Land Use Classification Research Articles

Impact of agricultural land-use on functional feeding groups of Afrotropical Ephemeroptera, Plecoptera and Trichoptera in the Kat River, Eastern Cape, South Africa

Despite Africa experiencing a substantial rise in inadequately managed agricultural practices, studies examining the effects of these activities on the functional organisation of macroinvertebrates in tropical streams are underdeveloped. The responses of Ephemeroptera, Plecoptera and Trichoptera (EPTs) functional feeding groups (FFGs) to agricultural pollution were investigated in the Kat River, Eastern Cape, South Africa, to identify potential FFG indicators. Physicochemical parameters and macroinvertebrates were sampled from eight sites delineated into four land-use impact categories (highly impacted, HIC; impacted category, IC; moderately impacted, MIC; and least impacted, LIC) based on the percentage of agricultural land cover. The Permutational multivariate analyses of variance (PERMANOVA) results revealed land use (F = 4.2, 3.62; p < 0.05) and season (F = 2.89, p < 0.03) influenced FFGs in the river, with shredder abundances decreasing with increasing agricultural stress. Conversely, collectors, predators and scrapers were tolerant of agricultural disturbance. Nutrient variables (NO3-N, NO2-N and NH4-N), canopy and depth were the critical variables that affected FFG structure in the river. Our findings provided more understanding and insights into the functional structure of EPT in relation to agricultural pollution and can contribute to developing trait-based biomonitoring tools in Africa.

A method to map land use impacts on microclimate regulation supply in urban environments

Land use impacts land surface temperature (LST), especially in urban areas where anthropogenic materials have a high capacity to store energy. Nevertheless, cities have many other land uses (e.g., forests, lawns) that can reduce LST and contribute to high microclimate regulation. In this work, we develop a method to map land use impacts on microclimate regulation supply using an Unmanned Aerial Vehicle (UAV). A detailed methodology was developed for 1) UAV's mission planning, 2) field data collection for method validation, 3) RGB and thermal mission reconstruction, 4) land use classification, 5) data extraction and 6) spatial and statistical analysis. The method developed can be beneficial to local authorities and transferable to other realms. It will allow us to understand the impacts of different land uses on microclimate regulation. For this, an area with heterogeneous land uses was used as a test site.• A novel methodology was created to map land use impacts on microclimate regulation supply in urban areas;• High-resolution UAV RGB and thermal imagery for land-use classification and surface temperature analysis;• The method can help understand the capacity of the different land uses on microclimate regulation;

Remote sensing applied to biophysical parameters and land cover to identify urban heat islands in Recife (PE), Brazil

Urban growth results in several changes, mainly related to demographic, social, economic, and environmental aspects, leading to a new connotation in the use and occupation of land. This new scenario impacts the local energy balance, creating what is called an “urban heat island”. This study aims to investigate the occurrence of urban heat islands in Recife city, the capital of Pernambuco, Brazil, based on the processing of biophysical parameters, the classification of land use and occupation, and surface temperature. The orbital images of the study region were obtained and processed using the Google Earth Engine cloud processing platform from 2013 to 2021. The results showed an increase in areas with greater urban density and a reduction in areas with vegetation. It was realized that in regions with greater urban density, the surface temperature observed was up to 5.20°C higher than in the area with vegetation.

An in-depth multiscale analysis of farmland abandonment and recultivation dynamics in the Yangtze River Delta, China: A landscape ecology perspective empowered by google earth engine

