Search Results (653)

Using LULC change detection analysis, it is possible to identify changes due to urbanization, deforestation, or a natural disaster in an area. As population growth and urbanization increase, real-time solutions for the effects of urbanization on land use are required to assess its implications for food security and livelihood. This study seeks to identify and quantify recent LULC changes in Limbe, Cameroon, and to measure rates of conversion between agricultural, forest, and urban lands between 1986 and 2020 using remote sensing and GIS. Also, there is a deficiency of research employing these data to evaluate the efficiency of LULC satellite data and a lack of awareness by local stakeholders regarding the impact on LULC change. The changes were identified in four classes utilizing maximum supervised classification in ENVI and ArcGIS environments. The classification result reveals that the 2020 image has the highest overall accuracy of 94.6 while the 2002 image has an overall accuracy of 89.2%. The overall gain for agriculture was approximately 4.6 km², urban had an overall gain of nearly 12.7 km², while the overall loss for forest was −16.9 km² during this period. Much of the land area previously occupied by forest is declining as pressures for urban areas and new settlements increase. This study’s findings have significant policy implications for sustainable land use and food security. It also provides a spatial method for monitoring LULC variations that can be used as a framework by stakeholders who are interested in environmentally conscious development and sustainable land use practices. Full article

This study presents an integrated spatiotemporal assessment of drought conditions in the Thung Kula Ronghai region of Northeastern Thailand from 2001 to 2023. Multiple satellite-derived drought indices, including SPI, SPEI, RDI, and AI, together with NDVI anomalies, were used to detect seasonal and long-term drought dynamics affecting rainfed Hom Mali rice production. The results show that dry season droughts now affect up to 17 percent of the region’s agricultural land in some years, while severe drought zones persist across more than 2.5 million hectares over the 20-year period. In the most recent 5 years, approximately 50 percent of cultivated areas experienced moderate to severe drought conditions. The RDI showed the strongest correlation with NDVI anomalies (r = 0.22), indicating its relative value for assessing vegetation response to moisture deficits. The combined index approach delineated high-risk sub-regions, particularly in central Thung Kula Ronghai and lower Surin, where drought frequency and severity have intensified. These findings underscore the region’s increasing exposure to dry-season water stress and highlight the need for site-specific irrigation development and adaptive cropping strategies. The methodological framework demonstrated here provides a practical basis for improving drought monitoring and early warning systems to support the resilience of Thailand’s high-value rice production under changing climate conditions. Full article

Accurate land parcel segmentation in remote sensing imagery is critical for applications such as land use analysis, agricultural monitoring, and urban planning. However, existing methods often underperform in complex scenes due to small-object segmentation challenges, blurred boundaries, and background interference, often influenced by sensor resolution and atmospheric variation. To address these limitations, we propose a dual-stage framework that combines an enhanced YOLOv5s detector with the Segment Anything Model (SAM) to improve segmentation accuracy and robustness. The improved YOLOv5s module integrates Efficient Channel Attention (ECA) and BiFPN to boost feature extraction and small-object recognition, while Soft-NMS is used to reduce missed detections. The SAM module receives bounding-box prompts from YOLOv5s and incorporates morphological refinement and mask stability scoring for improved boundary continuity and mask quality. A composite Focal-Dice loss is applied to mitigate class imbalance. In addition to the publicly available CCF BDCI dataset, we constructed a new WuJiang dataset to evaluate cross-domain performance. Experimental results demonstrate that our method achieves an IoU of 89.8% and a precision of 90.2%, outperforming baseline models and showing strong generalizability across diverse remote sensing conditions. Full article

