms of the level of detail required. This study introduces a hierarchical-modular framework based on the globally applicable Food and Agriculture Organization (FAO) Land Cover Classification System (LCCS) whereby the land cover classes can be systematically translated to habitat categories and further differentiated by referencing contextual information and expert knowledge. Application is showcased for Wales (United Kingdom) where 10 m spatial resolution land cover maps were first constructed nationally from time-series of Sentinel-1C-band radar and Sentinel-2 optical data (2018–2020). The contextual datasets derived from non-EO sources were utilised to associate dominant vegetation types to detailed habitat classes.The accuracy assessment done using field survey data highlights that habitat classes directly derived from EO, including cultivated/managed and forest types, demonstrated higher mapping accuracies (>70% User's and Producer's Accuracies) compared to those that were more heavily dependent on non-EO-derived contextual information. These included neutral grasslands and fen/marsh/swamp that demonstrated lower accuracies (<20%) but also other detailed wetland classes (user's and producer's accuracies ranging from 25 to 60%). These reduced accuracies were largely associated with discrepancies in the contextual datasets used for their differentiation and mapping, and those integrated within field validation datasets. Dependency on contextual datasets diminished as detailed habitat maps were generalized into broader categories. The study proposes that, for enhanced habitat mapping, efforts should focus not only on EO data but also on maximising the accuracy and minimizing inconsistencies in contextual datasets as well as taxonomical systems. The flexible structure of the FAO LCCS hierarchical framework is also highlighted, emphasizing its adaptability for future improvements in habitat mapping by incorporating contextual datasets and more advanced algorithms that can improve EO-derived land cover descriptions.

A spatiotemporal comparison of interobserver error in vegetation sampling

AbstractQuestionsWe asked how interobserver error in sampling vegetation (excluding trees) varied over time, space and habitat type; determined whether there were any obvious correlates of observer error; and evaluated evidence of bias among observers.LocationNine national park units in the Midwestern USA.MethodsWe quantified observer error in the context of a long‐term monitoring program employing three observers, evaluating interobserver error across 11 locations in the Midwestern USA over five years. The vegetation (excluding trees) was sampled independently by two teams of observers at prairie and woodland locations (n = 94 plots total).ResultsTotal pseudoturnover ranged between 20.2% and 22.1% at prairie locations, and between 16.8% and 28.6% at woodland locations. The overlooking component of pseudoturnover accounted for 75% or more of total pseudoturnover, with misidentification and cautious components each contributing 19% or less of the total, depending on location. The percentage of comparisons in which both observers recorded the same cover class ranged from 71.3% to 78.5% at the prairie locations and 56.9% to 85.6% at woodland locations. When observers did not agree on cover class, they were off by more than one class less than 6% of the time. Overlooking error was more likely to occur for species with less cover, while estimation error was more likely to occur for species with greater cover. A bias existed among observers, as the least experienced observer recorded 6.2%–11.8% more species than the other two observers. Interobserver bias also existed for rates of estimation error, as one observer consistently recorded higher cover classes.ConclusionsObserver error is a pervasive aspect of vegetation sampling. Continued training and experience yielded limited increases in precision. Elements of the sampling design probably reduced observer error to a certain degree, although some level of interobserver error in vegetation surveys is unavoidable.

Spatio-temporal assessment and prediction of wetlands: Examining the changes in ecosystem service value of RAJUK DAP area using Artificial Neural Network and Geospatial Techniques

