Search Results (264)

Accurate estimation of Total Phosphorus, referred to as “Phosphorus, Total” (PPUT; µg/L) in the sourced monitoring data, is essential for understanding eutrophication dynamics and guiding water-quality management in inland lakes. However, lake-wide PPUT mapping at high resolution is challenging to achieve using conventional in-situ sampling, and nearshore gradients are often poorly resolved by medium- or low-resolution satellite sensors. This study exploits multi-generation PlanetScope imagery (Dove Classic, Dove-R, and SuperDove; 3–5 m, near-daily revisit) to develop a hybrid AI framework for PPUT retrieval in Lake Simcoe, Ontario, Canada. PlanetScope surface reflectance, short-term meteorological descriptors (3 to 7-day aggregates of air temperature, wind speed, precipitation, and sea-level pressure), and in-situ Secchi depth (SSD) were used to train five ensemble-learning models (HistGradientBoosting, CatBoost, RandomForest, ExtraTrees, and GradientBoosting) across eight feature-group regimes that progressively extend from bands-only, to combinations with spectral indices and day-of-year (DOY), and finally to SSD-inclusive full-feature configurations. The inclusion of SSD led to a strong and systematic performance gain, with mean R² increasing from about 0.67 (SSD-free) to 0.94 (SSD-aware), confirming that vertically integrated optical clarity is the dominant constraint on PPUT retrieval and cannot be reconstructed from surface reflectance alone. To enable scalable SSD-free monitoring, a knowledge-distillation strategy was implemented in which an SSD-aware teacher transfers its learned representation to a student using only satellite and meteorological inputs. The optimal student model, based on a compact subset of 40 predictors, achieved R² = 0.83, RMSE = 9.82 µg/L, and MAE = 5.41 µg/L, retaining approximately 88% of the teacher’s explanatory power. Application of the student model to PlanetScope scenes from 2020 to 2025 produces meter-scale PPUT maps; a 26 July 2024 case study shows that >97% of the lake surface remains below 10 µg/L, while rare (<1%) but coherent hotspots above 20 µg/L align with tributary mouths and narrow channels. The results demonstrate that combining commercial high-resolution imagery with physics-informed feature engineering and knowledge transfer enables scalable and operationally relevant monitoring of lake phosphorus dynamics. These high-resolution PPUT maps enable lake managers to identify nearshore nutrient hotspots, tributary plume structures. In doing so, the proposed framework supports targeted field sampling, early warning for eutrophication events, and more robust, lake-wide nutrient budgeting. Full article

Despite a growing number of Earth Observation satellites, a critical observational gap persists for timely, high-resolution flood mapping, primarily due to infrequent satellite revisits and persistent cloud cover. To address this issue, we propose a novel framework that synergistically fuses complementary data from three public sensor types. Our methodology harmonizes these disparate data sources by using surface water fraction as a common variable and downscaling them with flood susceptibility and topography information. This allows for the integration of sub-daily observations from the Visible Infrared Imaging Radiometer Suite and the Advanced Himawari Imager with the cloud-penetrating capabilities of the Advanced Microwave Scanning Radiometer 2. We evaluated this approach on the February 2022 flood in Brisbane, Australia using an independent ground truth dataset. The framework successfully compensates for the limitations of individual sensors, enabling the consistent generation of detailed, high-resolution flood maps. The proposed method outperformed the flood extent derived from commercial high-resolution optical imagery, scoring 77% higher than the Copernicus Emergency Management Service (CEMS) map in the Critical Success Index. Furthermore, the True Positive Rate was twice as high as the CEMS map, confirming that the proposed method successfully overcame the cloud cover issue. This approach provides valuable, actionable insights into inundation dynamics, particularly when other public data sources are unavailable. Full article

Accurate delineation of inland waterbodies is critical for applications such as hydrological monitoring, disaster response preparedness and response, and environmental management. While optical satellite imagery is hindered by cloud cover or low-light conditions, Synthetic Aperture Radar (SAR) provides consistent surface observations regardless of weather or illumination. This study introduces a deep learning-based ensemble framework for precise inland waterbody detection using high-resolution X-band Capella SAR imagery. To improve the discrimination of water from spectrally similar non-water surfaces (e.g., roads and urban structures), an 8-channel input configuration was developed by incorporating auxiliary geospatial features such as height above nearest drainage (HAND), slope, and land cover classification. Four advanced deep learning segmentation models—Proportional–Integral–Derivative Network (PIDNet), Mask2Former, Swin Transformer, and Kernel Network (K-Net)—were systematically evaluated via cross-validation. Their outputs were combined using a weighted average ensemble strategy. The proposed ensemble model achieved an Intersection over Union (IoU) of 0.9422 and an F1-score of 0.9703 in blind testing, indicating high accuracy. While the ensemble gains over the best single model (IoU: 0.9371) were moderate, the enhanced operational reliability through balanced Precision–Recall performance provides significant practical value for flood and water resource monitoring with high-resolution SAR imagery, particularly under data-constrained commercial satellite platforms. Full article

