Landscape Function Research Articles

Ensemble Machine Learning on the Fusion of Sentinel Time Series Imagery with High-Resolution Orthoimagery for Improved Land Use/Land Cover Mapping

In the United States, several land use and land cover (LULC) data sets are available based on satellite data, but these data sets often fail to accurately represent features on the ground. Alternatively, detailed mapping of heterogeneous landscapes for informed decision-making is possible using high spatial resolution orthoimagery from the National Agricultural Imagery Program (NAIP). However, large-area mapping at this resolution remains challenging due to radiometric differences among scenes, landscape heterogeneity, and computational limitations. Various machine learning (ML) techniques have shown promise in improving LULC maps. The primary purposes of this study were to evaluate bagging (Random Forest, RF), boosting (Gradient Boosting Machines [GBM] and extreme gradient boosting [XGB]), and stacking ensemble ML models. We used these techniques on a time series of Sentinel 2A data and NAIP orthoimagery to create a LULC map of a portion of Irion and Tom Green counties in Texas (USA). We created several spectral indices, structural variables, and geometry-based variables, reducing the dimensionality of features generated on Sentinel and NAIP data. We then compared accuracy based on random cross-validation without accounting for spatial autocorrelation and target-oriented cross-validation accounting for spatial structures of the training data set. Comparison of random and target-oriented cross-validation results showed that autocorrelation in the training data offered overestimation ranging from 2% to 3.5%. The XGB-boosted stacking ensemble on-base learners (RF, XGB, and GBM) improved model performance over individual base learners. We show that meta-learners are just as sensitive to overfitting as base models, as these algorithms are not designed to account for spatial information. Finally, we show that the fusion of Sentinel 2A data with NAIP data improves land use/land cover classification using geographic object-based image analysis.

Mapping protein conformational landscapes from crystallographic drug fragment screens.

Proteins are dynamic macromolecules. Knowledge of a protein's thermally accessible conformations is critical to determining important transitions and designing therapeutics. Accessible conformations are highly constrained by a protein's structure such that concerted structural changes due to external perturbations likely track intrinsic conformational transitions. These transitions can be thought of as paths through a conformational landscape. Crystallographic drug fragment screens are high-throughput perturbation experiments, in which thousands of crystals of a drug target are soaked with small-molecule drug precursors (fragments) and examined for fragment binding, mapping potential drug binding sites on the target protein. Here, we describe an open-source Python package, COLAV (COnformational LAndscape Visualization), to infer conformational landscapes from such large-scale crystallographic perturbation studies. We apply COLAV to drug fragment screens of two medically important systems: protein tyrosine phosphatase 1B (PTP-1B), which regulates insulin signaling, and the SARS CoV-2 Main Protease (MPro). With enough fragment-bound structures, we find that such drug screens also enable detailed mapping of proteins' conformational landscapes.

Single-cell profiling reveals altered immune landscape and impaired NK cell function in gastric cancer liver metastasis.

Gastric cancer (GC) is a substantial global health concern, and the development of liver metastasis (LM) in GC represents a critical stage linked to unfavorable patient prognoses. In this study, we employed single-cell RNA sequencing (scRNA-seq) to investigate the immune landscape of GC liver metastasis, revealing several immuno-suppressive components within the tumor immune microenvironment (TIM). Our findings unveiled an increased presence of cancer-associated fibroblasts (CAFs), myeloid-derived suppressor cell (MDSC)-like macrophages, tumor-associated macrophage (TAM)-like macrophages, and naive T cells, while conventional dendritic cells (cDCs) and effector CD8 T cells declined in LM. Additionally, we identified two distinct natural killer (NK) cell clusters exhibiting differential cytotoxicity-related gene expression, with cytotoxic NK cells notably reduced in LM. Strikingly, TGFβ was identified as an inducer of NK cell dysfunction, potentially contributing to immune evasion and tumor metastasis. In preclinical LM models, the combined approach of inhibiting TGFβ and transferring NK cells exhibited a synergistic impact, resulting in a significant reduction in liver metastasis. This work highlights the importance of understanding the complex immune dynamics within GC liver metastasis and presents a promising strategy combining TGFβ inhibition and NK-based immunotherapy to improve patient outcomes.