In this work, we examine the correlation between financial inclusion and the Environmental, Social, and Governance (ESG) factors of sustainable development with the assistance of an exhaustive panel dataset of 103 emerging and developing economies spanning 2011 to 2022. The “Account Age” variable, standing for financial inclusion, is the share of adults owning accounts with formal financial institutions or with the providers of mobile money services, inclusive of both conventional and digital entry points. Methodologically, the article follows an econometric approach with panel data regressions, supplemented by Two-Stage Least Squares (2SLS) with instrumental variables in order to control endogeneity biases. ESG-specific instruments like climate resilience indicators and digital penetration measures are utilized for the purpose of robustness. As a companion approach, the paper follows machine learning techniques, applying a set of algorithms either for regression or for clustering for the purpose of detecting non-linearities and discerning ESG-inclusion typologies for the sample of countries. Results reflect that financial inclusion is, in the Environmental pillar, significantly associated with contemporary sustainability activity such as consumption of green energy, extent of protected area, and value added by agriculture, while reliance on traditional agriculture, measured by land use and value added by agriculture, decreases inclusion. For the Social pillar, expenditure on education, internet, sanitation, and gender equity are prominent inclusion facilitators, while engagement with the informal labor market exhibits a suppressing function. For the Governance pillar, anti-corruption activity and patent filing activity are inclusive, while diminishing regulatory quality, possibly by way of digital governance gaps, has a negative correlation. Policy implications are substantial: the research suggests that development dividends from a multi-dimensional approach can be had through enhancing financial inclusion. Policies that intersect financial access with upgrading the environment, social expenditure, and institutional reconstitution can simultaneously support sustainability targets. These are the most applicable lessons for the policy-makers and development professionals concerned with the attainment of the SDGs, specifically over the regions of the Global South, where the trinity of climate resilience, social fairness, and institutional renovation most significantly manifests. Full article

As a carrier of civilization, cultural heritage reflects the dynamic relationship between humans and their environment within specific historical contexts. During the Ming and Qing Dynasties (1368–1912 CE), the Yangtze River Basin was one of the most prominent regions for economic and cultural activities in ancient China. The cultural heritage of this period was characterized by its dense distribution and continuous evolution. Considering the applicability bias of modern data in historical interpretation, this study selected four characteristic variables: population density, agricultural productivity, technological level, and temperature anomaly. A hierarchical Bayesian model was constructed and change points were detected to quantitatively analyze the driving mechanisms behind the spatiotemporal distribution of cultural heritage. The results show the following: (1) The distribution of cultural heritage exhibited a multipolar trend by the mid-period in both Dynasties, with high-density areas contracting in the later period. (2) Agricultural productivity consistently had a significant positive impact, while population density also had a significant positive impact, except during the mid-Ming period. (3) The cultural calibration terms, which account for observational differences resulting from the interaction between cultural systems and environmental variables, exhibited slight variations. (4) The change point for population density was 364.83 people/km², and for agricultural productivity it was 2.86 × 10⁹ kJ/km². This study confirms that the differentiation in the spatiotemporal distribution of cultural heritage is driven by the synergistic effects of population and resources. This provides a new perspective for researching human–land relations in a cross-cultural context. Full article

The use of Google Earth Engine (GEE), a cloud-based computing platform, in spatio-temporal evaluation studies has increased rapidly in natural sciences such as forestry. In this study, Sentinel-2 satellite imagery and Shuttle Radar Topography Mission (SRTM) elevation data and image classification algorithms based on two machine learning techniques were examined. Random Forest (RF) and Classification and Regression Trees (CART) were used to classify land use and land cover (LULC) in western Oregon (USA). To classify the LULC from the spectral bands of satellite images, a composition consisting of vegetation difference indices NDVI, NDWI, EVI, and BSI, and a digital elevation model (DEM) were used. The study area was selected due to a diversity of land cover types including research forest, botanical gardens, recreation area, and agricultural lands covered with diverse plant species. Five land classes (forest, agriculture, soil, water, and settlement) were delineated for LULC classification testing. Different spatial points (totaling 75, 150, 300, and 2500) were used as training and test data. The most successful model performance was RF, with an accuracy of 98% and a kappa value of 0.97, while the accuracy and kappa values for CART were 95% and 0.94, respectively. The accuracy of the generated LULC maps was evaluated using 500 independent reference points, in addition to the training and testing datasets. Based on this assessment, the RF classifier that included elevation data achieved an overall accuracy of 92% and a kappa coefficient of 0.90. The combination of vegetation difference indices with elevation data was successful in determining the areas where clear-cutting occurred in the forest. Our results present a promising technique for the detection of forests and forest openings, which was helpful in identifying clear-cut sites. In addition, the GEE and RF classifier can help identify and map storm damage, wind damage, insect defoliation, fire, and management activities in forest areas. Full article

