Land Classification Research Articles

Pollution Evaluation and Risk Control Suggestion of Heavy Metals in Soil-crop System in Different Soil Parent Material Areas of Guangxi

To study the heavy metal pollution and influencing factors of soils and crops in different parent material areas and provide the basis for the classification and control of cultivated land, a total of 1 326 soil surface samples and 46 crop seed-root soil samples were collected from Xingye County in the southeast of Guangxi. The enrichment characteristics of heavy metals in the soil-crop system of four soil-forming parent materials were compared and analyzed, and the influencing factors of Cd absorption by rice were studied. The comprehensive quality impact index method was used to evaluate the soil and crops in the study area, and the safe use of cultivated land was proposed according to the evaluation results. The results showed that in the four soil-forming parent material areas, only the carbonate rock parent material area showed obvious enrichment of heavy metals in the soil, especially Cd. According to the "National Food Safety Standard for the Limit of Pollutants in Food" （GB 2762-2022）, the excess rate of heavy metal Cd in rice seeds was 35.7%, and the other heavy metal rates were not exceeded. The bioconcentration coefficient of heavy metal Cd in rice from different parent material areas was as follows： quaternary sediment area > carbonate parent material area > clastic parent material area > granite parent material area. The enrichment of Cd in rice was affected by soil pH and CaO. When the soil pH value was in the range of 5.5-6.5, the Cd content and exceeding rate of rice seed increased significantly. The evaluation results of soil-crop heavy metal pollution showed that the overall heavy metal risk in the study area was high, and the proportions of clean, mild, light, moderate, and heavy pollution were 23.91%, 10.87%, 17.39%, 17.39%, and 30.43%, respectively. Combined with the distribution of the comprehensive quality influence index and the pollution characteristics of different parent materials, the classification and control suggestions were put forward, which provided ideas for the safe utilization of polluted cultivated land.

The urban air quality nexus: Assessing the interplay of land cover change and air pollution in emerging South Asian cities

Air quality degradation presents a significant public health challenge, particularly in rapidly urbanizing regions where changes in land use/land cover (LULC) can dramatically influence pollution levels. This study investigates the association between LULC changes and air pollution (AP) in the five fastest-growing cities of Bangladesh from 1998 to 2021. Leveraging satellite data from Landsat and Sentinel-5P, the analysis reveals a substantial increase in urban areas and sparse vegetation, with declines in dense vegetation and water bodies over this period. Urban expansion was most pronounced in Sylhet (22–254%), while Khulna experienced the largest increase in sparse vegetation (2–124%). Dense vegetation loss was highest in Dhaka (20–77%) and water bodies (9–59%) over this period. Concentrations of six major air pollutants (APTs) - aerosol index, CO, HCHO, NO2, O3, and SO2 - were quantified, showing alarmingly high levels in densely populated industrial and commercial zones. Pearson's correlation indicates strong positive associations between APTs and urban land indices (R > 0.8), while negative correlations exist with vegetation indices. Geographically weighted regression modeling identifies city centers with dense urban built-up as pollution hotspots, where APTs exhibited stronger impacts on land cover changes (R2 > 0.8) compared to other land classes. The highest daily emissions were observed for O3 (1031 tons) and CO (356 tons) at Chittagong in 2021. In contrast, areas with substantial green cover displayed weaker pollutant-land cover associations. These findings underscore how unplanned urbanization drives AP by replacing natural land cover with emission sources, providing crucial insights to guide sustainable urban planning strategies integrating pollution mitigation and environmental resilience.

Critical Land Mapping of Protected Forest Areas in Sukamakmur District, Bogor Regency

Sukamakmur District is one of the areas in Bogor Regency where disasters often occur related to critical land conditions. This situation is often associated with changes in land cover as population growth continues. This research aims to identify and map critical land using a geographic information system (GIS) in Sukamakmur District. The method used is tumpeng stacking analysis with classification, scoring and weighting. There are 4 classes of critical land in Sukamakmur District, the largest percentage of low potentially critical land is 14,008 ha (82.32%). Then followed by slightly critical land with an area of 2,777.5 ha (16.32%), critical land with an area of 215.5 ha (1.27%), and very critical land with an area of only 16 ha (0.09%) of total area. This indicates that critical land for protected forests in Sukamakmur District is still relatively low.