Landscape understanding and values in extended public consultations on spatial planning in rural communes in Poland

A large part of spatial planning projects in Polish rural communes deals with landscape issues such as protection and planning. Besides legal regulations extended public consultations (EPCs) on spatial planning processes provide an opportunity to comprehensively address and negotiate landscape arguments. This research aims to identify the understanding and value of the concept of landscape by local communities in the examined EPC cases. This paper explores landscape issues through a systematic analysis (multiple-case study) of six cases of EPCs carried out in Poland between 2019 and 2022. The landscape was negotiated in terms of its various functions to provide value for aesthetics, culture, history, identity, recreation, and economy. In some cases, the landscape was used as an argument to promote a hidden agenda. In the rural communes, aesthetic functions of landscapes were frequently addressed, while natural, ecological, and climatic functions of the landscape were barely mentioned, suggesting that the understanding of landscape remains at a representative, cultural, and visual level, which differs from urban discourses that often focus on climatic and ecological functions of landscape. EPCs are a sound instrument to further integrate landscape as a common asset into spatial planning processes.

Digital mapping of coastal landscapes integrating ocean-environment relationships and machine learning

Digital mapping of coastal landscapes integrating ocean-environment relationships and machine learning

Single-cell EpiChem jointly measures drug–chromatin binding and multimodal epigenome

Studies of molecular and cellular functions of small-molecule inhibitors in cancer treatment, eliciting effects by targeting genome and epigenome associated proteins, requires measurement of drug-target engagement in single-cell resolution. Here we present EpiChem for in situ single-cell joint mapping of small molecules and multimodal epigenomic landscape. We demonstrate single-cell co-assays of three small molecules together with histone modifications, chromatin accessibility or target proteins in human colorectal cancer (CRC) organoids. Integrated multimodal analysis reveals diverse drug interactions in the context of chromatin states within heterogeneous CRC organoids. We further reveal drug genomic binding dynamics and adaptive epigenome across cell types after small-molecule drug treatment in CRC organoids. This method provides a unique tool to exploit the mechanisms of cell type-specific drug actions.

Biogeochemical Migration of Some Rare Elements in the “Leaf Debris–Soil” System of the Catenary Landscapes in Tropical Mountainous Forests in Southern Vietnam

Expeditionary studies of the functioning of landscapes of mid-mountain monsoon (including fog) forests have been being conducted within the landscape and ecological station in the territory of the Bidoup-Nui Ba National Park and the adjacent Hon Giao since 2018 and are currently underway. One of the research objectives is to clarify the biogeochemical migrations of the material composition of soils in the “leaf debris–soil” system. We have consistently studied natural objects for their material composition as well as the intensity and rate of involvement of chemical elements in physicochemical migration processes in the “leaf debris–soil” system. Our findings indicate an active influx of a select group of examined elements (Se, Pd, Ag, Cd, Sn, Bi), particularly Bi, Pd, Se, and Cd, through the leaf debris and the detachment of aboveground plant organs, warranting their integration into organogenic soil horizons. Subsequently, lateral migration (Pd, Cd, Se) ensues. Slope processes within subordinate landscape facets, in addition to soil moisture and aeration processes, contribute to the subsequent redistribution of elemental volumes introduced into organogenic soil horizons.

Fitness Landscapes and Evolution of Catalytic RNA.

The relationship between genotype and phenotype, or the fitness landscape, is the foundation of genetic engineering and evolution. However, mapping fitness landscapes poses a major technical challenge due to the amount of quantifiable data that is required. Catalytic RNA is a special topic in the study of fitness landscapes due to its relatively small sequence space combined with its importance in synthetic biology. The combination of in vitro selection and high-throughput sequencing has recently provided empirical maps of both complete and local RNA fitness landscapes, but the astronomical size of sequence space limits purely experimental investigations. Next steps are likely to involve data-driven interpolation and extrapolation over sequence space using various machine learning techniques. We discuss recent progress in understanding RNA fitness landscapes, particularly with respect to protocells and machine representations of RNA. The confluence of technical advances may significantly impact synthetic biology in the near future.