Stones in agricultural fields pose a recurring challenge, particularly due to their potential to damage agricultural machinery and disrupt field operations. As modern agriculture moves toward automation and precision farming, efficient stone detection has become a critical concern. This study explores the potential of thermal imaging as a non-invasive method for detecting stones under varying environmental conditions. A series of controlled laboratory experiments and field investigations confirmed the assumption that stones exhibit higher surface temperatures than the surrounding soil, especially when soil moisture is high and air temperatures are cooling rapidly. This temperature difference is attributed to the higher thermal inertia of stones, which allows them to absorb and retain heat longer than soil, as well as to the evaporative cooling from moist soil. These findings demonstrate the viability of thermal cameras as a tool for stone detection in precision farming. Incorporating this technology with GPS mapping enables the generation of accurate location data, facilitating targeted stone removal and reducing equipment damage. This approach aligns with the goals of sustainable agricultural engineering by supporting field automation, minimizing mechanical inefficiencies, and promoting data-driven decisions. Thermal imaging thereby contributes to the evolution of next-generation agricultural systems. Full article

Woody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s National Ecological Observatory Network (NEON) Aerial Observation Platform (AOP). We evaluated the accuracy of land cover classification using NAIP, NEON, and both sources combined. We compared two machine learning models—support vector machines and random forests—implemented in R using large training and evaluation data sets. Our study site, Konza Prairie Biological Station, is a long-term experiment in which variable fire and grazing have created mosaics of herbaceous plants, shrubs, deciduous trees, and evergreen trees (Juniperus virginiana). All models achieved high overall accuracy (>90%), with NEON slightly outperforming NAIP. NAIP underperformed in detecting evergreen trees (52–78% vs. 83–86% accuracy with NEON). NEON models relied on LiDAR-based canopy height data, whereas NAIP relied on multispectral bands. Combining data from both platforms yielded the best results, with 97.7% overall accuracy. Vegetation indices contributed little to model accuracy, including NDVI (normalized digital vegetation index) and EVI (enhanced vegetation index). Both machine learning methods achieved similar accuracy. Our results demonstrate that free, high-resolution imagery and open-source tools can enable accurate, high-resolution, landscape-scale WPE monitoring. Broader adoption of such approaches could substantially improve the monitoring and management of grassland biodiversity, ecosystem function, ecosystem services, and environmental resilience. Full article

This article analyses the impact of urban sprawl on the Valencia Plain aquifer system from 1990 to 2018, focusing on land use and land cover (LULC) changes and their environmental implications. The study applies the Weighted Environmental Index (WEI), a composite indicator based on a functional landscape perspective, to quantify changes in the environmental value over time. The WEI combines CORINE Land Cover and World Settlement Footprint data to enhance spatial resolution and urban land detection. The results show a significant territorial transformation, with urban surfaces expanding by 70% and rainfed agricultural areas declining by over 59%. Consequently, the WEI decreased from 44.80 in 1990 to 40.68 in 2018, representing a 9.2% reduction in the environmental value. These changes threaten the sustainability of key ecosystems such as the Albufera Natural Park and indicate a reduced capacity to deliver ecosystem services, including aquifer recharging, biodiversity conservation, and climate regulation. The findings underscore the need for integrated land-use planning, the protection of peri-urban agricultural areas, and the implementation of nature-based solutions to counteract the environmental impacts of urban growth in Mediterranean metropolitan contexts. Full article

