ABSTRACT This paper presents a methodological framework for estimating the economic value of soil erosion with a practical application to the region of Navarre in Spain. This framework is based on the coordinated use of land use/land cover change (LULCC) models, the revised universal soil loss equation (RUSLE) and replacement cost (RC) models. Previous erosion literature has considered either LULCC and RUSLE type models, overlooking the relevance of economic valuation, or RUSLE and RC type models, ignoring the influence of land use changes. In addition, those that cover economic valuation tend to provide a static valuation. This methodology overcomes these limitations. Based on observed data (2005–2023) and projections (2024–2030), the applied analysis shows the quantification and economic valuation of the impact of land use changes on erosion in Navarre, showing a slight decrease in erosion with a slight increase in erosion valuation. It also produces spatially explicit, dynamic and aggregated results that capture the spatial and temporal heterogeneity of erosion changes in Navarre, varying from −19% to −4.6%, depending on the areas. Moreover, the methodology identifies critical geographical areas where erosion is intense and economically significant. This is particularly valuable as it provides a basis for precise, cost-efficient decision-making.

ABSTRACT The construction of the Padma Bridge, one of the most transformative infrastructure projects in Bangladesh, has triggered significant shifts in regional land use and river morphology. This study harnesses Geographic Information Systems to assess and visualize the temporal and spatial fluctuations in land cover and river morphology surrounding the bridge site. Utilizing satellite imagery and spatial data from 2015 to 2025, the study captures the evolving landscape during the key phases of the bridge’s development. The analysis is structured across four critical observation periods: 2015–2017, 2017–2020, 2020–2022 and 2022–2025, corresponding with major phases of construction and post-construction activity. The results reveal pronounced changes in regional land use, dynamic patterns of erosion and deposition, and notable shifts in the river’s channel morphology within these phases. This temporal breakdown enables a clearer understanding of how each construction phase impacted the surrounding environment.

Element concentration, stable and radioactive isotope data from multiple environmental matrices in two mid-sized Central-European river basins.

Artificial intelligence in urban land use: How regional policy and institutional embeddedness shape the economic efficiency-social legitimacy paradox

Spatio-temporal dynamics and drivers of carbon storage in arid ecosystems: Integrated analysis using InVEST and PLUS models with machine learning.

The expansion of land use in Brazil has caused biodiversity loss and increased human interaction with parasites and pathogens previously restricted to natural ecosystems. Chigger mites are ectoparasites during the larval stage and can cause skin reactions or transmit pathogens to their hosts, including humans. This study aimed to evaluate the diversity of chiggers collected from all five Brazilian biogeographical regions, along with pathogen surveillance. Specimens were subjected to both morphological taxonomy and endogenous control, followed by PCR assays targeting pathogens of the genera Borrelia, Orientia, and Rickettsia. The analyses revealed a high species richness, including two novel records in Brazil: the genus Boshkerria and the species Quadraseta antillarum. Additionally, the genus Quadraseta tested positive for Rickettsia sp., while tests for the other agents were negative. This is the first report of a Rickettsia sp. agent detected in a Quadraseta nymph.

The ongoing land use and land cover changes (LUCC) in Indonesia significantly contribute to climate warming and land degradation. At the same time, competing policy frameworks and land contestation are emerging, particularly regarding degraded land utilization for restoration and commodity production (e.g., timber, bioenergy). However, no study has assessed, at the national scale, the spatial availability of degraded land suitable for timber plantations and the associated carbon implications. Here, we combine a Geographical Information System (GIS)-based land suitability analysis with a dynamic material flow and life cycle assessment (MFA–LCA) framework to evaluate the climate mitigation potential of restoring degraded lands for wood materials and energy in Indonesia. The GIS analysis identifies 0.44–3.60 Mha of degraded land suitable for Acacia, Teak, and Rubber plantations, depending on degraded land definitions and biophysical constraints. The dynamic MFA–LCA model quantifies temporal carbon emissions and sequestration from biospheric and technospheric carbon flows over a 200-year time horizon. Our results show reforesting degraded land exhibits the highest climate benefit, achieving up to −456 Mt CO 2 -eq over 200 years. In comparison, wood plantations yield less mitigation effects, with cumulative emissions ranging from −324 to 1130 Mt CO 2 -eq depending on species and scenarios. Teak offers the greatest long-term carbon sequestration potential (−47 to −324 Mt CO 2 -eq), while fast-growing Acacia supports short-term targets, potentially reducing Indonesia's 2030 Nationally Determined Contributions (NDC) emissions by 5.7%. These findings highlight the need for policies that balance immediate emission reductions with long-term carbon sequestration through spatially targeted degraded land restoration. • Spatially explicit degraded land scenarios to grow wood plantations in Indonesia. • Teak generates lower carbon emissions than Acacia and Rubber in the long-term. • Reforesting restored degraded land exhibits the highest climate benefit. • From a climate perspective, leaving the degraded land idle shall be avoided.