Wetlands are a crucial component of the earth's socio-ecological structure, providing significant ecosystem services to people. Changes in wetlands, driven by both natural and manmade causes, are altering these ecosystem services. Although Bangladesh is developing, natural resources like wetlands are changing in the country at different scales, with urban areas experiencing significant impacts. This study intends to evaluate the past, present, and future scenarios of wetlands and examine the changes in ecosystem service value (ESV) of the RAJUK (Rajdhani Unnayan Kartripakkha or Capital Development Authority) Detailed Area Plan (DAP) region. This research examined the effects of five different Land Use and Land Cover (LULC) classes on ESVs for 27 years from 1995 to 2022. Findings reveal that the current wetland area is 80.16 km2 in the post-monsoon season and 306.67 km2 in the pre-monsoon season. Composite post-monsoon wetland map from 1995 to 2015 that 19.48 km2 of wetlands are classified as hydro-ecologically consistent wetlands. Wetland area has decreased by 140.926 km2 between 1995 and 2022, according to simulations, and is predicted to do so by another 27.11 km2 during the following eight years. The total ESV of wetlands dropped by about 26.72 percent between 1995 and 2022, primarily due to conversion to habitation and agricultural use. Also, the projection of LULC and associated ESV for the year 2030 demonstrates how ESV evolves throughout this period and which LULC classes are more susceptible to change, while the kappa coefficient was used to compare the simulated models to the actual wetland area. The current study will undoubtedly be helpful to decision-makers who make a substantial contribution to preserving ecosystem services and the wetland landscape.

The Driving Forces that Influence Land Use Land Cover Changes in Khwisero Sub County, Kakamega County, Kenya

Land use land cover changes have to a great extent changed the world's landscapes, rebuilding environments and what they provide to humans during the time spent supporting the rising population across the globe. The drivers of these changes vary from location to location causing varying effects that challenge the essential design and the functioning capacity of the land quality with flowing consequences to land quality. A cross sectional descriptive design together with a longitudinal design were used. A random sampling was used to obtain a sample size of 384 from a study population of 113,476. Based on agriculture, forest land, bare land and built up land categories, the study classified Landsat images through supervised classification algorithm then applied post - classification comparison change detection to measure land use land cover percentage area change over time. Primary data was collected through interviews and discussions with key informants, field observations, and questionnaires administered to individual households in Khwisero Sub County. Secondary data involved downloading Landsat images (Landsat 7, 8 and 9; 30-meter multispectral), summaries and citation of other works carried in journals articles, original documents, annual reports, development plans and internet. Quantitative data analysis involved measures of central tendency and measures of dispersion (SPSS) and analysis of variance (ANOVA). Qualitative data was analysed by organizing and grouping the arising issues into various categories relevant to the study. Land use land cover classification of the study area realized four land use land cover classes of agriculture 81.34 km2, forest 52.75 km2, built up 8.86 km2 and bare land 2.65 km2 for the study area as at 2023. Change detection noted that agricultural land use has been reducing from 2002 to 2023, built up has been increasing from 2002 to 2023, bare land increased between 2002 to 2012 but decreased between 2012 and 2023 while forests reduced between 2002 to 2012 but increased between 2012 to 2023 Accuracy assessment for the land use land cover classes for 2002 was 85.45% with a Kappa coefficient of 0.756, 2012 was 83.64% with a Kappa coefficient of 0.5454 while 2023 was 81.82% with a Kappa coefficient of 0.6034 for the land use land cover classes revealing that the classification is accurate. The study revealed that LULCCs are driven by settlement, poverty and climate change mostly thus affecting cropland vegetation and soil fertility majorly. The study concluded that LULCC drivers varied from location to location even within the sub county. The study recommends creation of awareness of understanding the various drivers of LULCCs and impact of each on land quality.

Assessing the Utility of Uncrewed Aerial System Photogrammetrically Derived Point Clouds for Land Cover Classification in the Alaska North Slope

Uncrewed aerial systems (UASs) have been used to collect “pseudo field plot” data in the form of large-scale stereo imagery to supplement and bolster direct field observations to monitor areas in Alaska. These data supplement field data that is difficult to collect in such a vast landscape with a relatively short field season. Dense photogrammetrically derived point clouds are created and are facilitated to extract land cover data using a support vector machine (SVM) classifier in this study. We test our approach using point clouds derived from 1-cm stereo imagery of plots in the Alaska North Slope region and compare the results to field observations. The results show that the overall accuracy of six land cover classes (bare soil, shrub, grass, forb/herb, rock, and litter) is 96.8% from classified patches. Shrub had the highest accuracy (&gt;99%) and forb/herb achieved the lowest (&lt;48%). This study reveals that the approach could be used as reference data to check field observations in remote areas.

