Search Results (51)

Harmful algal blooms (HABs) are increasing in frequency in the Chesapeake Bay, posing risks to marine ecosystems, water quality, and public health. Chlorophyll-a (Chl-a) is a widely used indicator of algal biomass, and satellite observations such as Sentinel-3 Ocean and Land Color Instrument (OLCI) enable large-scale monitoring of bloom dynamics. However, cloud cover and atmospheric interference frequently introduce missing pixels in daily satellite products, reducing temporal continuity and limiting monitoring reliability. Satellite-derived chlorophyll-a (Chl-a) data exhibit substantial missingness, with daily pixel gaps ranging from approximately 52.30% to 100% (mean ≈ 88.95%). This study evaluates spatial interpolation, EOF-based, supervised machine-learning, deep-learning, and convolutional autoencoder approaches for reconstructing missing Chl-a values. Sentinel-3 OLCI Chl-a data from 2023–2024 were used for model training, while data from 2025 served as a temporally independent test set to avoid spatiotemporal leakage. To simulate cloud-induced data gaps, artificial missingness scenarios ranging from 50% to 90% were applied for the Inverse Distance Weighting (IDW) and Data Interpolating Empirical Orthogonal Functions (DINEOF) baseline approaches, while machine-learning, deep-learning, and convolutional autoencoder models were evaluated using real satellite-derived missing observations. The evaluated models include IDW, DINEOF, K-Nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), XGBoost, a Long Short-Term Memory (LSTM) network, and a Temporal Data Interpolating Convolutional Autoencoder (Temporal DINCAE). Model performance was assessed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), prediction bias, and the coefficient of determination (R²). Results indicate that tree-based ensemble models outperform spatial interpolation and EOF-based methods, with XGBoost achieving the best overall performance (R² ≈ 0.86; RMSE ≈ 9.61 mg m⁻³). The LSTM model achieved lower prediction errors (RMSE ≈ 5.87 mg m⁻³; MAE ≈ 2.16 mg m⁻³), highlighting the benefit of incorporating temporal dependencies, although with slightly reduced variance capture. The convolutional autoencoder-based Temporal DINCAE model achieved strong reconstruction performance (R² ≈ 0.84; RMSE ≈ 11.15 mg m⁻³). Uncertainty quantification shows that Extra Trees tends to underestimate uncertainty with narrower prediction intervals, whereas XGBoost provides better-calibrated but wider intervals. Full article

Sustainable groundwater management in hyper-arid regions requires accurate water quality assessments, yet remote desert environments present major challenges due to data scarcity, high sampling costs, and limited laboratory infrastructure. This study proposes a framework integrating the Water Quality Index (WQI) with Inverse Distance Weighting (IDW)-based spatial data augmentation and machine learning classification for groundwater quality assessment in the Tabelbala region, southwestern Algeria. Three classifiers were evaluated, Random Forest (RF), Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs), and trained on an augmented dataset generated from 178 original groundwater samples using IDW interpolation with a sensitivity-optimized 150 m radius, producing 2779 augmented training points. RF achieved the highest predictive accuracy (85.9%), followed by ANNs (84.7%) and SVMs (83.1%), with all models demonstrating excellent discriminative performances (area under the receiver operating characteristic curve > 0.96). Permutation Feature Importance analysis identified total dissolved solids (TDS), sulfates (SO₄²⁻), total hardness (TH), and chlorides (Cl⁻) as the most influential parameters, consistent with World Health Organization (WHO) guidelines. Spatial distribution maps revealed that the majority of groundwater sources exhibited poor to very poor quality, highlighting the urgent need for local water management interventions. The proposed framework offers a replicable decision-support tool for water resource managers in data-scarce arid environments, supporting SDG 6 (Clean Water and Sanitation) and SDG 13 (Climate Action). Full article