Ресурсная оценка оленьих пастбищ как особо ценных земель Арктики в условиях ее промышленного освоения

The article discusses the issues of managing the territories of traditional economic activity in the Arctic zone, taking into account the results of their resource assessment. The authors analyze the methods for resource assessment of reindeer pastures as the basis for reindeer husbandry — the main activity of indigenous peoples of the northern regions of Russia and other countries. Based on the main productivity indicator of reindeer pastures — reindeer capacity, they propose a classification of lands according to their economic value. The practical significance of the research results lies in the possibility of using them in justifying projects for the industrial development of the Arctic, in conducting market and cadastral assessments of Arctic territories, and in calculating compensation payments to communities of indigenous peoples of the North during the industrial development of the Arctic.

Determination of the Change of Agricultural Landscapes Based on CORINE Land Cover Agricultural Land Classes Using GIS and Visual Quality Value with the AHP Method: The Case of Tekı̇rdağ Province

Agricultural landscapes contribute positively to the visual texture of the city and change over time. In this context, this study aims to determine the visual landscape quality of agricultural landscapes based on parameters on expert approach the hypothesis; it is important and necessary to determine the visual landscape values based on the change in agricultural landscapes over time. Within the framework of the developed hypothesis, it aims to make an expert-based visual landscape assessment of the agricultural landscapes of Tekirdağ Province, located in the northwestern part of Türkiye, based on nine subclasses created according to the CORINE land cover (CLC) classes, on the basis of 4 main parameters. Using the AHP technique, the priorities of the parameters and agricultural landscape classes and the relationships between basic parameters and visual preferences were determined. In this direction, the questions; What are the priorities of parameters that are effective in determining the visual quality of agricultural landscapes on the basis of expert approach?; What kind of changes have occurred in agricultural landscapes during the years 1990-2000-2006-2012-2018 in 9 subclasses created according to the CLC classes? and; How should the visual landscape quality values of the agricultural landscape subclasses created according to the CLC classes be ranked? The results of the study can be used as a tool in landscape planning and management studies as a factor in strengthening landscape quality.

Enhancing climate adaptation: Integrating place-based risk perceptions and coastalscape values using Q+PPGIS

Effective climate change adaptation planning requires evaluating the interplay of physical landscape characteristics and community perceptions of places. Geographic information system (GIS)-based approaches to measuring environmental values can identify locations for planning prioritization. But they seldom are used to consider spatial differences in socio-ecological worldview. This study aims to identify how place-based risk perceptions and landscape values can inform climate change adaptation using a Q+PPGIS method. We integrated mapped landscape values and climate risks (from 39 PPGIS participants) with elicited discourses (for 28 Q-method participants) to develop a novel land classification approach (reflexive Q+PPGIS). The results demonstrate significant differences between wilderness as a discourse and perceived, and the physical features associated with mapped wild areas. Similar differences in discourse and spatial patterns are observed for climate risks. For example, participants’ mapped areas of bushfire risk do not align with agencies’ identified risk areas, their jurisdictions, and capacities to take action. This disconnect presents a challenge to adaptation. Local governments can use this new method to show constituents multiple and often competing community demands for action, enabling honest conversations about feasible actions, responsibilities, and resource allocation.

Land Cover and Land Use Ontology—Evolution of International Standards, Challenges, and Opportunities

Knowledge of land is of central importance to manage the impact of mankind upon the environment. The understanding and treatment of land vary greatly across different regions and communities, making the description of land highly specific to each locality. To address the larger global issues, such as world food production or climate change mitigation, one needs to have a common standardized understanding of the biosphere cover and use of land. Different governments and institutions established national systems to describe thematic content of land within their jurisdictions. These systems are all valid and tuned to address various national needs. However, their integration at regional or global levels is lacking. Integrating data from widely divergent sources to create world datasets not only requires standards, but also an approach to integrate national and regional land cover classification systems. The ISO 19144 series, developed through the collaboration between the Food and Agriculture Organization of the United Nations (FAO) and the International Organization for Standardization (ISO), offers a meta-language for the integration of disparate land classification systems, enhancing interoperability, data sharing, and national to global data integration and comparison. This paper provides an overview of classification system concepts, different stages for the development of standards in ISO and the status of different standards in the ISO 19144 series. It also explores the critical role of the ISO 19144 series in standardizing land cover and land use classification systems. Drawing on practical case studies, the paper underscores the series’ potential to support global sustainable development goals and lays out a path for its future development and application. Using these standards, we gain not only a tool for harmonizing land classification, but also a critical level for advancing sustainable development and environmental stewardship worldwide.