Using interpenetrating subsampling to incorporate interpreter variability into estimation of the total variance of land cover area estimates

Reference data obtained by interpreters is a key component of sample-based estimation of area of land cover and land cover change. However, interpreters may disagree when assigning the reference class label for a given sample unit and this inconsistency between interpreters contributes to the overall uncertainty of the estimated area. Interpenetrating subsampling (IPS) offers a practical way to incorporate interpreter variability into an unbiased estimator of the total variance. This method requires partitioning the full sample into g nonoverlapping groups with the sample units in each group then evaluated by a different interpreter and each interpreter determines the reference class data for only one group. The total variance is estimated by the among group variability of the g estimates of area. IPS was applied to estimate the total variance of land cover area estimates for a sample of 300 pixels selected from the Puget Sound region of the Northwest United States. The reference land cover data were obtained by seven interpreters who each labeled all 300 pixels. These data provided a unique opportunity to explore properties of IPS such as variability over different random partitions of the sample into groups and variability over different subsets of interpreters. IPS estimates of total variance were produced for each land cover class for group sizes of g = 2 through g = 6 and all possible combinations of the seven interpreters for each group size. The estimated total variance decreased with increasing number of groups. Incorporating interpreter variance increased the estimated total variance by a factor ranging from 1.08 (agriculture) to 7.06 (grass/shrub) in simple random sampling. The total variance estimates varied substantially over the random partitions of the sample into groups, but this variability decreased as the group size increased. Compared with other total variance estimators, the IPS estimator is simpler to compute and is more cost effective because it does not require repeat interpretations

Pemanfaatan Data Raster Dalam Menentukan Perubahan Penutupan Lahan Sub Daerah Aliran Sungai (DAS) Biyonga Kabupaten Gorontalo

This study aims to analyze changes in land cover over a specific period, focusing on the influencing factors and their impacts on the Biyonga Sub-Watershed ecosystem. The method used in this research is a combination of descriptive research method with spatial analysis interpretation approach and field survey. The research findings indicate that spatial analysis of land cover in the Biyonga Sub-Watershed revealed nine land cover classes, such as forest, shrubland, settlements, and agriculture. Land use change patterns were evaluated by overlaying land cover maps from 1990 to 2020. Significant changes in land cover occurred between 1990 and 2000, where secondary dryland forest cover changed to shrubland covering an area of 2,299.98 hectares. For the period 2000-2011, it was found that there was a loss of primary forest cover totaling 2097.27 hectares, which transitioned into secondary dry land forest and shrubland. Other changes included paddy fields transitioning into settlements and dry land agriculture, and dry land agriculture transitioning into settlements. From 2011 to 2020, there was an increase in the area of secondary forest cover and transitions from shrubland and dry land agriculture to secondary forest as well as mixed dry land agriculture.

Modeling of groundwater productivity in the Alfred Nzo District, South Africa, using relative frequency ratio and Shannon entropy models

Study regionAlfred Nzo District, Eastern Cape Province, South Africa. Study focusThe study aimed to identify groundwater potential zones in the Alfred Nzo District using advanced geographic information systems and remote sensing applications by integrating relative frequency ratio (RF) with predictor rate and Shannon entropy (SE) models. Seven influential factors that are thought to control groundwater availability in the Alfred Nzo District were considered to identify groundwater potential zones. These factors are drainage density, lineament density, rainfall, slope, land use and land cover, lithology, and soil class. The factors were weighted in the RF and SE approaches. About 70 % of boreholes were used as training datasets, and 30 % were used for validation. Groundwater potential zones were delineated by integrating all these factors and their corresponding weights in ArcGIS software. The accuracy of each model was evaluated using receiver operating characteristic curve and area under curve techniques. New hydrological insights for the regionFive groundwater potential zones were found in the research area, which includes very poor, poor, moderate, good, and very good, by RF and SE models. The results of the models revealed that the SE model, with a success rate of 79.80 %, performed better than the RF, with a success rate of 75.10 %. The results of this research could be helpful in adequately managing groundwater resources in the research area.