Accurate delineation of stream networks in low-gradient wetlands remains challenging due to subtle topographic variation and dense vegetation cover. This study systematically evaluated 48 Unmanned Aerial Vehicle Light Detection and Ranging (UAV-LiDAR) processing workflows through 1128 pairwise comparisons to identify optimal approaches for mapping fine-scale channels in Japan’s Kushiro Wetland, a Ramsar-designated ecosystem. The workflows combined three ground filtering methods (Progressive Morphological Filter, Cloth Simulation Filter, Multiscale Curvature Classification), four interpolation techniques (Inverse Distance Weighting, Triangulated Irregular Network, Kriging, Multilevel B-spline Approximation), two sink-filling algorithms (Planchon & Darboux; Wang & Liu), and two flow direction models (D8, D-infinity). Performance was first assessed using pixel-based Intersection over Union (IoU) metrics to quantify inter-method consensus. Independent plausibility-based validation was then conducted using near-contemporaneous Sentinel-2 imagery. Although pairwise statistical analysis identified workflows that achieved high inter-method consensus (median IoU = 0.90), external validation demonstrated that the CSF-MBA-Planchon-D8 workflow provided the most realistic presentation of optically observable channel corridors (validation IoU ≈ 0.85). These findings reveal that high inter-method agreement does not necessarily imply accurate landscape representation; multiple workflows may converge on systematically biased solutions. Ground filtering exerted the strongest influence on pairwise consensus, whereas plausibility-based validation highlighted the importance of selecting workflow combinations that preserve subtle channel morphology. Sink-filling and flow direction choices exerted comparatively minor effects in this low-gradient setting. The proposed dual-validation framework provides methodological guidance for wetland restoration planning and highlights the necessity of external validation in LiDAR-derived hydrological feature extraction. Full article

Hydrological modelling in lowland catchments is often constrained by flat terrain and sparce meteorological station networks, which limits the accuracy of spatial interpolation of precipitation and temperature. In these conditions, the nearest available station may be located tens of kilometres away, making interpolated meteorological inputs highly uncertain and prone to systematic bias. This study aims to improve interpolated meteorological data for hydrological applications by developing and evaluating a practical bias correction approach suitable for low-relief regions with insufficient station density. Long-term temperatures and precipitation records from 18 meteorological stations in Lithuania (1961–2020) were used as reference data. Meteorological fields were reconstructed using Ordinary Kriging and Spline interpolation and evaluated against observations at monthly and daily time scales using correlation (r), Root Mean Square Error (RMSE), Percent Bias (PBIAS), Nash–Sutcliffe Efficiency (NSE), and Probability of Detection (POD) for precipitation. Bias correction was applied to interpolated datasets using inverse distance weighting (IDW) based on one to four neighbouring stations, reflecting typical distances of 50–70 km between observation sites. The results show that while the interpolation method strongly influences precipitation accuracy, bias correction substantially reduces systematic errors without altering temporal structure. The most robust improvements were obtained using two to three neighbouring stations and an IDW power parameter of one, particularly under flat terrain conditions. When applied as input to the HBV rainfall–runoff model for three representative lowland catchments, bias-corrected interpolated meteorological data consistently improved runoff simulations, bringing model performance closer to that achieved using historical station observations. The findings demonstrate that targeted bias correction is an effective and computationally simple strategy for improving interpolated meteorological data in data-sparse lowland regions. The proposed approach provides practical guidance for hydrological modelling where dense observation networks are unavailable and reliance on interpolation is unavoidable. Full article

Accurate lightning data are critical for disaster warning and climate research. This study systematically compares the Fengyun-4A Lightning Mapping Imager (FY-4A LMI) satellite and the Advanced Time-of-arrival and Direction (ADTD) lightning location network in the Beijing-Tianjin-Hebei (BTH) region (April–August, 2020–2023) using coefficient of variation (CV) analysis, Welch’s independent samples t-test, Pearson correlation analysis, and inverse distance weighting (IDW) interpolation. Key results: (1) A significant systematic discrepancy exists between the two datasets, with an annual mean ratio of 0.0636 (t = −5.1758, p < 0.01); FY-4A LMI shows higher observational stability (CV = 5.46%), while ADTD excels in capturing intense lightning events (CV = 28.01%). (2) Both datasets exhibit a consistent unimodal monthly pattern peaking in July (moderately strong positive correlation, r = 0.7354, p < 0.01) but differ distinctly in diurnal distribution. (3) High-density lightning areas of both datasets concentrate south of the Yanshan Mountains and east of the Taihang Mountains, shaped by topography and water vapor transport. This study reveals the three-factor (climatic background, topographic forcing, technical characteristics) coupled regulatory mechanism of data discrepancies and highlights the complementarity of the two datasets, providing a solid scientific basis for satellite-ground data fusion and regional lightning disaster defense. Full article