Remotely sensed cropland abandonment monitoring is crucial for providing spatially explicit references for maintaining sustainable agricultural practices and ensuring food security. However, abandoned cropland is commonly detected based on multi-date classification or the dynamics of a single vegetation index, with the interactions between vegetation and soil time series often being neglected, leading to a failure to understand its full-life-cycle succession processes. To fill this gap, we propose a new full-life-cycle modeling framework based on the interactive trajectories of vegetation–soil-related endmembers to identify abandoned and reclaimed cropland in Jinan from 2000 to 2022. In this framework, highly accurate annual fractional vegetation- and soil-related endmember time series are generated for Jinan City for the 2000–2022 period using spectral mixture models. These are then used to integrally reconstruct temporal trajectories for complex scenarios (e.g., abandonment, weed invasion, reclamation, and fallow) using logistic and double-logistic models. The parameters of the optimization model (fitting type, change magnitude, start timing, and change duration) are subsequently integrated to develop a rule-based hierarchical identification scheme for cropland abandonment based on these complex scenarios. After applying this scheme, we observed a significant decline in green vegetation (a slope of −0.40% per year) and an increase in the soil fraction (a rate of 0.53% per year). These pathways are mostly linked to a duration between 8 and 15 years, with the beginning of the change trend around 2010. Finally, the results show that our framework can effectively separate abandoned cropland from reclamation dynamics and other classes with satisfactory precision, as indicated by an overall accuracy of 86.02%. Compared to the traditional yearly land cover-based approach (with an overall accuracy of 77.39%), this algorithm can overcome the propagation of classification errors (with product accuracy from 74.47% to 85.11%), especially in terms of improving the ability to capture changes at finer spatial scales. Furthermore, it also provides a better understanding of the whole abandonment process under the influence of multi-factor interactions in the context of specific climatic backgrounds and human disturbances, thus helping to inform adaptive abandonment management and sustainable agricultural policies. Full article

Understanding a catchment’s geomorphological and erosion processes is essential for sustainable land management and soil conservation. This study investigates the Xynias drained lake catchment in Central Greece using a twofold geospatial modelling approach that combines morphometric analysis with the Revised Universal Soil Loss Equation (RUSLE) to evaluate the area’s landscape evolution, surface drainage features, and soil erosion processes. The catchment exhibits a sixth-order drainage network with a dendritic and imperfect pattern, shaped by historical lacustrine conditions and the carbonate formations. The basin has an elongated shape with steep slopes, high total relief, and a mean hypsometric integral value of 26.3%, indicating the area is at an advanced stage of geomorphic maturity. The drainage density and frequency are medium to high, reflecting the influence of the catchment’s relatively flat terrain and carbonate formations. RUSLE simulations also revealed mean annual soil loss to be 1.16 t ha⁻¹ y⁻¹ from 2002 to 2022, along with increased erosion susceptibility in hilly and mountainous areas dominated by natural vegetation. In comparison to these areas, agricultural regions displayed less erosion risk. These findings demonstrate the effectiveness of combining GIS with remote sensing for detecting erosion-prone areas, informing conservation initiatives. Along with the previously stated results, more substantial conservation efforts and active land management are required to meet the Sustainable Development Goals (SDGs) while considering the monitored land use changes and climate parameters for future catchment management. Full article