Protein instability in white wines is mainly caused by pathogenesis-related (PR) proteins that survive winemaking and can form haze in bottle. Because PR-protein synthesis is modulated by vine stress, this study evaluated whether unmanned aerial vehicle (UAV) multispectral imagery and NDVI-based vigor zoning can be used as early predictors of protein instability in commercial Chardonnay and Sauvignon Blanc wines. High-resolution multispectral images were acquired over two seasons (2023–2024) in two vineyards, and three vigor zones (high, medium, low) were delineated from the NDVI at the individual vine scale. A total of 180 georeferenced vines were sampled, and musts were analyzed for thaumatin-like proteins and chitinases via RP-HPLC. Separate microvinifications were carried out for each vigor zone and cultivar, and the resulting wines were evaluated for protein instability (heat test) and bentonite requirements. Low-vigor vines consistently produced musts with higher PR-protein concentrations, greater turbidity after heating, and higher bentonite demand than high-vigor vines, with stronger effects in Sauvignon Blanc. These vigor-dependent patterns were stable across vintages, despite contrasting seasonal conditions. Linear discriminant analysis using NDVI, PR-protein content, turbidity, and bentonite dosage correctly separated vigor classes. Overall, UAV NDVI–based vigor zoning provided a robust, non-destructive tool for identifying vineyard zones with increased risk of protein instability. This approach supports precision enology by enabling site-specific stabilization strategies that reduce overtreatment with bentonite and preserve white wine quality. Full article

Cotton (Gossypium hirsutum L.) is a primary global commercial crop, and accurate monitoring of its growth and yield prediction are essential for optimizing water management. This study integrates leaf area index (LAI) data derived from unmanned aerial system (UAS) imagery into the Decision Support System for Agrotechnology Transfer (DSSAT) model to improve cotton growth simulation and yield estimation. The results show that the normalized difference vegetation index (NDVI) exhibited higher estimation accuracy for the cotton LAI during the squaring stage (R² = 0.56, p < 0.05), whereas the modified triangle vegetation index (MTVI) and enhanced vegetation index (EVI) demonstrated higher and more stable accuracy in the flowering and boll-setting stages (R² = 0.64 and R² = 0.76, p < 0.05). After assimilating LAI data, the optimized DSSAT model accurately represented canopy development and yield variation under different irrigation levels. Compared with the DSSAT, the assimilated model reduced yield prediction error from 40–52% to 3.6–6.3% under 30%, 60%, and 90% irrigation. These findings demonstrate that integrating UAS-derived LAI data with the DSSAT substantially enhances model accuracy and robustness, providing an effective approach for precision irrigation and sustainable cotton management. Full article

The growing density of Earth-orbiting objects demands improved Space Situational Awareness (SSA) to mitigate collision risks and sustain space operations. This study demonstrates a dual-purpose star tracker (ST) for SSA using data from the Resident Space Object Near-space Astrometric Reconnaissance (RSONAR) stratospheric balloon campaign under the 2022 Canadian Space Agency–Centre National d’Études Spatiales (CSA–CNES) STRATOS program. The low-cost optical payload—a wide-field monochromatic imager flown at 36 km altitude—acquired imagery subsequently used for post-processed attitude determination and Resident Space Object (RSO) detection. During stabilized pointing, over 27,000 images yielded sub-pixel astrometry and stable image quality (mean full-width-Half-maximum ≈ 388 arcsec). Photometric calibration to the Tycho-2 catalog achieved 0.37 mag root mean square (RMS) scatter, confirming radiometric uniformity. Apparent angular velocities of $7\times {10}^2$ to $8\times {10}^3$ arcsec ${\mathrm{s}}^{-1}$ corresponded to sunlit low-Earth-orbit (LEO) objects observed at 25°–35° phase angles. Covariance-weighted Mahalanobis correlation with two-line elements (TLEs) achieved sub-arcminute positional agreement. The Proximity Filtering and Tracking (PFT) algorithm identified 22,036 total RSO and 387 total streaks via image stacking. Results confirm that commercial off-the-shelf STs can serve as dual-use SSA payloads, and that stratospheric ballooning offers a viable alternative for optical SSA research. Full article

