Search Results (1,007)

In this study, we evaluated the use of five different ML algorithms (CatBoost, XGBoost, random forest, gradient boosting, and support vector regression [SVR]) to estimate daily ET₀ based only on four independent variables: 2 m air temperature, vapor pressure deficit, 10 m wind speed, and sunshine duration. We used a total of 9132 daily values (2000–2025) from the Open-Meteo Historical Weather API (2000–2025) at 10 stations in the Tlemcen province of northwest Algeria. The dataset was divided into training, validation, and testing sets using a chronological split of 70/15/15. We estimated the performance of each algorithm by using several statistics (RMSE, MAE, R², NSE, RSR, and Willmott Index) as well as some statistics to evaluate the potential of overfitting and the ability to reproduce the behavior observed during the training phase. CatBoost had the highest overall accuracy and the most generalized performance, with an RMSE of approximately 0.292 mm day⁻¹, MAE of approximately 0.208 mm day⁻¹, R² of 0.971, and NSE of 0.971 in the test set, suggesting an extremely low risk of overfitting. The optimal CatBoost model was also used to estimate the spatial and temporal variations of monthly ET₀. The results showed high interannual variability (changes from year to year from −12.815 to +8.707 mm month⁻¹) in the semi-arid region of Tlemcen but no significant long-term trends (cumulative net change of approximately −0.021 mm month⁻¹ over 2000–2025). Therefore, the use of CatBoost is recommended as a robust, efficient, and reliable emulator of the FAO-56 Penman–Monteith equation (ET₀) for estimating ET₀ in semi-arid environments with limited climate data availability, and could be particularly useful in northwestern Algeria and other semi-arid Mediterranean regions. Full article

Surface solar radiation at the ground is affected by aerosols, clouds, and atmospheric moisture, as well as by circulation-related conditions that influence cloud formation and pollutant transport. In daily observations, these influences are mixed, which makes pollution-related variability difficult to interpret. We analyzed data from Beijing station 54511 (2015–2019), including daily integrated radiation components and collocated meteorological and pollution variables. We used wavelet coherence, pollution-stratified association analysis, and gray relational analysis, and compared two meteorological normalization methods: multiple linear regression (MLR) and random forest (RF). The results show that meteorological–radiation relationships vary systematically across pollution levels, indicating substantial meteorological confounding in daily radiation analyses. Among the radiation components, DR shows the clearest pollution-dependent shift in its relationship with RH, while several direct components become less sensitive to cloud cover under heavier pollution. RF reproduced daily radiation components with strong predictive performance (R² = 0.83–0.88), and the meteorologically adjusted anomalies from RF were consistent with those from MLR (r = 0.63–0.78 across components). These findings suggest that both MLR and RF can be effectively used to normalize meteorological effects in daily station records. The analysis supports routine interpretation of day-to-day surface radiation variability and can be extended to multi-site studies and finer temporal resolution. Full article

Rising human-caused nitrogen (N) deposition and increased rainfall variability threaten the capacity of temperate forests to sequester carbon. However, the combined effects of N enrichment and moisture changes on total soil respiration (Rs), including its autotrophic (Ra) and heterotrophic (Rh) components, remain poorly understood, especially in northern China’s warm-temperate forests. To explore this, a factorial field experiment was conducted at the Beijing Yanshan Earth Critical Zone National Research Station in Huairou District, Beijing. The experiment involved N addition (50 kg N ha⁻¹ yr⁻¹ as urea [CO(NH₂)₂]) and precipitation manipulation (±50% of ambient throughfall) during the 2024 growing season. Six treatments were implemented: control (CK), nitrogen addition (NA), 50% increased precipitation (W+50%), 50% decreased precipitation (W−50%), nitrogen addition with increased precipitation (NW+50%), and nitrogen addition with decreased precipitation (NW−50%). Under natural rainfall conditions, N addition increased Rs (+11.8%; p < 0.05). However, the effects of N largely depended on water availability: with increased rainfall, N addition significantly boosted Rs, Rh, and Ra by promoting fine root biomass and accelerating litter decomposition; under reduced rainfall, N addition still increased Rs, Rh, and Ra compared to drought alone (NW−50% vs. W−50%), though the extent of stimulation was considerably lower than under elevated precipitation, indicating that water availability influences the strength of N effects on forest soil respiration. Structural equation modelling (SEM; χ²/df = 1.8, RMSEA = 0.040, CFI = 0.97) revealed that water availability was a key mediator of the interaction between N addition and precipitation. These findings enhance understanding of how nitrogen supply and water availability interact in temperate forest soils, though further validation across other forest types and over longer periods remains necessary. Full article

Accurate estimation of river discharge is fundamental for water resources management, flood forecasting, and drought monitoring in the Amazon River Basin. Rating curves, which relate water level (stage) to discharge, are the primary tool for streamflow estimation. This study evaluates traditional curve-fitting methods and machine learning algorithms for modeling rating curves at the two largest gauging stations in the Amazon River: Itacoatiara and Óbidos. The analysis is based on 70 stage–discharge measurements at Itacoatiara (2008–2023) and 176 measurements at Óbidos (1968–2023). Five modeling approaches were compared: Power Law, Linear Regression, Decision Tree, Random Forest, XGBoost, and Multi-Layer Perceptron (MLP). Model performance was assessed against official baseline rating curves maintained by Brazil’s National Water Agency (ANA) and the Geological Survey of Brazil (SGB/CPRM) using Root Mean Square Error (RMSE), coefficient of determination (r²), Mean Bias Error (MBE), Nash–Sutcliffe Efficiency (NSE) and Kling–Gupta Efficiency (KGE). Results indicate that ensemble-based machine learning methods, particularly XGBoost (RMSE = 7463 m³/s, NSE = 0.973 at Itacoatiara; RMSE = 18,378 m³/s, NSE = 0.872 at Óbidos), outperformed traditional methods. However, the Decision Tree exhibited overfitting that could not be resolved through pruning, depth limitation, or other strategies given the sample size. Traditional methods such as the optimized Power Law remain practical and transparent alternatives for operational use. The findings suggest that machine learning can complement traditional approaches for improving rating curve accuracy in large tropical rivers, with K-fold cross-validation used to assess variability and performance. Full article