Approach maximum likelihood classification and cellular automata markov chain model for land use/land cover change prediction in Nagan Raya Country, Indonesia

Approach maximum likelihood classification and cellular automata markov chain model for land use/land cover change prediction in Nagan Raya Country, Indonesia

Analysis of Agricultural Land Classification in East Kotawaringin District, Central Kalimantan Province using Landsat 8-OLI Image

Purpose:This research aims to map agricultural land in East Kotawaringin Regency, Kalimantan Province, and analyze it using Landsat 8 OLI satellite imagery in 2023.Methodology:The method used in this research is supervised classification, which will then carry out a data analysis process related to natural conditions in the field. Based on the results of satellite image data processing, there are five categories of land cover classification in the East Kotawaringin Regency area: built-up land, empty land, fields/moors, gardens and forests.Findings:According to the accuracy test results, the overall accuracy value of satellite imagery in East Kotawaringin Regency is 87%. Community activities, such as economic activities and meeting needs for public facilities and housing, influence the distribution of existing land cover areas.Implication:The classification results obtained later through maps of agricultural land in East Kotawaringin Regency can be used to find various studies, especially on expanding the agricultural sector.

Prediction of Canopy Cover for Agricultural Land Classification in Land Parcel Identification System (LPIS) Data Using Planet-Scope Multispectral Images: A Case Study of Gelendost District

Prediction of Canopy Cover for Agricultural Land Classification in Land Parcel Identification System (LPIS) Data Using Planet-Scope Multispectral Images: A Case Study of Gelendost District

Assessing Soil and Land Suitability of an Olive–Maize Agroforestry System Using Machine Learning Algorithms

Exponential population increases are threatening food security, particularly in mountainous areas. One potential solution is dual-use intercropped agroforestry systems such as olive (Olea europaea)–maize (Zea mays), which may mitigate risk by providing multiple market sources (oil and grain) for smallholder producers. Several studies have conducted integrated agroforestry land suitability analyses; however, few studies have used machine learning (ML) algorithms to evaluate multiple variables (i.e., soil physicochemical properties and climatic and topographic data) for the selection of suitable rainfed sites in mountainous terrain systems. The goal of this study is therefore to identify suitable land classes for an integrated olive–maize agroforestry system based on the Food and Agriculture Organization (FAO) land suitability assessment framework for 1757 km2 in Khyber Pakhtunkhwa province, Pakistan. Information on soil physical and chemical properties was obtained from 701 soil samples, along with climatic and topographic data. After determination of land suitability classes for an integrated olive–maize-crop agroforestry system, the region was then mapped through ML algorithms using random forest (RF) and support vector machine (SVM), as well as using traditional techniques of weighted overlay (WOL). Land suitability classes predicted by ML techniques varied greatly. For example, the S1 area (highly suitable) classified through RF was 9%↑ than that of SVM, and 8%↓ than that through WOL. The area of S2 (moderately suitable) classified through RF was 18%↑ than that of SWM and was 17%↓ than the area classified through WOL; similarly, the S3 (marginally suitable) class area via RF was 27%↓ than that of SVM, and 45%↓ than the area classified through WOL. Conversely, the area of N2 (permanently not suitable class) classified through RF and SVM was 6%↑ than the area classified through WOL. Model performance was assessed through overall accuracy and Kappa Index and indicated that RF performed better than SVM and WOL. Crop suitability limitations of the study area included high elevation, slope, pH, and large gravel content. Results can be used for sustainable intensification in mountainous rainfed regions by expanding intercrop agroforestry systems in developing nations to close yield gaps.