Clarifying the residential space differentiation in urban fringe areas and its influencing factors are crucial for land use planning and sustainable urban development. This study investigates residential space differentiation and its influencing factors in the urban fringe area of Beijing from the perspective of housing rent. Utilizing multi-source data, including housing rent statistics from the China Real Estate Price Platform, remote sensing imagery, and POI big data, we employ the residential dissimilarity index for tenants, geographical detector, and MGWR model to analyze spatial patterns and driving mechanisms. The results show the following: (1) The residential space differentiation in the urban fringe area of Beijing is obvious, showing an “X”-shaped fragmentation pattern, with the northeast and southwest regions forming high differentiation values, while the northwest and southeast regions form low differentiation values. (2) The residential space differentiation in the marginal area shows a strong scale effect, which originates from the historic “collage” development mode of Beijing. (3) The differentiation of residential space in Beijing’s urban fringe area is sensitive to the spatial accessibility of residential areas to other facilities, and is less affected by the spatial proximity, such as the number of facilities. (4) The central potential and traffic potential factors are still the core driving forces shaping the differentiation pattern of residential space in the marginal area; the role of leisure supporting factors has become increasingly prominent, and it has gradually become the key factor strengthening residential space differentiation; and the influence of medical and commercial supporting factors is relatively weak. Full article

Post-industrial landscapes represent one of the most complex challenges for contemporary sustainable land management, as they combine environmental degradation, cultural heritage, and socio-economic restructuring. This study examines five representative post-industrial sites within the Dąbrowa Basin (southern Poland), selected from an initial pool of 20 locations to capture the full diversity of contemporary transformation pathways. The research integrates multi-temporal satellite imagery (1999–2025), historical maps (1936, 1965), extensive field surveys, and a systematic review of literature and regional press to assess environmental, functional, and cultural dimensions of landscape change. The results reveal four distinct transformation trajectories: hydrological reclamation, heritage-led revitalization, passive ecological succession, economic redevelopment, and one additional case of unmanaged degradation. Hydrological and cultural revitalization produced the most sustainable outcomes, characterized by high environmental stability, strong public accessibility, and preserved industrial identity. Natural succession created ecologically valuable but functionally limited spaces, while commercial redevelopment ensured economic stability at the cost of industrial memory. Sites lacking coordinated revitalization remain unsafe, inaccessible, and environmentally unstable. The study demonstrates that post-industrial transformation is strongly influenced by municipal engagement, land ownership, historical legacy, and the interaction between natural and engineered processes. These findings contribute to the international discourse on sustainable post-industrial redevelopment and highlight the need for integrated, cross-sectoral strategies supporting multifunctional, resilient landscapes in Central Europe. Full article

Aquaculture monitoring increasingly relies on computer vision to evaluate fish behavior and welfare under farming conditions. This dataset was collected in a commercial recirculating aquaculture system (RAS) integrated with hydroponics in Queretaro, Mexico, to support the development of robust visual models for Nile tilapia (Oreochromis niloticus). More than ten hours of underwater recordings were curated into 31 clips of 30 s each, a duration selected to balance representativeness of fish activity with a manageable size for annotation and training. Videos were captured using commercial action cameras at multiple resolutions (1920 × 1080 to 5312 × 4648 px), frame rates (24–60 fps), depths, and lighting configurations, reproducing real-world challenges such as turbidity, suspended solids, and variable illumination. For each recording, physicochemical parameters were measured, including temperature, pH, dissolved oxygen and turbidity, and are provided in a structured CSV file. In addition to the raw videos, the dataset includes 3520 extracted frames annotated using a polygon-based JSON format, enabling direct use for training object detection and behavior recognition models. This dual resource of unprocessed clips and annotated images enhances reproducibility, benchmarking, and comparative studies. By combining synchronized environmental data with annotated underwater imagery, the dataset contributes a non-invasive and versatile resource for advancing aquaculture monitoring through computer vision. Full article