Modelling Multi-Scenario Ecological Network Patterns and Dynamic Spatial Conservation Priorities in Mining Areas

Mining activities have significantly altered the land use patterns of mining areas, exacerbated the degree of landscape fragmentation, and thereby led to the loss of biodiversity. Ecological networks have been recognized as an essential component for enhancing habitat connectivity and protecting biodiversity. However, existing studies lack dynamic analysis at the landscape scale under multiple future scenarios for mining areas, which is adverse to the identification of ecological conservation regions. This study used the MOP-PLUS (multi-objective optimization problem and patch-level land use simulation) model to simulate the land use patterns in the balance of ecology and economy (EEB) scenario and ecological development priority (EDP) scenario for the Shendong coal base. Then, climate change and land use patterns were integrated into ecosystem models to analyze the dynamic changes in the ecological networks. Finally, the conservation priorities were constructed, and dynamic conservation hotspots were identified using landscape mapping methods. The following results were obtained: (1) From 2000 to 2020, large grassland areas were replaced by mining areas, while cultivated land was replenished. By 2030, the forest and grassland areas (967.00 km2, 8989.70 km2) will reach their peaks and the coal mine area (356.15 km2) will reach its nadir in the EDP scenario. (2) The fragmentation of ecological sources intensified (MPS decreased from 19.81 km2 to 18.68 km2) and ecological connectivity declined (in particular, α decreased by 6.58%) from 2000 to 2020. In 2030, the connectivity in the EDP scenario will increase, while the connectivity in the EEB scenario will be close to that of 2020. (3) The central and southeastern parts of the Shendong coal base have higher conservation priorities, which urgently need to be strengthened. This study offers guidance on addressing the challenges of habitat and biodiversity conservation in mining areas.

Transcription factor network dynamics during the commitment to oncogene-induced senescence

Aberrant oncogenic signaling causes cells to transition into oncogene-induced senescence (OIS) to limit uncontrolled proliferation. Despite being a potent tumor suppressor mechanism, OIS is an unstable cell state susceptible to reprogramming that can promote tumorigenesis. Therefore, elucidating the underlying gene regulatory mechanisms that commit cells to OIS is critical to identifying actionable targets to modulate the senescence state. We previously showed that timely execution of the OIS program is governed by hierarchical transcription factor (TF) networks. However, the gene regulatory mechanisms that prime cells to commit to the OIS fate early upon oncogene hyperactivation are currently not known. Here, we leveraged our time-resolved multi-omic profiling approach to generate TF networks during the first 24 h of oncogenic HRASG12V activation. Using this approach, we demonstrate that the commitment to OIS requires the rearrangement of the TF network on a pre-established epigenomic landscape, priming the cells for the substantial chromatin remodeling that underpins the transition to OIS. Our results provide a detailed map of the chromatin landscape before cells transition to OIS thus offering a platform for manipulation of senescence outcomes of potentially therapeutic value.

Improvement of methods of rational use in conditions of land degradation in the Almaty region, Karasai district

The study was aimed at identifying the potential of modern methods of rational land use in the Karasai district of the Almaty region of Kazakhstan, taking into account their intensive degradation. The research methodology was represented by the methods of statistical observation, comparison, analytical-structural grouping and forecasting. The priority goals of modernisation of agriculture of the Republic in the technological aspect have been analysed. It was established that innovative approaches to land use have the potential to increase the level of efficiency of the agrarian sector, improve the state of local and regional landscape. The concept of improving the state of degraded lands, including a system of management measures and practical activities, has been developed. It was proved that it should be based on the synergy of economic efficiency and environmental safety, with the mandatory introduction of modern innovative technological approaches. The effectiveness of methods of rational use of degraded lands as an effective tool for the transformation of the agrarian sector has been determined. It was proposed to intensify the development of organic agricultural production, which is positioned as the gentlest for degraded landscapes. It was proved that the implementation of sustainable management of landscape complexes in the innovative context implies the use of information monitoring technology, which anticipates the diagnosis, genesis and forecasting of the state of the studied ecosystems. Such measures will make it possible to develop programmes for the restoration of ecological functions of natural landscapes, which is an integral part of sustainable development programmes. Actualised the situation in the context of ecologisation of land use in Kazakhstan, predicted further destruction of ecosystems of agrarian landscapes in case of use of aggressive methods of soil cultivation. The necessity of introduction of improved methods of rational land use is substantiated, and the specificity of the introduction of organic and biological technologies of agricultural production is outlined, with an indication of tangential risks and challenges in the economic realities of Kazakhstan. The study substantiated that the application of integrated management and ecosystem approach have a synergistic potential to ensure the rational use of land in the Almaty region, the Karasai district in the conditions of their degradation