Farmland abandonment represents the extreme utilization of marginal land and results from the interplay between humans and the environment. In the Yangtze River Delta region of China, a significant economic hub, understanding the landscape patterns and driving mechanisms of farmland abandonment and recultivation land is crucial for regional sustainable development. This study aims to map the extent of farmland abandonment in 2020 and recultivation land in 2021 across the Yangtze River Delta, analyze the landscape patterns of farmland abandonment and recultivation land on multiple scales, and explore their driving mechanisms. Utilizing multi-source data and the Land Use Trajectory Change Method on the Google Earth Engine platform, we classified land use and identified farmland abandonment, fallow land, active farmland, and recultivation land. Spatial statistical analysis was conducted to investigate the distribution and patterns of farmland abandonment and recultivation land at Yangtze River Delta, provincial, and municipal scales. Additionally, a stepwise multiple linear regression model was employed to dissect the main driving forces of farmland abandonment and recultivation land. Results revealed that farmland abandonment in the Yangtze River Delta region exceeded an abandonment rate of 10%, with a reclamation rate in the following year of less than 30%. The spatial distribution of farmland abandonment and recultivation land varied significantly across different scales. On the Yangtze River Delta scale, farmland abandonment was positively influenced by altitude, distance to rivers, and temperature, while recultivation land was positively correlated with night light intensity. At the provincial and municipal scales, the driving forces exhibited scaling effects, with different factors becoming significant. Our findings contribute to a deeper understanding of the complexity and diversity of farmland abandonment in the Yangtze River Delta region. The results provide a scientific basis for formulating land use policies, promoting sustainable agricultural development, and ensuring ecological balance. By uncovering the land use status and ecosystem balance influenced by human-environment interactions, this study offers insights into achieving a harmonious coexistence between economy, society, and ecology in the Yangtze River Delta region.

Effects of Peromyscus spp. (Rodentia: Cricetidae) presence, land use, and ecotone on Ixodes scapularis (Acari: Ixodidae) ecology in an emergent area for tick-borne disease.

As the range of Ixodes scapularis Say expands, host abundance and land use can play important roles in regions where ticks and their associated pathogens are emerging. Small mammal hosts serve as reservoirs of tick-borne pathogens, with Peromyscus leucopus Rafinesque often considered a primary reservoir. A sympatric species Peromyscus maniculatus Wagner is also a competent reservoir and is notoriously difficult to differentiate from P. leucopus. Anthropogenic land use can alter host and habitat availability, potentially changing tick exposure risk. We tested the hypotheses that tick infestation and pathogen prevalence differ between the two Peromyscus spp. and that host-seeking I. scapularis density and pathogen prevalence differ across land use and ecotone gradients. We live trapped small mammals and collected ticks across 3 land-use classifications and ecotones in Maine, an emergent area for tick-borne disease. We tested each small mammal and tick sample for Borrelia burgdorferi, Anaplasma phagocytophilum, and Babesia microti. While both Peromyscus spp. serve as hosts for immature ticks, P. leucopus exhibited a higher tick infestation frequency and intensity. We did not detect any significant difference in pathogen infection prevalence between the two species. The density of I. scapularis nymphs and the density of infected nymphs did not differ significantly between land-use types, though did differ across ecotones. We also noted a significant north/south gradient, with higher tick densities and pathogen prevalence at the southern end of the study area. Our study highlights the potential variability in tick density and pathogen prevalence across fine spatial scales within an emerging region for tick-borne disease.

Assessing Chile's national expansion of urban and artificial coverages between 2000 and 2022

Abstract. This study investigates the national expansion of urban and artificial coverages in Chile between 2000 and 2022 using remote sensing techniques. The research employed Google Earth Engine and Landsat imagery to classify land use and land cover (LULC) changes. By analyzing annual cloud-free composites and employing random forest algorithms, the study produced detailed LULC maps, focusing on the 'infrastructure' class, which includes urban areas and major roads. Results indicate a significant 33% increase in infrastructure coverage, growing from approximately 380,000 hectares in 2000 to 510,000 hectares in 2022. This expansion was predominantly observed in seven regions, which accounted for 68% of the total infrastructure area and 83% of the national increase. A notable correlation (0.6) between urban growth and population growth was identified, suggesting that urban expansion is largely driven by demographic changes. However, regions with higher population growth exhibited more vertical urban development. The study highlights the complex interplay between urbanization, population dynamics, and regional planning, emphasizing the need for sustainable development strategies to manage urban growth effectively. Validation efforts showed high classification accuracies, with infrastructure class accuracies averaging 82% for the User and 87% for the Producer across the evaluated years.