Soil fertility assessment is fundamental for improving agricultural productivity and promoting sustainable land management. This study proposes an integrated methodological framework that combines Sentinel-2 satellite imagery, spatial analysis techniques, and field-based soil data to evaluate soil fertility in Arabica coffee plantations in the Lonya Grande district, Peruvian Amazon. The framework involves three analytical phases: (i) spatial interpolation of soil macronutrients using Inverse Distance Weighting (IDW), (ii) local modeling through Geographically Weighted Regression (GWR), and (iii) spectral correlation analysis between field-measured soil properties and Sentinel-2 reflectance bands. The SWIR2 (Band 12) data were identified as the most sensitive predictor of soil moisture-related properties, with the strongest relationship observed for soil saturation (R² = 0.40). Field validation revealed pronounced spatial heterogeneity, particularly for macronutrients such as nitrogen, phosphorus, and potassium. The study also found that soils exhibited moderately acidic pH values (5.1–6.8), favorable for coffee cultivation. Despite adequate water retention, nutrient deficiencies highlight the need for site-specific soil management strategies. Overall, spatial analysis confirmed consistent relationships between remote sensing data and soil parameters, demonstrating the feasibility and cost-effectiveness of this approach under data-limited tropical conditions. The proposed framework offers a scalable basis for regional soil fertility monitoring, and future research should incorporate machine learning and expanded sampling networks to further enhance predictive performance. Full article

Snowmelt recharge critically affects water table fluctuations in cold-region unconfined aquifers, where it serves as a primary source of groundwater. This study investigates the temporal and spatial variations in water table responses to snowmelt events in the Oakes Aquifer, North Dakota. Climatic data, including winter snowfall and temperature, were collected from the North Dakota Agricultural Weather Network (NDAWN), as well as the National Weather Service (NWS) and National Oceanic and Atmospheric Administration (NOAA) stations. Observation well data (1991–2023) were analyzed, and Inverse Distance Weighting (IDW) interpolation in ArcGIS Pro 3.6 was used to generate continuous spatial maps of groundwater level rises during spring. Results indicate that snowmelt significantly drives water table fluctuations, with higher snowfall associated with larger rises. Spatial variability in responses reflects differences in soil permeability, and land cover, with high-permeability soils showing more pronounced increases. Temperature strongly influenced the magnitude of snowmelt-induced groundwater rise, with warmer winters generally associated with greater recharge, while colder periods limited infiltration, likely due to frozen soil effects. These findings underscore the role of snowmelt as a key recharge source in cold-region unconfined aquifers, with variations controlled by local hydrogeological and climatic conditions. Understanding these dynamics is critical for groundwater management, particularly under changing climate scenarios. Future studies should focus on long-term monitoring, climate modeling, and cross-regional comparisons to improve predictions of snowmelt-driven recharge. Full article

The availability of reliable and spatially distributed rainfall data is a key element flood and landslide risk assessment, both for forecasting and post-event analysis. In this context, this study evaluates the contribution of radar-based rainfall estimates to enhancing the spatial accuracy of precipitation fields with respect to those derived from rain gauge networks alone. The analysis was conducted over a ~100 km² area in the Liguria Region, north-western Italy, characterized by a dense rain gauge network, with an average density of one gauge per 10 km², and covers seven years of hourly rainfall observations. Radar-derived rainfall fields, available at a 1 × 1 km² spatial resolution, were locally corrected across the study area by interpolating gauge-based local correction factors through an Inverse Distance Weighting (IDW) scheme. The corrected radar fields were then assessed through Leave-P-Out Cross-Validation and rainfall-intensity-based classification, also simulating scenarios with progressively reduced gauge density. The results demonstrate that radar-corrected estimates systematically provide a more accurate spatial representation of rainfall, especially for high-intensity events and in capturing the actual magnitude of local rainfall peaks, even in areas covered by a dense rain gauge network. Regarding the implications for rainfall-induced landslide hazard assessment, the analysis of 56 landslides from the ITALICA (Italian Rainfall-Induced Landslides Catalogue) database showed that including radar information can lead to significant differences in the estimation of rainfall thresholds for landslide initiation compared with gauge-only data. Full article

Reference evapotranspiration (ET₀) is a fundamental variable for irrigation scheduling and water management. Conventional estimation methods, such as the FAO-56 Penman–Monteith equation, are of limited use in developing regions where meteorological data are scarce. This study evaluates the potential of machine learning (ML) approaches to estimate ET₀ in Paraguay, using only geographical and temporal predictors—latitude, longitude, altitude, and month. Five algorithms were tested: artificial neural networks (ANNs), k-nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGB), and adaptive neuro-fuzzy inference systems (ANFISs). The framework consisted of ET₀ calculation, baseline model testing (ML techniques), ensemble modeling, leave-one-station-out validation, and spatial interpolation by inverse distance weighting. ANFIS achieved the highest prediction accuracy (R² = 0.950, RMSE = 0.289 mm day⁻¹, MAE = 0.202 mm day⁻¹), while RF and XGB showed stable and reliable performance across all stations. Spatial maps highlighted strong seasonal variability, with higher ET₀ values in the Chaco region in summer and lower values in winter. These results confirm that ML algorithms can generate robust ET₀ estimates under data-constrained conditions, and provide scalable and cost-effective solutions for irrigation management and agricultural planning in Paraguay. Full article