Evaluation of landscape ecological security pattern via the “pattern-function-stability” framework in the Guanzhong Plain Urban Agglomeration of China

Most studies have assessed and constructed landscape ecological security patterns (LESPs) primarily from the perspective of landscape morphology by employing morphological spatial pattern analysis, with little attention paid to fundamental ecosystem attributes (such as ecosystem functions and stability). Thus, this study proposed a comprehensive evaluation and optimization framework for LESPs from the perspective of “mode function stability” by integrating assessment landscape pattern, ecological function, and landscape stability. A comprehensive evaluation and optimization of the LESPs was conducted using the Minimum Cumulative Resistance (MCR) model in the Guanzhong Plain Urban Agglomeration (GPUA) as the research area. The results showed that: (1) Generally, the landscape quality in urban agglomerations was relatively low because of the large area of agricultural vegetation, high human interference, and landscape fragmentation, which caused low levels of landscape pattern, function, and stability. (2) LESPs were mainly determined by landscape stability in urban agglomerations due to low-quality ecosystems, rapid landscape transformation, and severe anthropogenic disturbances. (3) There was a large variation in the landscape function and stability of a certain landscape type due to their different structures and human interference across space in urban agglomerations. According to assessment by “pattern-function-stability” framework, the ecological sources and corridors covered with natural forest were the crucial cornerstone to constructing LESPs, and the rivers in crop planting areas were the inevitably selected corridors, but their ecological function and stability needed further improvement in construction. (4) The framework can assess spatial patterns and ecological functions to further the stability and sustainability of the landscape in maintaining ecological security and facilitating the identification of improvement objectives or measures of individual ecological sources or corridors in regional ecological infrastructure construction practices.

What factors influence employee loyalty? A meta-analysis using VOSviewer

Academic research on employee loyalty, which is a crucial aspect of organizational success in today's competitive business era, is gaining increasing attention in the human resource management literature. Therefore, this study aims to map out concepts to provide a systematic and comprehensive analysis of trends related to employee loyalty through a bibliometric approach. The Scopus database was utilized to analyze and categorize all English-language literature published during the period from 2017 to 2023. VOSviewer software is also employed for graphical mapping of the scholarly landscape. Out of 263 documents retrieved from the Scopus database related to employee loyalty, 148 documents were selected for bibliometric analysis to comprehensively assess the current state and anticipate future trends. The analysis results indicate an increase in the number of publications on employee loyalty from 2017 to 2023. The selected articles cover various topics, including factors influencing employee loyalty, measurement of loyalty, human resource management strategies to enhance employee loyalty, and the impact of employee loyalty on organizational performance. The results indicate a significant increase in the literature, demonstrating that employee loyalty has a substantial impact on organizational sustainability and cohesion among its members. The practical implications of these findings can assist organizations in designing more effective human resource management strategies to retain and enhance employee loyalty, which, in turn, can contribute to the long-term success of the organization.

Study on the multifunctional spatial-temporal evolution and coupling coordination of cultivated land: A case study of Hebei Province, China.