Urban Heat Islands (UHIs) are urbanized areas that experience significantly higher temperatures than their surroundings, contributing to thermal discomfort, increased air pollution, heightened public health risks, and greater energy demand. In Bhutan, where urban expansion is concentrated within narrow valley systems, the formation and intensification of UHIs present emerging challenges for climate-resilient urban development. Thimphu, in particular, is experiencing rapid urban growth and densification, making it highly susceptible to UHI effects. Therefore, the aim of this study was to evaluate and simulate UHI conditions for Thimphu Thromde. We carried out the simulation using a GIS, multi-temporal Landsat imagery, and an Artificial Neural Network model. Land use and land cover classes were mapped through supervised classification in the GIS, and surface temperatures associated with each class were derived from thermal bands of Landsat data. These temperature values were normalized to identify existing UHI patterns. An Artificial Neural Network (ANN) model was then applied to simulate future UHI distribution under expected land use change scenarios. The results indicate that, by 2031, built-up areas in Thimphu Thromde are expected to increase to 72.82%, while vegetation cover is projected to decline to 23.52%. Correspondingly, both UHI and extreme UHI zones are projected to expand, accounting for approximately 14.26% and 6.08% of the total area, respectively. Existing hotspots, particularly dense residential areas, commercial centers, and major institutional or public spaces, are expected to intensify. In addition, new UHI zones are likely to develop along the urban fringe, where expansion is occurring around the current hotspots. These study findings will be useful for Thimphu Thromde authorities in deciding the mitigation measures and pre-emptive strategies required to reduce UHI effects. Full article

Historic districts, as important spatial units that carry urban cultural memory and everyday social life, play a crucial role in shaping residents’ spatial identity, emotional attachment, and perceptual experience. Although quantitative research on built environments and perception has advanced considerably in recent years, the mechanisms through which perception is formed in historic districts, particularly the nonlinear threshold effects and perceptual trade-off patterns that arise under conditions of high-density and mixed land use, remain insufficiently examined. To address this gap, this study develops an analytical framework that integrates spatial attributes with multidimensional subjective perceptions. Focusing on six historic districts in central Shanghai, the study combines micro-scale environmental indicators extracted from street-view imagery, POI data, and public perceptual evaluations and employs an XGBoost model to identify the nonlinear response patterns, threshold effects, and perceptual trade-offs across seven perceptual dimensions. The results show that natural elements such as visual greenery and sky openness generate significant threshold-based enhancement effects, and once reaching a certain level of visibility, they substantially increase positive perceptions including beauty, safety, and cleanliness. By contrast, commercial and traffic-related facilities exhibit dual and competing perceptual influences. Moderate densities enhance liveliness, whereas high concentrations tend to induce perceptual fatigue and intensify negative emotional responses. Overall, perceptual quality in historic districts does not arise from linear accumulation but is shaped by dynamic perceptual trade-offs among natural features, functional elements, and cultural symbolism. Overall, the study reveals the coupling mechanism between spatial renewal and perceptual experience amid the pressures of urban modernization. It also demonstrates that increasing visible greenery (e.g., planting street trees, incorporating micro-green spaces, improving façade greening), enhancing street openness (e.g., optimizing view corridors, reducing visual obstruction, implementing moderate setback adjustments), guiding a moderate mix and spatial distribution of commercial and service functions, and strengthening the perceptibility of cultural landscape elements (e.g., façade restoration, streetscape coordination, and improved signage systems) are concrete and effective planning and design actions for improving landscape quality and enhancing the experiential quality of historic districts. Full article

Affordable optical data from Unmanned Aerial Vehicles (UAVs) coupled with process-based models could constitute an integrative platform to map complex spatio-temporal patterns of nitrate leaching and reduce uncertainties in tightening the nitrogen (N) cycle of silvopastoral systems. This study uses field data from a commercial farm in Denmark with lactating sows housed in paddocks with pastures flanking a central zone of poplars, either pruned (P) or unpruned (tall, T), each with resources (feed and hut) on the same (S) or opposite side (O) of the tree zone. The poplar leaf area index derived from canopy cover using a computer vision approach on true-colour UAV imagery was fed to a process-based model alongside soil data and geostatistical analyses to derive the soil water balance across the paddocks and explicitly map the variation in soil nitrate leaching. The results showed clear patterns not seen before of nitrate leaching hotspots shifting from high values in the pre-study year without animals to diluted lower values in the main study year involving the pigs. The results also showed a seasonal and spatial variation of 7 to 860 kg N ha⁻¹ year⁻¹, a wide leaching range otherwise difficult to capture, by employing only a process-based model using mean effective parameters. Nitrate leaching was in the order PO > PS > TO > TS. The N cycle was tightened with T regardless of S/O. The approach could be improved with more machine learning-aided process-based modelling to operationally monitor complex silvopastoral systems to alleviate nitrate leaching in outdoor pig systems. Full article