Agrobiodiversity decline depends on wider-scale landscape ecological traits. Studying inter-scale patterns helps in understanding context-specific farm-scale biodiversity issues and needs. In this study, we investigated the drivers of agrobiodiversity in four Po Plain sites (northern Italy), an intensively impacted agricultural district. Farm-scale floristic–vegetational indicators reflecting anthropic disturbance (biological forms, chorological traits, and maturity traits) were studied for their relationship with species richness and phytocoenosis α-diversity values. Their correlation with local- and extra-local-scale landscape ecology traits was also studied. Species richness and α-diversity were negatively related to floristic contamination and therophytes; they tended to increase with the Eurasiatic and phanerophyte ratio, suggesting a role of disturbance conditions on diversity values. Extra-local/local scale showed similar relationships with farm-scale floristic–vegetational traits; correlation was higher for local scale. Species richness and α-diversity tended to increase with higher landscape natural components, landscape diversity, biological territorial capacity, and connectivity. These landscape traits also tended to be positively related to Eurasiatic, hemicryptophyte, chamaephyte, phanerophyte, and maturity values, while they were negatively related to adventitious, wide distribution, aliens, and therophytes. Corridors’ ecological quality apparently influenced disturbance-related species amount. Maps representing these inter-scale biodiversity facets are provided (land-use-based support ecosystem service maps integrated with landscape diversity maps). The detected patterns orient context-specific multi-scale biodiversity support. They confirm the theoretical frameworks and should be validated on wider datasets to strengthen their representativeness. Full article

Microplastic contamination in agricultural soils has become a growing concern due to its potential impact on soil quality and ecosystem health. This study aimed to quantify the abundance, particle shape ratio, and examine the vertical distribution of microplastic particles in agricultural soils under different tillage and fertilization regimes. Field experiments were conducted using a split-split-plot design at two sites with differing land-use histories. Treatments included conventional tillage (ST), conservation tillage (deep (CTD) and shallow (CTS)), and varying fertilization practices. Microplastics (MPs) were detected in 100% of soil samples, ranging from 200 to 7400 particles/kg. Statistical analysis showed significantly lower MPs abundance in CTS compared to CTD, while ST showed intermediate levels. Vertical profiles revealed homogeneous distribution in ST and CTS and heterogeneous distribution in CTD, with the highest accumulation in the topsoil. At the Cacinci site, fertilization significantly increased MPs levels (p = 0.021), supporting the hypothesis that inorganic fertilizers contribute to microplastic input as well. This study highlights the need for agricultural practices that minimize both the input and vertical redistribution of MPs in soils, as well as the need for more research on this topic. Full article

Soil salinization hinders plant growth and agricultural production, so breeding salt-tolerant crops is an economical way to exploit saline–alkali soils. However, the specific metabolites and associated pathways involved in salt tolerance of the dandelion have not been clearly elucidated so far. Here, we compared the transcriptome and metabolome responses of 0.7% NaCl-stressed dandelion ‘BINPU2’ (variety A) and ‘TANGHAI’ (variety B). Our results showed that 222 significantly altered metabolites mainly enriched in arginine biosynthesis and pyruvate metabolism according to a KEGG database analysis in variety A, while 147 differential metabolites were predominantly enriched in galactose metabolism and the pentose phosphate pathway in variety B. The transcriptome data indicated that the differentially expressed genes (DEGs) in variety A were linked to secondary metabolite biosynthesis, phenylpropanoid biosynthesis, and photosynthesis–antenna proteins. Additionally, KEGG annotations revealed the DEGs had functions assigned to general function prediction only, post-translation modification, protein turnover, chaperones, and signal transduction mechanisms in variety A. By contrast, the DEGs had functions assigned to variety B as plant–pathogen interactions, phenylpropanoid biosynthesis, and photosynthesis–antenna proteins, including general function prediction, signal transduction mechanisms, and secondary metabolite biosynthesis from the KOG database functional annotation. Furthermore, 181 and 162 transcription factors (TFs) expressed under saline stress conditions specifically were detected between varieties A and B, respectively, representing 36 and 37 TF families. Metabolomics combined with transcriptomics revealed that salt stress induced substantial changes in terpenoid metabolites, ubiquinone biosynthesis metabolites, and pyruvate metabolites, mediated by key enzymes from the glycoside hydrolase family, adenylate esterases family, and P450 cytochrome family at the mRNA and/or metabolite levels. These results may uncover the potential salt-response mechanisms in different dandelion varieties, providing insights for breeding salt-tolerant crop plants suitable for saline–alkali land cultivation. Full article