The rational use of cultivated land can guarantee food security and thus is highly important for ensuring social stability, economic development and national security. The current study investigated the multifunctional temporal and spatial variation characteristics of cultivated land and explored the spatial and temporal characteristics of the multifunction and coupling coordination degrees of cultivated land throughout Hebei Province. Based on the administrative division data, statistical yearbook data and land use status data of the impacted areas, a multifunctional evaluation index system of cultivated land was established. The CRITIC weight method and entropy weight method were used to determine the weight of the index, the comprehensive index model was used to determine the production, social security, ecology and landscape functions of cultivated land of Hebei Province in different periods, the coupling coordination model was used to explore the multifunctional coupling coordination degree of cultivated land in each county, and spatial autocorrelation analysis was performed to determine the correlation of the multifunctional coupling coordination degrees. From 2000 to 2020, the production, social security and landscape function of cultivated land in Hebei Province trended upward; the ecological function trended slightly downward. The multifunctional coupling coordination degree of cultivated land in Hebei Province trended significantly upward and changed from limited coordination to intermediate coordination. Furthermore, it exhibited strong agglomeration and a significant positive spatial correlation, forming a 'V'-type change rule of first decreasing and then increasing. Hebei Province exhibited remarkable spatial and temporal characteristics of the multifunction and coupling coordination degrees of cultivated land. Regions could thus customize different cultivated land functions to maximize the benefits of cultivated land use. The findings of this study may provide a scientific basis and theoretical support for sustainably using and managing cultivated land resources in areas with similar human geographical environments.

Ландшафтно-экологическое территориальное зонирование (на материалах Акмолинской области)

Introduction. Modern human activities in nature are subject to increasing regulation and restrictions, which should be reflected in systems for the use of natural resources, primarily in agricultural production. The problem under consideration is of particular relevance for the regions of Northern Kazakhstan, since the natural landscapes of the region have been radically changed and transformed into natural and agricultural complexes with a disturbed landscape-ecological balance.From the point of view of modern natural science, the organization of the rational use of rural areas should be solved by applying a concept based on the landscape-ecological approach. The purpose of the study. Territorial zoning of the agricultural landscape to optimize the use of agricultural land based on the landscape-ecological approach. Research methods. Cartographic materials used as the basis for the creation of diagrams and design developments, obtained on the basis of data from the virtual information system of the land cadastre of the Republic of Kazakhstan and processed using the ArcGIS program. Research results. Based on materials from the steppe zone of the Akmola region of the Republic of Kazakhstan, an analysis of landscape conditions and ecological stability of agricultural landscape systems was carried out. Analysis of territorial landscape zoning allowed us to conclude that the predominant part of the field landscapes of the steppe eons of this region is occupied by natural-territorial complexes of watershed spaces and watershed slopes, and the most common form of relief is slope surfaces. Ecological zoning of agricultural landscapes in the Akmola region revealed that the most common agricultural landscapes are characterized by weak stability and unstable agricultural landscapes. The article proposes a methodology for territorial zoning of agricultural lands on a landscape-ecological basis in the conditions of the Akmola region. It includes the following procedure: drawing up a landscape map. identification of homogeneous ecological zones; agrolandscape microzoning. As a result of research at the research object, a scheme of territorial landscape-ecological zoning for land use of agricultural formations was compiled, which is based on taking into account the paradynamic landscape structure of steppe landscapes and the degree of their anthropogenic transformation. At the same time, relatively homogeneous landscape-ecological microzones were identified, within which the elementary landscapes of the steppe catena were differentiated according to measures that stabilize the stability of the agricultural landscape. Conclusions. 1. On the territory of the Akmola region, natural landscapes have been transformed into agricultural production modifications. with a low degree of sustainability, requiring measures to maintain landscape-ecological balance. 2. The methodology for territorial zoning of steppe agricultural landscapes should be based on taking into account the paradynamic landscape structure of steppe landscapes, i.e. its catenary device. 3. Application of the results of territorial landscape-ecological zoning in design developments for the use and protection of land will allow the selection of optimal directions that ensure the sustainability of agricultural landscapes.

Supply chain competitiveness through agility and digital technology: A bibliometric analysis

Supply chain competitiveness and agility are matured areas in supply chain management. While there is an ongoing evolution in digital technology alongside supply chain competitiveness and agility, the literature appears to have limited bibliometric reviews on how digital technology impacts these aspects. This study examines supply chain competitiveness with bibliometric analysis, focusing on the critical elements of supply chain agility and the impact of rapidly advancing digital technologies. The study bridges the gap between management and technology disciplines. Employing the PRISMA methodology, 147 scholarly articles were meticulously selected and analysed, adopting a multifaceted analytical approach that combines bibliometric and descriptive analyses. This thorough literature synthesis reveals a profound and intricate connection between supply chain agility and digital technology, underscoring their joint significance in fostering competitive advantage within the dynamic business landscape. This investigation contributes to the existing body of knowledge by identifying seven distinct clusters, offering a detailed map of the current research landscape. This study charts a course for future academic inquiries into this critical area and provides valuable insights for practitioners. It underscores the importance of integrating agile supply chain practices and digital technologies to maintain and enhance competitive positioning in today’s fast-paced business environment.