KAJIAN STUDI GEOTEKNIK KLASIFIKASI TANAH PERMUKAAN UNTUK PERENCANAAN PEMBANGUNAN DIKAWASAN UNIVERSITAS SAMUDRA

Soil classification is a science that aims to study ways to differentiate soil properties and divide soil into classes based on general characteristics. The aim of this research is to determine the physical properties of the land surface and determine the classification of surface land in the Samudra University area to be mapped based on soil type using ArcGis. 38 undisturbed soil samples were taken using a hand drill and 38 soil samples were tested in the laboratory to determine the physical properties of the soil and to map research results for surface soil types using Arcgis with the kriging interpolation method. From the test results, the lowest water content was at point 35 with a value of 4 55% and the highest was at point 5 with a value of 62 64%. The lowest liquid limit was at point 1 with a value of 15 65% and the highest was at point 13 with a value of 47 99% and the lowest plasticity index was at point 5 with a value of 5 70% and the highest at point 3 with a value of 26 93% while the lowest filter analysis was at points 10 and 12 with a value of 0% and the highest was at point 5 with a value of 40 74%. From the research results, it was concluded that the soil types in the Ocean University area received 7 classification groups based on AASHTO with the most dominant group being group A.2-6 with 19 points.

Assessing forest fragmentation due to land use changes from 1992 to 2023: A spatio-temporal analysis using remote sensing data

The increasing pressures of urban development and agricultural expansion have significant implications for land use and land cover (LULC) dynamics, particularly in ecologically sensitive regions like the Murree and Kotli Sattian tehsils of the Rawalpindi district in Pakistan. This study's primary objective is to assess spatial variations within each LULC category over three decades (1992–2023) using cross-tabulation in ArcGIS to identify changes in LULC and investigates into forest fragmentation analysis using the Landscape Fragmentation Tool (LFTv2.0) to classify forest into several classes such as patch, edge, perforated, small core, medium core, and large core. Utilizing remote sensing data from Landsat 5 and Landsat 9 satellites, the research focuses on the temporal dynamics in various land classes including Coniferous Forest (CF), Evergreen Forest (EF), Arable Land (AR), Buildup Area (BU), Barren Land (BA), Water (WA), and Grassland (GL). The Support Vector Machine (SVM) classifier and ArcGIS software were employed for image processing and classification, ensuring accuracy in categorizing different land types. Our results indicate a notable reduction in forested areas, with Coniferous Forest (CF) decreasing from 363.9 km2, constituting 45.0 % of the area in 1992, to 291.5 km2 (36.0 %) in 2023, representing a total decrease of 72.4 km2. Similarly, Evergreen Forests have also seen a significant reduction, from 177.9 km2 (22.0 %) in 1992 to 99.8 km2 (12.3 %) in 2023, a decrease of 78.1 km2. The study investigates into forest fragmentation analysis using the Landscape Fragmentation Tool (LFTv2.0), revealing an increase in fragmentation and a decrease in large core forests from 20.3 % of the total area in 1992 to 7.2 % in 2023. Additionally, the patch forest area increased from 2.4 % in 1992 to 5.9 % in 2023, indicating significant fragmentation. Transition matrices and a Sankey diagram illustrate the transitions between different LULC classes, providing a comprehensive view of the dynamics of land-use changes and their implications for ecosystem services. These findings highlight the critical need for robust conservation strategies and effective land management practices. The study contributes to the understanding of LULC dynamics and forest fragmentation in the Himalayan region of Pakistan, offering insights essential for future land management and policymaking in the face of rapid environmental changes.

A dataset of vector and coverage of river and lake surface water in Guangxi, Yunnan, Guizhou (China), and the ASEAN member states