A quantitative classification method of land uses and assessment of per-and poly-fluoroalkyl substances (PFAS) occurrence in freshwater environments

We developed a quantitative method for classifying land uses for PFAS-related investigations in freshwater environments and determined PFAS ambient concentrations associated with specific land-use classes. Furthermore, our study presents a comprehensive assessment of the ambient occurrence and risks of PFAS mixtures beyond the usually studied PFOS-PFOA mixtures. Eighty-five inland (freshwater only) sites were sampled for water, sediment, and riparian soil in Victoria, south-east Australia, and analyzed for 33 PFAS. PFAS were detected in 91% of water samples, 34% of sediment samples, and 28% of riparian soil samples. Four land-use classes were defined: remote, agricultural, mixed, and urban. In the remote land-use class, only PFOS was detected at a low ambient concentration (0.0002 μg/L) in one water sample. Short-chain PFCA were frequently detected in the agricultural and mixed water samples. PFBA had the highest median ambient concentration in both land uses (ca. 0.01 μg/L), contributing to both ΣPFAS (40%) and ΣPFCA (50%) concentrations. In the urban land-use class, several congeners (PFBA, PFPeA, PFHxA, PFOA, PFHxS, and PFOS) had median ambient concentrations at or close to 0.01 μg/L and contributed similarly to ΣPFAS (10–20%). Elevated risk to the aquatic environment was found only for PFOS in two mixed and eight urban sites. This pattern was consistent with the finding for PFAS mixtures, where the elevated risk was driven by PFOS at those same sites. Our study provides critical information about environmentally relevant ambient concentrations and PFAS mixtures. This information, together with the land-use classification approach presented herein, can be used as reference levels for several critical purposes, including identifying PFAS-contaminated sites, informing land use planning and development decisions, setting standards and guidelines, and tracking changes over time.

Mapping Urban Transformation: The Random Forest Algorithm to Monitor Land Use and Land Cover Change in Bandar Lampung City

Bandar Lampung City has substantially altered its land cover due to rapid urbanization in the past decade. Landsat 8 OLI is suitable for conducting land cover change research and offers current and precise data on the present land cover. This research aimed to monitor and analyze the changes in seven categories of land use and land cover (LULC): forest, agricultural land, rice field, settlement, water body, bare land and industrial area. The land use and land cover (LULC) in Bandar Lampung City were analyzed using Landsat 8 OLI satellite images from 2013 to 2023. The Random Forest Algorithm was employed for this analysis. The LULC model assessment was carried out with a confusion matrix, resulting in almost perfect agreement for the 2013 and 2023 LULC models. The LULC classes showed an area growth in settlement of 5,526.25 ha (29.12%) and agricultural land of 1,071.63 ha (5.30%) but opposite with forest class that experienced significant area loss that reached 2,012.35 ha (-26.02%) and waterbody and industrial area 285.64 (-6.15%) and 167.67 ha (-4.04%), respectively. The findings reveal significant shifts in forest and agricultural land, highlighting the region’s rapid urbanization and deforestation patterns. These changes have practical implications for environmental management and urban planning, suggesting the need for sustainable LULC policies to prevent the impacts of rapid LULC transformations on ecosystem services and local communities. Keywords: Bandar Lampung, K-nearest neighbors, land use and land cover change, QGIS 3.20, random forest algorithm

A Swin Transformer-based method for Classification of Land Use and Land Cover Images

A Swin Transformer-based method for Classification of Land Use and Land Cover Images

Selection of priority watershed for water environment management.

As part of the National Water Management Basic Plan, this study conducted research to identify priority management watersheds in the Yeongsan River basin to respond to changes in water environmental conditions and improve water quality. Analysis of water quality over the past decade revealed that points located in the middle and lower of the Yeongsan River exceeded the target water quality standards. As based on the results, pollution sources and loads indicated that the W-1 watershed, classified as urban areas, exhibited high levels in residential, industrial, and urban landuse characteristics, whereas the W-6 watershed, classified as rural areas, showed high levels in livestock farming, aquaculture, and agricultural landuse (wet and dry filed) categories. To understand the impact of point source (PS) and non-point source (NPS) pollution within the watershed, load duration curve (LDC) analysis was conducted, indicating that downstream segments of all flow ranges exceeded the target water quality standards, necessitating management of both PS and NPS. Multivariate log-linear analysis also confirmed the influence of PS and NPS, suggesting that watershed management should concurrently address both types of pollution. Based on the results, priority management watershed rankings were derived through the calculation of standard and integrated indicators, with the analysis indicating the following order: W-1 > W-6 > W-3 > W-4 > W-2 > W-5 > W-7 > W-8. PRACTITIONER POINTS: Priority management watersheds that urgently need water environment management can be identified. The priority management watershed rankings were derived through the calculation of integrated indicators data on BOD, TP concentration, and loads. Serve as a guide for future diagnostic assessments of pollution sources and the development of effective management strategies. Anticipated to significantly contribute to the establishment of robust water quality management practices in the basin.