THE ROLE OF OPEN-AIR CALVARIES IN THE CONTEXT OF LANDSCAPE HERITAGE PROTECTION OF THE EASTERN SUDETES

The article concerns the meaning and landscape functions of Small Calvaries located in the Eastern Sudetes in the border area of the Czech Republic and Poland. The publication aims to indicate the main typological features of this type of calvary, taking into account the current behaviour of residents having a common sarcastic heritage. Due to the subject, interdisciplinary research was undertaken in the direction of valorization as well as environmental interviews. The use of geosociological methodology made it possible to assess the landscape in terms of its contemporary functions and potential threats. The research allowed us to distinguish two types of landscape layouts: elliptical and linear of a historical nature, and modern, mainly linear. Sociological research showed the attitude of local communities to the sacred heritage in the Eastern Sudetes.

Comprehensive analysis of EphA2 in pan-cancer: A prognostic biomarker associated with cancer immunity.

Several studies have reported a significant relationship between Ephrin receptor A2 (EphA2) and malignant progression in numerous cancers. However, there is a lack of comprehensive pan-cancer analysis on the prognostic value, mutation status, methylation landscape, and potential immunological function of EphA2. Using The Cancer Genome Atlas, Genotype Tissue Expression Database and GEO data, we analysed the differences in EphA2 expression between normal and tumour tissues and the effects of EphA2 on the prognosis of different tumours. Furthermore, using GSCALite, cBioPortal, TISDB, ULCLAN and TIMER 2.0 databases or platforms, we comprehensively analysed the potential oncogenic mechanisms or manifestations of EphA2 in 33 different tumour types, including tumour mutation status, DNA methylation status and immune cell infiltration. The correlation of EphA2 with immune checkpoints, tumour mutational burden, DNA microsatellite instability and DNA repair genes was also calculated. Finally, the effects of EphA2 inhibitors on the proliferation of human glioma and lung cancer cells were verified in cellular experiments. EphA2 is differentially expressed in different tumours, and patients with overexpression have poorer overall survival. In addition, gene mutations, gene copy number variation and DNA/RNA methylation of EphA2 have been identified in various tumours. Moreover, EphA2 is positively associated with immune infiltration involving macrophages and CD8+ T cells. Further, EphA2 mRNA expression is significantly associated with immune checkpoint in various cancers, especially programmed death-ligand 1. Finally, the EphA2 inhibitor ALW-II-41-27 shows potent anti-tumour activity. Our first pan-cancer study of EphA2 provides insight into the prognostic and immunological roles of EphA2 in different tumours, suggesting that EphA2 might be a potential biomarker for poor prognosis and immune infiltration in cancer.

Reverse engineering neuron type-specific and type-orthogonal splicing-regulatory networks using single-cell transcriptomes.

Cell type-specific alternative splicing (AS) enables differential gene isoform expression between diverse neuron types with distinct identities and functions. Current studies linking individual RNA-binding proteins (RBPs) to AS in a few neuron types underscore the need for holistic modeling. Here, we use network reverse engineering to derive a map of the neuron type-specific AS regulatory landscape from 133 mouse neocortical cell types defined by single-cell transcriptomes. This approach reliably inferred the regulons of 350 RBPs and their cell type-specific activities. Our analysis revealed driving factors delineating neuronal identities, among which we validated Elavl2 as a key RBP for MGE-specific splicing in GABAergic interneurons using an in vitro ESC differentiation system. We also identified a module of exons and candidate regulators specific for long- and short-projection neurons across multiple neuronal classes. This study provides a resource for elucidating splicing regulatory programs that drive neuronal molecular diversity, including those that do not align with gene expression-based classifications.

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.