Characterization and Mapping of the Potential Area of Oil Palm Using Multi-Criteria Decision Analysis in a Geographic Information Systems Environment

This study presents a GIS-based Multi-Criteria Decision Analysis (MCDA) spatial model to assess land suitability for oil palm (OP) cultivation in rainfed conditions. Initially, twelve parameters, viz., rainfall, number of rainy days, mean temperature, RH, ground water level, soil pH, salinity, soil depth, surface texture, stoniness, slope, and drainage, were selected for assessing OP suitability in one of the states (Kerala). However, subsequent ground verification revealed significant discrepancies, which prompted refining the model by focusing on key parameters with greater accuracy and relevance. Accordingly, only five the most critical parameters affecting OP cultivation under rainfed conditions were selected through the rank sum method, and weights were assigned ac-cording to their significance. This study was aimed at creating a comprehensive tool for informed decision making in agricultural planning. District-level spatial data from reliable sources were utilized for Multi-Criteria Decision Analysis. Thematic rasters, representing key factors influencing land suitability, were created in a GIS. Utilizing MCDA techniques, a digital suitability map was generated in ArcGIS 10.3, delineating three distinct classes over an extensive area of 10.5 million hectares. Further, with an aim to focus on actual locations that can be readily planted with oil palm, the suitable locations identified were restricted to eight selected land use/land cover (LULC) classes. This strategic limitation aimed to facilitate the expansion of OP cultivation exclusively to areas deemed most suitable based on the identified criteria. The validation of this developed model involved comparing the suitability map generated with the performance of existing oil palm plantations across diverse locations. The reasonable similarity between the model’s predictions and real-world plantation outcomes validated the effectiveness of this MCDA spatial model. This model not only helps identify suitable locations for rainfed oil palm cultivation but also serves as a valuable tool for strategic decision making in agricultural land use planning.

Teaching on the cheap? The extent and impact of teaching assistants covering classes and leading lessons

AbstractThis study provides a detailed picture of how the on‐going challenge of teacher shortages in England and Wales is driving the deployment of teaching assistants (TAs) to cover classes in place of teachers. Analyses of data from a survey of nearly 6000 TAs in mainstream and special schools found that TAs cover classes for up to 4 h a week, with one in four covering classes because schools do not have enough teachers and/or are unable to get external supply teachers. The conditions under which TAs cover classes are challenging and a cause of stress and anxiety. Unlike teachers, TAs cover classes without a lesson plan or support from another TA. The majority of TAs said that covering classes inevitably involves them having to teach pupils – despite national guidance stipulating that cover by TAs should not involve ‘active teaching’. Three in four TAs report that their own role is not covered when they cover for teachers. Being deployed to cover classes disrupts and diverts TAs from carrying out their regular duties of delivering curriculum interventions and providing classroom support. Consequently, TAs feel that undertaking cover negatively impacts the quality of learning and provision for pupils with additional needs, as well as their workload, wellbeing, sense of effectiveness and job satisfaction. The conclusion that TAs actively teach lessons to whole classes has potentially significant real‐world consequences and implications for policy and practice. This paper calls for an urgent policy response to what is, in essence, a troubling symptom of the current teacher recruitment and retention crisis.

Assessing the vertical accuracy of digital elevation models by quality level and land cover

ABSTRACT The vertical accuracy of elevation data in coastal environments is critical because small variations in elevation can affect an area’s exposure to waves, tides, and storm-related flooding. Elevation data contractors typically quantify the vertical accuracy of lidar-derived digital elevation models (DEMs) on a per-project basis to gauge whether the datasets meet quality and accuracy standards. Here, we collated over 5200 contractor elevation checkpoints along the Atlantic and Gulf of Mexico coasts of the United States that were collected for project-level analyses produced for assessing DEMs acquired for the U.S. Geological Survey’s Three-Dimensional Elevation Program. We used land cover data to quantify non-vegetated vertical accuracy and vegetated vertical accuracy statistics (overall and by point spacing bins) and assessed elevation error by land cover class. We found the non-vegetated vertical accuracy had an overall root mean square error of 6.9 cm and vegetated areas had a 95th percentile vertical error of 22.3 cm. Point spacing was generally positively correlated to elevation accuracy, but sample size limited the ability to interpret results from accuracy by land cover, particularly in wetlands. Based on the specific questions a researcher may be asking, use of literature or fieldwork could assist with enhancing error statistics in underrepresented classes.