The concentration characteristics of SO₂, NO₂, O₃, and CO in the marine atmosphere are of great significance for understanding air–sea interactions and regional atmospheric chemical processes. However, due to the challenging conditions of marine monitoring, long-term continuous observational data remain scarce. To address this gap, this study proposes a Transfer Learning–Convolutional Neural Network (TL-CNN) model that integrates ERA5 meteorological data, EAC4 atmospheric composition reanalysis data, and ground-based observations through multi-source data fusion. During data preprocessing, the Data Interpolating Empirical Orthogonal Function (DINEOF), inverse distance weighting (IDW) spatial interpolation, and Gaussian filtering methods were employed to improve data continuity and consistency. Using ERA5 meteorological variables as inputs and EAC4 pollutant concentrations as training targets, a CNN-based inversion framework was constructed. Results show that the CNN model achieved an average coefficient of determination (R²) exceeding 0.80 on the pretraining test set, significantly outperforming random forest and deep neural networks, particularly in reproducing nearshore gradients and regional spatial distributions. After incorporating transfer learning and fine-tuning with station observations, the model inversion results reached an average R² of 0.72 against site measurements, effectively correcting systematic biases in the reanalysis data. Among the pollutants, the inversion of SO₂ performed relatively poorly, mainly because emission reduction trends from anthropogenic sources were not sufficiently represented in the reanalysis dataset. Overall, the TL-CNN model provides more accurate pollutant concentration fields for offshore regions with limited observations, offering strong support for marine atmospheric environment studies and assessments of marine ecological effects. It also demonstrates the potential of combining deep learning and transfer learning in atmospheric chemistry research. Full article

As shallow mineral resources become increasingly depleted, the search for deep-seated orebodies has emerged as a crucial focus in modern gold exploration. This study investigates Vein 171 in the Linglong gold field, Jiaodong Peninsula, using 3D attribute modeling for deep mineralization prediction and precise orebody delineation. The research integrates surface and block models through Vulcan 2021.5 3D mining software to reconstruct the spatial morphology and internal attribute distribution of the orebody. Geostatistical methods were applied to identify and process high-grade anomalies, with grade interpolation conducted using the inverse distance weighting (IDW) method. The results reveal that Vein 171 is predominantly controlled by NE-trending extensional structures, and grade enrichment occurs in zones where fault dips transition from steep to gentle. The grade distribution of the 171₁ and 171_sub-1 orebodies demonstrates heterogeneity, with high-grade clusters exhibiting periodic and discrete distributions along the dip and plunge directions. Key enrichment zones were identified at elevations of –1800 m to –800 m near the bifurcation of the Zhaoping Fault, where stress concentration and rock fracturing have created complex fracture networks conducive to hydrothermal fluid migration and gold precipitation. Nine verification drillholes in key target areas revealed 21 new mineralized bodies, resulting in an estimated additional 2.308 t of gold resources and validating the predictive accuracy of the 3D model. This study not only provides a reliable framework for deep prospecting and mineral resource expansion in the Linglong Goldfield but also serves as a reference for exploration in similar structurally controlled gold deposits globally. Full article

Driven by the increasing global population and rapid urbanization, aircraft noise pollution has emerged as a significant environmental challenge, impeding the sustainable development of the aviation industry. Traditional noise prediction methods are limited by incomplete datasets, insufficient spatiotemporal consistency, and poor adaptability to complex meteorological conditions, making it difficult to achieve precise noise management. To address these limitations, this study proposes a novel noise prediction framework based on a hybrid Convolutional Neural Network–Bidirectional Long Short-Term Memory–Attention (CNN–BiLSTM–Attention) model. By integrating multi-source data, including meteorological parameters (e.g., temperature, humidity, wind speed) and aircraft trajectory data (e.g., altitude, longitude, latitude), the framework achieves high-precision prediction of aircraft noise. The Haversine formula and inverse distance weighting (IDW) interpolation are employed to effectively supplement missing data, while spatiotemporal alignment techniques ensure data consistency. The CNN–BiLSTM–Attention model leverages the spatial feature extraction capabilities of CNNs, the bidirectional temporal sequence processing capabilities of BiLSTMs, and the context-enhancing properties of the attention mechanism to capture the spatiotemporal characteristics of noise. The experimental results indicate that the model’s predicted mean value of 68.66 closely approximates the actual value of 68.16, with a minimal difference of 0.5 and a mean absolute error of 0.89%. Notably, the error remained below 2% in 91.4% of the prediction rounds. Furthermore, ablation studies revealed that the complete CNN–BiLSTM–AM model significantly outperformed single-structure models. The incorporation of the attention mechanism was found to markedly enhance both the accuracy and generalization capability of the model. These findings highlight the model’s robust performance and reliability in predicting aviation noise. This study provides a scientific basis for effective aviation noise management and offers an innovative solution for addressing noise prediction problems under data-scarce conditions. Full article