Runoff plays an important role in the water cycle, and information on the distribution of rivers in a watershed is essential for water resources, ecology, environment as well as socio-economic activities in a certain region. The region involving Guangxi, Yunnan and Guizhou in China, and the ASEAN member states is known for cloudy rainfall and distinct mountainous terrain. A comparative analysis of existing river datasets highlights the insufficient characterization of river information in this unique region. To obtain more accurate river distribution data for assessing water resources and the ecological environments, we integrated in this paper the Eurasian continental river vector data (2010) and the ESA land classification data (2020). Following this, we employed an expansion and contraction buffer analysis method to address the issue of river discontinuity. And in this way, we produced a dataset of river surface water in Guangxi, Yunnan and Guizhou in China and the ASEAN member states. After further processing the ESA land classification data, we derived a vector dataset of lake surface water encompassing Guangxi, Yunnan, and Guizhou in China, along with the ASEAN member states. Finally, we calculated the coverage of river and lake surface water and compiled a coverage dataset with a resolution of 1km grid across Guangxi, Yunnan, Guizhou in China, and the ASEAN member states. Comparing with the HydroRIVERS dataset and our water remote sensing datasets (Global Surface water, Esri Land Cover, Dynamic World V1, GRWL), this dataset excels in characterizing the river system in the study area, and provides richer details than the input datasets, as evidenced by the following. This dataset can fill in gaps in the mountainous tributary sections of the Eurasian continent's river vector data from 2010, and effectively address the issue of discontinuous and missing rivers. The dataset can be used to provide basic prior data for water extraction in Guangxi, Guizhou, Yunnan and the ASEAN state members, and it holds great value in flood forecasting and water resources management. Moreover, it can also serve social and economic activities such as ecological preservation, transportation planning, agricultural irrigation and energy use.

Evaluation of land suitability for sorghum crops in Lampasio District, Tolitoli Regency

Sorghum is an alternative food ingredient that contains high levels of carbohydrates and calories so it can be a solution to food security problems. This research aims to evaluate the suitability of land for sorghum (Sorghum bicolor L.) in Tolitoli Regency, Indonesia. This research was conducted in Lampasio District, Tolitoli Regency using purposive sampling and survey methods on five land map units (SPL). The results of the research show that the area is classified as quite suitable land class (S2) with limiting factors for drainage and nutrient retention (oa, nr) with a land area of 3,652.7 ha spread over 5 SPL, namely SPL 1,2,3 and 5 while class The land (S3) is SPL 4. However, this can be overcome by adding fertilizer and adding organic material. So that it can improve the status of each land to be very suitable (S1) and quite suitable (S2).

Creating territorialized sustainability indices to evaluate pollination

CONTEXTIdentifying sustainable practices and landscape features that enhance the abundance of organisms providing ecosystem services can be challenging due to a limited understanding of the link between these practices and ecosystem functioning. One approach to assessing system complexity is to incorporate reliable indices that are markers of an essential ecosystem regulation service such as insect pollination. OBJECTIVEConsolidate indicators of sustainable farming practices and landscape features into two indices that consider different spatial scales (regional and local) to categorize peri-urban farms within two gradients of territorialized environmental sustainability. These indices enable the assessment of agroecosystem sustainability for a particular ecosystem service (insect pollination), which is critical for many crops. METHODSThe regional-scale index utilized four indicators of composition and configuration that reflected the landscape's heterogeneity and its influence on key resources and bee movement. For these features, we used three land classes: semi-natural, farm, and extensive crops within a 3000-m radius circle from the centre of the farm. The local-scale index included eight indicators relating to the sustainability of farming practices derived from semi-structured interviews with the farmers. Additionally, we included an indicator based on the extent of semi-natural areas within a 100-m radius circle. RESULTS AND CONCLUSIONSBoth indices generated a synthesis to obtain two gradients (regional and local) of territorialized environmental sustainability for the farms. We validated these metrics through records of bee abundance on Cucurbita maxima flowers in each farm, as an indicator of the bee-pollination service. The variations of regional and local indices among and within the same farm (e.g., a high local-scale index and a low regional-scale index) emphasize the importance of considering both spatial contexts when evaluating ecosystem services. Both indices correlated with bee abundance, with the local-scale index exhibiting a positive stronger correlation than the regional (0.68 vs. 0.61 respectively). For farmers, making changes to farming practices at the local scale is more achievable than altering features at the regional scale, where government territorial planning and coordinated efforts among residents in the area are required. Consequently, enhancing a local-scale practice might be a more feasible way to increase farm sustainability. SIGNIFICANCEThe indices will enable a more straightforward comparison of sustainability among farms or within the same farm over time than analyzing each socio-environmental metric separately. Following the methodology proposed here, other indices for other essential ecosystem services in agroecosystems could be developed.

Class: A Memoir of Motherhood, Hunger, and Higher Education

Book review of Stephanie Land's Class: A Memoir of Motherhood, Hunger, and Higher Education by Benjamin Michael Dadzie from Clemson University.