A depth-based land-use semantic extraction method for landscape images

Integrated aerial and ground-based observations are essential for rapid land-use classification in modern land surveys, requiring efficient analysis of large volumes of landscape images. These images often contain background noise that impedes classification accuracy and exhibit spatial compression of the main scene, which causes semantic spatial distortion as depth increases. To address these challenges, this paper proposes a depth-based land-use semantic extraction (DLSE) method that effectively reduces background noise and corrects spatial distortions. The DLSE method follows three main steps: (1) depth estimation per pixel using a multi-resolution neural network to delineate the main scene range, filtering semantic noise; (2) conversion of perspective projection to orthographic projection per pixel to correct spatial distortion; and (3) improved land-use semantic extraction through MobileViT-enhanced feature extraction in SegNet. Experimental results demonstrate that DLSE achieves a 96.84% accuracy with more detailed outputs and operates at 23 fps, positioning it as an efficient tool for automated land surveys and land-use decision-making.

The impact of landscape structure on pesticide exposure to honey bees

Pesticides may have serious negative impacts on bee populations. The pesticide exposure of bees could depend on the surrounding landscapes in which they forage. In this study, we assess pesticide exposure across various land-use categories, while targeting the Japanese honey bee, Apis cerana japonica, a native subspecies of the eastern honey bee. In a project involving public participation, we measured the concentrations of major pesticides in honey and beeswax collected from 175 Japanese honey bee colonies across Japan and quantitatively analyzed the relationships between pesticide presence/absence or pesticide concentration and land-use categories around the colonies. Our findings revealed that the surrounding environment in which bees live strongly influences pesticide residues in beehive materials, whether the pesticides are systemic or not, with a clear trend for each land-use category. Agricultural lands, particularly paddy fields and orchards, and urban areas resulted in higher pesticide exposure, whereas forests presented a lower risk of exposure. To effectively control pesticide exposure levels in bees, it is essential to understand pesticide usage patterns and to develop appropriate regulatory systems in non-agricultural lands, similar to those in agricultural lands.

Operational Google-Earth-Engine Workflow to Monitor Irrigated Areas in a Semi-Arid Climate

Abstract. Sustainable water resources management relies on advanced hydrological models calibrated from long-term satellite observations of water cycles. Monitoring water resources from Earth-observing satellites is enabled by cloud computing environments like Google Earth Engine (GEE) that support easy processing and analysis of archived data. While there are different satellite-based indicators of water resources availability, this paper focuses on mapping irrigated areas for each summer harvest season. The paper presents an automated workflow to extract yearly irrigated areas from imagery made public by Landsat and Sentinel-2. This method uses a normalised difference vegetation index (NDVI) to identify fields that exhibit higher vegetation greenness than their surroundings and are potentially being irrigated. As a first step, Google Earth Engine was used to create a seasonal maximum NDVI composite on which a grid-based thresholding algorithm was applied to identify irrigated areas in different parts of a catchment. The irrigated areas were then refined using morphological image processing and a quality-control step was conducted with ancillary datasets such as the most recent landuse classification, evapotranspiration data and crop phenology information. Finally, real-world use cases are presented to demonstrate the ability of satellite remote sensing to provide critical information on irrigation practices over the last 4 decades at the catchment scale.