Accurate coastal bathymetry is critical for navigation, environmental monitoring, and marine resource management. This study presents a deep learning-based approach that fuses Sentinel-2 multispectral imagery with airborne hyperspectral-derived reference data to generate high-resolution satellite-derived bathymetry (SDB). To address the spatial resolution mismatch between Sentinel-2 (10 m) and LiDAR reference data (1 m), three interpolation methods—Inverse Distance Weighting (IDW), Natural Neighbor (NN), and Spline—were employed to resample spectral reflectance data to a 1 m grid. Two spectral input configurations were evaluated: the log-ratio of Bands 2 and 3, and raw RGB composite reflectance (Bands 2, 3, and 4). A Fully Convolutional Neural Network (FCNN) was trained under each configuration and validated using LiDAR-based depth. The RGB + NN combination yielded the best performance, achieving an RMSE of 1.2320 m, MAE of 0.9381 m, bias of +0.0315 m, and R² of 0.6261, while the log-ratio + IDW configuration showed lower accuracy. Visual and statistical analyses confirmed the advantage of the RGB + NN approach in preserving spatial continuity and spectral-depth relationships. This study demonstrates that both interpolation strategy and input configuration critically affect SDB model accuracy and generalizability. The integration of spatially adaptive interpolation with airborne hyperspectral reference data represents a scalable and efficient solution for high-resolution coastal bathymetry mapping. Full article

In subsurface geological mapping, it is more than advisable to compare different solutions obtained with neural and other algorithms. Here, for such comparison, we used the previously published and well-prepared dataset of subsurface data collected from the Bjelovar Subdepression, a 2900 km² large regional macrounit in the Croatian part of the Pannonian Basin System. Data on depth were obtained for the youngest (the shallowest) Lonja Formation (Pliocene, Quaternary) and mapped using neural network (NN), inverse distance weighting (IDW), and ordinary kriging (OK) algorithms. The obtained maps were compared based on square error (using k-fold cross-validation) and the visual interpretation of isopaches. Two other algorithms were also tested, namely, random forest (RF) and extreme gradient boosting (XGB) algorithms, but they were rejected as inappropriate for this purpose solely based on the visuals of the obtained maps, which did not follow any interpretable geological structures. The results showed that NN is a highly adjustable method for interpolation, with adjustment for numerous hyperparameters. IDW showed its strength as one of the classical interpolators, and its results are always located close to the top if several methods are compared. OK is the relative winner, showing the flexibility of variogram analysis regarding the number of data points and possible clustering. The presented variogram model, even with a relatively high sill and occasional nugget effect, can be well fitted into OK, giving better results than other methods when applied to the presented area and datasets. This was not surprising because kriging is a well-established method used exclusively for interpolation. In contrast, NN and machine learning algorithms are used in many fields, and these algorithms, particularly the fitting of hyperparameters in NN, simply cannot be the best solution for all. Full article

Accurate forecasting of river flows is essential for effective water resource management, flood risk reduction and environmental protection. The ongoing effects of climate change, in particular the shift in precipitation patterns and the increasing frequency of extreme weather events, necessitate the development of advanced forecasting models. This study investigates the application of long short-term memory (LSTM) neural networks in predicting river runoff in the Velika Morava catchment in Serbia, representing a pioneering application of LSTM in this region. The study uses daily runoff, precipitation and temperature data from 1961 to 2020, interpolated using the inverse distance weighting method. The LSTM model, which was optimized using a trial-and-error approach, showed a high prediction accuracy. For the Velika Morava station, the model showed a mean square error (MSE) of 2936.55 and an R² of 0.85 in the test phase. The findings highlight the effectiveness of LSTM networks in capturing nonlinear hydrological dynamics, temporal dependencies and regional variations. This study underlines the potential of LSTM models to improve river forecasting and water management strategies in the Western Balkans. Full article