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.

Winter GPS tagging reveals home ranges during the breeding season for a boreal-nesting migrant songbird, the Golden-crowned Sparrow.

Determining space use for species is fundamental to understanding their ecology, and tracking animals can reveal insights into their spatial ecology on home ranges and territories. Recent technological advances have led to GPS-tracking devices light enough for birds as small as ~30 g, creating novel opportunities to remotely monitor fine-scale movements and space use for these smaller species. We tested whether miniaturized GPS tags can allow us to understand space use of migratory birds away from their capture sites and sought to understand both pre-breeding space use as well as territory and habitat use on the breeding grounds. We used GPS tags to characterize home ranges on the breeding grounds for a migratory songbird with limited available breeding information, the Golden-crowned Sparrow (Zonotrichia atricapilla). Using GPS points from 23 individuals across 26 tags (three birds tagged twice), we found home ranges in Alaska and British Columbia were on average 44.1 ha (95% kernel density estimate). In addition, estimates of territory sizes based on field observations (mean 2.1 ha, 95% minimum convex polygon [MCP]) were three times smaller than 95% MCPs created using GPS tags (mean 6.5 ha). Home ranges included a variety of land cover classes, with shrubland particularly dominant (64-100% of home range cover for all but one bird). Three birds tracked twice returned to the same breeding area each year, supporting high breeding site fidelity for this species. We found reverse spring migration for five birds that flew up to 154 km past breeding destinations before returning. GPS-tracking technology allowed for critical ecological insights into this migratory species that breeds in very remote locations.

Using Google Earth Engine to Assess the Current State of Thermokarst Terrain on Arga Island (the Lena Delta)

The mapping of thermokarst landscapes and the assessment of their conditions are becoming increasingly important in light of a rising global temperature. Land cover maps provide a basis for quantifying changes in landscapes and identifying areas that are vulnerable to permafrost degradation. The study is devoted to assessing the current state of thermokarst terrain on Arga Island. We applied a random forests algorithm using the capabilities of the Google Earth Engine cloud platform for the supervised classification of the composite image. The analyzed composite consists of a Sentinel-2 image and a set of calculated indices. The study found that thermokarst-affected terrains occupy 35% of the total area, and stable terrains cover 29% at the time of image acquisition. The classifier has also mapped water bodies, slopes, and blowouts. The accuracy assessment revealed that the overall accuracy for all the different land cover classes was 98.34%. A set of other accuracy metrics also demonstrated a high level of performance. This study presents significant findings for assessing landscape changes in a region with unique environmental features. It also provides a potential basis for future interdisciplinary research and for predicting future thermokarst landscape changes in the Lena Delta area.

Surface Runoff Estimation Using SCS-CN Method for Kurumballi Sub-watershed in Shivamogga District, Karnataka, India

SCS-curve number (CN) is one of the most well-liked and commonly applied methods for estimating surface runoff. The present study aims to calculate surface runoff using SCS-CN watershed-based calculation and geospatial technology in the Kurumballi sub-watershed Shivamogga District of Karnataka, India. The study area covers about an area of 47.67 sq. km. The union of land use/land cover classification with hydrological soil groups (HSG) yields the runoff estimation by the SCS-CN curve approach. This method calculates the runoff volume from the land surface flows into the river or streams. Moreover, the study area’s delineation of runoff potential zones was done using the thematic integration method. Different thematic layers were used, including lithology, geomorphology, soil, slope, land use and land cover, drainage, surface water bodies, groundwater contour, and isohyetal maps. Furthermore, associating it with the SCS-CN technique, the total surface runoff volume of the study area was estimated. The total surface runoff volume in the study area is 21065849.7 m3. To this study, thematic integration with the SCS-CN approach to estimate runoff for watersheds is valuable for improving water management and soil conservation.