Analysis of the Biennial Productivity of Arabica Coffee with Google Earth Engine in the Northeast Region of São Paulo, Brazil

Numerous challenges are associated with the classification of satellite images of coffee plantations. The spectral similarity with other types of land use, variations in altitude, topography, production system (shaded and sun), and the change in spectral signature throughout the phenological cycle are examples that affect the process. This research investigates the influence of biennial Arabica coffee productivity on the accuracy of Landsat-8 image classification. The Google Earth Engine (GEE) platform and the Random Forest algorithm were used to process the annual and biennial mosaics of the Média Mogiana Region, São Paulo (Brazil), from 2017 to 2023. The parameters evaluated were the general hits of the seven classes of land use and coffee errors of commission and omission. It was found that the seasonality of the plant and its development phases were fundamental in the quality of coffee classification. The use of biennial mosaics, with Landsat-8 images, Brightness, Greenness, Wetness, SRTM data (elevation, aspect, slope), and LST data (Land Surface Temperature) also contributed to improving the process, generating a classification accuracy of 88.8% and reducing coffee omission errors to 22%.

Toxic metal accumulation, health risk, and distribution in road dust from the urban traffic-intensive environment.

Owing to increasing levels of potentially toxic metals in road dust, air pollutants suspended in the air, pose significant health risks due to rapid, unplanned urbanization and industrialization. This study investigated the pollution status and health risks of trace metals (i.e., Cr, Cd, Ni, Cu, and Pb) in road dust collected from 16 locations across six land-use categories in Eskişehir, Türkiye, including residential, roadside, traffic, tram stations, and car industrial areas. The analysis of trace metals revealed distinct types of urban pollution based on these functional areas. In areas with heavy traffic, high concentrations of the elements, especially Zn, Cr, and Ni, would indicate significant toxic metal pollution. The overall contamination was evaluated using three indices: enrichment factor (EF 0.45-65.75), geo-accumulation index (Igeo - 2.50-4.18), and pollution index (PI 0.27-27.22). Human health risks of potentially toxic trace metals in urban road dust were evaluated for children and adult groups based on hazardous index (HI) and total cancer risk (TCR). The health risk assessments revealed that children (mean HIchildren 8.62E - 01; TCRchildren 6.99E + 04) are more vulnerable to toxic metal exposure than adults (mean HIadults 1.01E - 01; TCRadults 3.01E + 04), with ingestion being the primary exposure route over dermal contact and inhalation. In conclusion, we have captured the interaction between road dust and health risks, especially for children.

DINÁMICA Y VULNERABILIDAD ECOLÓGICA DE LA RESERVA ESTATAL SIERRA DEL TENTZO, MÉXICO

&lt;p&gt;&lt;strong&gt;Background:&lt;/strong&gt; Knowledge and evaluation of ecological changes in Protected Natural Areas is important for their planning and management. The use of tools such as land use change prediction models and satellite image analysis are low-cost and high-precision alternatives that can contribute to this purpose. &lt;strong&gt;Objective:&lt;/strong&gt; Estimate the trend of land use change and vulnerability of the ecosystems of the Sierra del Tentzo State Reserve (REST), Mexico. &lt;strong&gt;Methodology:&lt;/strong&gt; The REST sites with the highest probability of change in their ecosystems were identified according to phases of the adaptive cycles of the Panarchy theory; the use of Landsat images to classify land use and vegetation types, and the identification of areas of greatest vulnerability with a Markov chain model. &lt;strong&gt;Results:&lt;/strong&gt; The trend of change from a state of conservation to a state of growth predominates in the reserve, which indicates a deterioration of the ecosystems with primary vegetation that are being transformed into grasslands and crop areas. While, in the future projection, the areas with greater ecological vulnerability are grouped in a pattern associated with human settlements in population centers. &lt;strong&gt;Implications:&lt;/strong&gt; The study was on a regional scale, so changes and vulnerability at the local level were not explored. &lt;strong&gt;Conclusion:&lt;/strong&gt; In the Sierra del Tentzo State Reserve there is a process of ecosystem degradation and some areas, particularly those most susceptible to human activities, are more vulnerable to this degradation. These areas should be considered in the reserve management program as priority attention.&lt;/p&gt;

Identification of Residential and Commercial Area using Convolutional Neural Network

Abstract— Image classification of land use using aerial scene classification has become increasingly common around the world. Utilizing the power of Convolutional Neural Networks (CNNs), identification of various city township areas using satellite imagery has become more efficient compared to the previous manual labeling. The objective of this research is to build a convolutional neural network model for residential and commercial area identification. In the research, we also adopted Inception V3 and VGG16 to develop two transfer learning models for the identification system. The Inception V3-based model achieved the highest overall accuracy value of 100%, showing its effectiveness in accurate residential and commercial area identification. The proposed CNN model achieved an accuracy of 99%, while the VGG-16 model with all configurations being frozen achieved 99% accuracy.