Digital agriculture is increasingly important for plant-level analysis, enabling detailed assessments of growth, nutrition and overall condition. Multispectral point clouds are promising due to the integration of geometric and radiometric information. Although RGB point clouds can be generated with commercial terrestrial scanners, multi-band multispectral point clouds are rarely obtained directly. Most existing methods are limited to aerial platforms, restricting close-range monitoring and plant-level studies. Efficient workflows for generating multispectral point clouds from terrestrial sensors, while ensuring geometric accuracy and computational efficiency, are still lacking. Here, we propose a workflow combining photogrammetric and computer vision techniques to generate high-resolution multispectral point clouds by integrating terrestrial light detection and ranging (LiDAR) and multispectral imagery. Bundle adjustment estimates the camera’s position and orientation relative to the LiDAR reference system. A frustum-based culling algorithm reduces the computational cost by selecting only relevant points, and an occlusion removal algorithm assigns spectral attributes only to visible points. The results showed that colourisation is effective when bundle adjustment uses an adequate number of well-distributed ground control points. The generated multispectral point clouds achieved high geometric consistency between overlapping views, with displacements varying from 0 to 9 mm, demonstrating stable alignment across perspectives. Despite some limitations due to wind during acquisition, the workflow enables the generation of high-resolution multispectral point clouds of vegetation. Full article

Unmanned Aerial Vehicles (UAVs) equipped with low-cost RGB and near-infrared (NIR) cameras represent efficient and scalable technology for monitoring sugarcane crops. This study evaluated the potential of UAV imagery and three-dimensional crop modeling to estimate sugarcane height and yield under different nitrogen fertilization levels. The experiment comprised 28 plots subjected to four nitrogen rates, and images were processed using a Structure from Motion (SfM) algorithm to generate Digital Surface Models (DSMs). Crop Height Models (CHMs) were obtained by subtracting DSMs from Digital Terrain Models (DTMs). The most accurate CHM was derived from the combination of the reference DTM and the NIR-based DSM (R² = 0.957; RMSE = 0.162 m), while the strongest correlation between height and yield was observed at 200 days after cutting (R² = 0.725; RMSE = 4.85 t ha⁻¹). The NIR-modified sensor, developed at a total cost of USD 61.59, demonstrated performance comparable with commercial systems that are up to two hundred times more expensive. These results demonstrate that the proposed low-cost NIR sensor provides accurate, reliable, and accessible data for three-dimensional modeling of sugarcane. Full article

Accurate pasture biomass (PB) estimation is critical for tactical grazing management, yet traditional satellite-derived vegetation indices such as Normalised Difference Vegetation Index (NDVI) saturate when canopy density exceeds about 3 t DM ha⁻¹. This limits predictive accuracy because the spectral signal plateaus under dense vegetation, masking further biomass increases. To address this limitation, this study integrated multiple data sources to improve PB estimation in dairy systems. The dataset combined Sentinel-2 spectral bands, rising plate-meter (RPM) PB measurements, daily weather data, and paddock management features. A total of 3161 paired RPM–satellite observations were collected from 80 paddocks across 16 New South Wales dairy farms between November 2021 and July 2024. Eight regression algorithms and four predictor configurations were evaluated using robust cross-validation, including an 80:20 farm/paddock-stratified train–test-set split. The XGBoost model using full-band reflectance and concurrent weather data achieved strong baseline performance (R² = 0.63; MAE = 243 kg DM ha⁻¹) on non-interpolated data, outperforming NDVI-based models. To address temporal gaps between field readings and satellite imagery, Multiquadric interpolation was applied to RPM data, adding roughly 30% new observations. This enhanced dataset improved test performance to R² = 0.70 and MAE = 216 kg DM ha⁻¹, with gains maintained on external validations (R² = 0.41/0.48; MAE = 267/235 kg DM ha⁻¹). A progressive training strategy, which refreshed model parameters with seasonally aligned data, further reduced errors by 30% compared to static models and sustained performance even when farms or seasons were excluded. This fortified Sentinel-2 modelling workflow, combining RPM interpolation and progressive calibration, achieved accuracy comparable to the commercial Pasture.io platform (R² = 0.66; MAE = 240 kg DM ha⁻¹) which uses satellite imagery with higher temporal and spatial resolution, demonstrating potential for automated recalibration and near real-time, paddock-level decision support in pasture-based dairy systems. Full article