A large-scale, longitudinal study on the epidemiology of Nosema (=Vairimorpha) ceranae and black queen cell virus (BQCV) in Apis mellifera colonies across the Italian agroecosystems.

Distinctive factors driving microplastic distribution in arid zone ecosystems.

Multicriteria environmental vulnerability modeling in hydropower basins of the southern Amazon using the AHP-Delphi approach.

A review of scenario analysis tools for urban green space planning and management.

Burial ability of polycyclic aromatic hydrocarbons in different functional lagoons of China.

Linking land use, pesticide pollution, and bacterioplankton responses to enhance small stream resilience.

Large-scale bryomonitoring of atmospheric trace elements in eastern Canada: Spatial patterns, ecological risk, and environmental drivers.

Prototype of a global model for regulating ecosystem services of inland wetlands.

Optimizing multidimensional land use for flood regulation supply-demand matching: Evidence from a GWRF-SHAP model.

Influence of urban land uses on per- and polyfluoroalkyl substances contamination in urban runoff and the receiving marine environment.

ABSTRACT Geographic Artificial Intelligence supports smart city land management, where modeling complex inter-parcel relationships and extracting effective features remain key challenges for accurate land use classification. Urban areas exhibit diverse relationships including spatial similarity between adjacent blocks, configurational similarity between non-adjacent blocks, and heterogeneous relationships among functional zones. However, existing research lacks comprehensive frameworks to fully describe these complex interaction systems. We propose a graph neural network framework based on higher-order Markov inference that integrates three types of complex relationships for urban land use identification. The framework utilizes social media check-in data to construct a third-order transition matrix, explicitly modeling population mobility’s chain influence mechanism. It employs hypergraph structures to fuse point-of-interest semantic features with remote sensing visual features, capturing similarities among spatially distant but functionally homogeneous areas. Finally, it integrates multi-source feature embeddings and block adjacency relationships through distance-weighted graph attention networks. Empirical studies using real data demonstrate superior performance compared to traditional machine learning methods. Higher-order activity type inference performs optimally in areas with high population density, monofunctional land use, and heterogeneous destination land use patterns for inter-regional travel. This model provides scientific modeling approaches and analytical tools for urban land use planning and smart city management.

Practical guidance about tradeoff choices between accuracy, efficiency and deployment ability in deep convolutional neural network architectures for land use and land cover classification has been largely unavailable because each study evaluates architectures differently. This paper provides a controlled comparative assessment of four popular convolutional neural network architectures for land use and land cover classification visual geometry group19, ResNet50, Inception_Version3 and MobileNet_V2 using the Euro_SAT benchmark which includes 27,000 Sentinel2 red green blue images that have been cut into 10 land uses classes. The convolutional neural network architectures were all trained and evaluated through the same preprocessing, augmentation, data splitting, training procedure and metric as follows: Overall accuracy/F1 macro averaging class by class confusion matrix convergence dynamics efficiency metrics (number of parameters and inference-oriented considerations). The results indicate that modern architectures provide significantly better than older sequential baselines: ResNet50 provided the highest total accuracy (>97%), along with consistent convergence behavior; InceptionV3 improved discrimination for classes with both ambiguous visual appearances and linear structures (river, highway); MobileNetV2 was able to achieve high accuracy (>94%), but had an order of magnitude less number of parameters than the other architectures and is well suited to lower source or real time application scenarios. Finally, this paper maps convolutional neural network outputs into an energy transition decision workflow (Renewable Siting → Corridor Constraints → Monitoring), and demonstrates how land use and land cover layers derived from convolutional neural networks can support net zero resource planning. • Benchmarks 4 CNNs on EuroSAT using identical training and evaluation setup. • ResNet50 achieved highest accuracy (>97%) for LULC classification. • MobileNetV2 reduced parameters by ∼6× while maintaining >94% accuracy. • InceptionV3 improved corridor feature detection (roads, rivers). • Enables decision-grade LULC for CCUS, geothermal, and net-zero planning.

A GAN-based framework for predicting pedestrian road safety based on land use and Points of Interest (POIs).