Comparative analysis of the performance of selected machine learning algorithms depending on the size of the training sample

Abstract The article presents an analysis of the effectiveness of selected machine learning methods: Random Forest (RF), Extreme Gradient Boosting (XGB), and Support Vector Machine (SVM) in the classification of land use and cover in satellite images. Several variants of each algorithm were tested, adopting different parameters typical for each of them. Each variant was classified multiple (20) times, using training samples of different sizes: from 100 pixels to 200,000 pixels. The tests were conducted independently on 3 Sentinel-2 satellite images, identifying 5 basic land cover classes: built-up areas, soil, forest, water, and low vegetation. Typical metrics were used for the accuracy assessment: Cohen’s kappa coefficient, overall accuracy (for whole images), as well as F-1 score, precision, and recall (for individual classes). The results obtained for different images were consistent and clearly indicated an increase in classification accuracy with the increase in the size of the training sample. They also showed that among the tested algorithms, the XGB algorithm is the most sensitive to the size of the training sample, while the least sensitive is SVM, which achieved relatively good results even when using training samples of the smallest sizes. At the same time, it was pointed out that while in the case of RF and XGB algorithms the differences between the tested variants were slight, the effectiveness of SVM was very much dependent on the gamma parameter – with too high values of this parameter, the model showed a tendency to overfit, which did not allow for satisfactory results.

Study on Urban Land Simulation under the Perspective of Local Climate Zoning—A Case Study of Guiyang City

The examination of land-use change simulations across a range of scenarios represents a pivotal research avenue for the advancement of sustainable development analysis. Nevertheless, the extant research merely categorises all building land in a land-use classification into a single category, which is unable to provide a detailed analysis of the dynamic internal spatial form of the city. This paper analyses 17 LCZ land-use types in Guiyang City in 2013 and 2022, and reclassifies them into 7 RLCZ land-use types based on the height of urban building sites. It also proposes three possible scenarios of BAU, WLC, and SPC in 2040 and simulates their land-use changes using the PLUS model. The results demonstrate that (1) the size of low-rise buildings in Guiyang has declined significantly over the past decade; (2) built-up land within cities is significantly affected by drivers such as night-time lighting, topography, elevation, and roads; (3) the SPC scenario emphasises a development pattern of land intensification and a focus on high density in urban built space. It also protects the stability of the ecosystem. The scenario can provide informative suggestions for spatial pattern changes in rapidly developing cities such as Guiyang.

Information-Theoretic Modeling of Categorical Spatiotemporal GIS Data.

An information-theoretic data mining method is employed to analyze categorical spatiotemporal Geographic Information System land use data. Reconstructability Analysis (RA) is a maximum-entropy-based data modeling methodology that works exclusively with discrete data such as those in the National Land Cover Database (NLCD). The NLCD is organized into a spatial (raster) grid and data are available in a consistent format for every five years from 2001 to 2021. An NLCD tool reports how much change occurred for each category of land use; for the study area examined, the most dynamic class is Evergreen Forest (EFO), so the presence or absence of EFO in 2021 was chosen as the dependent variable that our data modeling attempts to predict. RA predicts the outcome with approximately 80% accuracy using a sparse set of cells from a spacetime data cube consisting of neighboring lagged-time cells. When the predicting cells are all Shrubs and Grasses, there is a high probability for a 2021 state of EFO, while when the predicting cells are all EFO, there is a high probability that the 2021 state will not be EFO. These findings are interpreted as detecting forest clear-cut cycles that show up in the data and explain why this class is so dynamic. This study introduces a new approach to analyzing GIS categorical data and expands the range of applications that this entropy-based methodology can successfully model.