Connecting forest soil properties with ecosystem services: Toward a better use of digital soil maps—A review

AbstractThe soil supports many ecosystem services (ES) essential to human well‐being. Rapid developments in digital soil mapping (DSM) allow the mapping of soil types and soil properties with improved resolution and accuracy. However, the potential of DSM to improve the assessment and mapping of ES is not fully exploited. To better understand this potential, we synthesized the peer‐reviewed literature. We examined what empirical studies reveal about the role of soil properties in the assessment of four major ES provided by the forest: (I) timber production, (II) soil carbon storage, (III) regulation of water flow and provision of clean water, and (IV) the soil as a habitat for organisms. Results revealed that soil properties are strongly related to the provision of ES. Therefore, using DSM could greatly improve the assessment of the ES provided by forests. Several variables were related to specific ES regardless of region or ecosystem types, but others were found to be situation‐specific (climate and soil type) and need to be considered at the proper scale or within a proper land classification framework. DSM products have the potential to greatly improve the assessment of ES by turning qualitative relationships between soil and ES to quantitative ones. This could also lead to the discovery of new soil–ES relationships. For this potential to be realized, progress should be made in mapping the most crucial soil parameters with greater precision and in promoting the use of soil parameters in ES assessment.

Assessment of universal thermal climate index (UTCI) using the WRF-UCM model over a metropolitan city in India.

Rapid urbanization increases urban air temperature, considerably affecting health, comfort, and the quality of life in urban spaces. The accurate assessment of outdoor thermal comfort is crucial for urban health. In the present study, a high-resolution mesoscale model coupled with a layer Urban Canopy Model (WRF-UCM) is implemented over the city of Hyderabad (17.3850° N, 78.4867° E) to simulate urban meteorological conditions during the summer and winter period of 2009 and 2019. The universal thermal climate index (UTCI) has been estimated using the model-derived atmospheric variables and a human biometeorology parameter to assess the linkages between the outdoor environment and thermal comfort. Results revealed that during summer, the city experiences nearly 50h of very strong thermal stress, whereas about 120h of slight cold stress are experienced during winter. The urban area in Hyderabad expanded from 5 to 15% during the study period, leading to a 2.5℃ (2.8 ℃) increase in land surface temperature, and a 1.2 (1.9 ℃) rise in air temperature at 2m height and 1.5 (2.5 ℃) UTCI during summer (winter) time. The analysis reveals that the maximum UTCI values were noticed over built-up areas compared to other land classes during daytime and nighttime. The results derived from the present study have shown that the performance of WRF-UCM-derived UTCI reasonably portrayed the significant impact of urbanization on thermal comfort over the city and provided useful insights with regard to urban comfort and welfare.

Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications

Classifying land use and land cover (LULC) is essential for various environmental monitoring and geospatial analysis applications. This research focuses on land classification in District Sukkur, Pakistan, employing the comparison between machine and deep learning models. Three satellite indices, namely, NDVI, MNDWI, and NDBI, were derived from Landsat-8 data and utilized to classify four primary categories: Built-up Area, Water Bodies, Barren Land, and Vegetation. The main objective of this study is to evaluate and compare the effectiveness of comparison of machine and deep learning models. The machine learning models including Random Forest achieved an overall accuracy of 91.3% and a Kappa coefficient of 0.90. It accurately classified 2.7% of the area as Built-up Area, 1.9% as Water Bodies, 54.8% as Barren Land, and 40.4% as Vegetation. While slightly less accurate, Decision Tree model provided reliable classifications. Deep learning models showed significant accuracy, of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The CNN model achieved an impressive overall accuracy of 97.3%, excelling in classifying Water Bodies with User and Producer Accuracy exceeding 99%. The RNN model, with an overall accuracy of 96.2%, demonstrated strong performance in categorizing Vegetation. These findings offer valuable insights into the potential applications of machine learning and deep learning models for perfect land classifications, with implications for environmental monitoring management and geospatial analysis. The rigorous validation and comparative analysis of these models contribute to advancing remote sensing techniques and their utilization in land classification tasks. This research presents a significant contribution to the field and underscores the importance of precise land classification in the context of sustainable land management and environmental conservation.