Accurate solar radiation estimation is critical for optimizing solar energy applications. This study divided 819 meteorological stations in China into six solar radiation zones using k-means, hierarchical, and bisecting k-means clustering based on daily relative sunshine duration. Correlation analysis and feature importance evaluation were conducted to quantify the contributions of key meteorological variables. A comparison of models considering regional heterogeneity was performed. Six sunshine-based empirical models, three machine learning models (Random Forest, Support Vector Machine, and Extreme Gradient Boosting), and two deep learning models (Long Short-Term Memory and Gated Recurrent Unit) were systematically evaluated across 98 stations with observed solar radiation data. Model performance was assessed using the coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE), and normalized RMSE (NRMSE). Results showed that k-means clustering outperformed the other two methods and was adopted for final zoning. The correlation analysis identified sunshine duration (S), extraterrestrial radiation (R_a), temperature difference (ΔT), and maximum temperature (T_max) as the dominant influencing factors, with clear regional heterogeneity. The deep learning models, particularly LSTM (R² = 0.939, RMSE = 1.702 MJ/m/²/d¹, MAE = 1.319 MJ/m/²/d¹, NRMSE = 0.046), achieved the highest accuracy, followed by GRU, XGB, SVM, and RF. Among the empirical models, Model 5 performed best in Zones 1, 3, 4, and 5, while Model 6 was optimal in Zones 2 and 6. The key novelty of the study is an integrated zoning–prediction framework for regional solar radiation estimation, combining clustering validation, correlation analysis, empirical model calibration, and deep learning benchmarking, with enhanced physical interpretability and prediction accuracy. Full article

Using a coordinated multi-year monitoring dataset collected during the 2020–2024 partial-opening management period, we examined benthic diatom assemblages across the Sejong, Gongju, and Baekje weirs in the Geum River, Republic of Korea. Seasonal surveys at eight stations were used to evaluate spatiotemporal variation in water quality and benthic diatom community structure under this hydrological management regime. Annual basin-wide averages showed gradual interannual changes in water quality, including declines in total phosphorus, total nitrogen, chlorophyll-a, turbidity, and biochemical oxygen demand after 2021, accompanied by increased dissolved oxygen. Diatom community indices based on relative-abundance data showed corresponding temporal variation, with decreased dominance and increased Shannon diversity, evenness, and taxon richness. Ordination analyses indicated gradual differentiation between the earlier (2020–2021) and later (2022–2024) monitoring groups within the study period, whereas random forest models showed limited explanatory power and were treated as exploratory. Overall, the results support benthic diatoms as sensitive descriptors of ecological change in flow-regulated monsoonal rivers while underscoring the value of long-term monitoring where true pre-intervention biological baselines are unavailable. Full article

Urbanisation reshapes Land Cover and Land Use (LCLU) by driving deforestation, wetland loss, and the conversion of natural and agricultural areas into built environments. However, integrated analyses of LCLU change in response to climate variability in topographically complex, rapidly urbanising African cities remain limited. Therefore, this study examined 2000–2024 LCLU changes in hilly Gasabo District (Kigali, Rwanda) using 30 m Landsat imagery and a Random Trees classifier (92.7% accuracy, 70/30 train-test split), with 2032 projections via a population-driven hybrid trend model. Population estimates/projections 320,516 in 2002 to 967,512 in 2024, 1.41 million by 2032, were derived from Rwanda’s census data and exponential growth modelling (calibrated to 5.05% annual growth). Rapid population growth has driven a 539% expansion of Built-up Areas, accompanied by notable declines in cropland and Forest. Local climate trends (Meteo Rwanda stations) aligned with global datasets (ERA5-Land and CHIRPS): rainfall fluctuation and temperature rose, with strong correlations between population-driven Built-up Areas expansion. From 2024 to 2032, LCLU projections indicate that Built-up Areas will continue to expand by 29.5%. Cropland was forecast to decline to 15.9%, while Forest loss slowed to 5.7%. MLR analysis revealed strong correlations between population-driven expansion of Built-up Areas, cropland/forest loss, warming, and rainfall fluctuations in Gasabo. An ARDL model was applied to address multicollinearity among LCLU predictors, which limited the interpretation of individual coefficients, and confirmed the core MLR correlation trends, with statistically significant (p < 0.05) coefficients. The results highlight the need for data-driven spatial planning in Gasabo (stricter zoning, high-rise buildings, targeted reforestation, climate-resilient green infrastructure) to mitigate population and urbanisation-driven environmental degradation. Full article

Accurately characterizing the spatiotemporal variations in precipitation in China’s drylands is important for solving water scarcity in the region, guaranteeing security in the ecological environment, and conducting precise drought disaster management. To reduce the uncertainty in the existing precipitation products, we developed a two-stage machine-learning framework combining extreme gradient boosting (XGBoost) and random forest (RF) residual corrections. Based on the ground-based observation data from 1030 meteorological stations and numerous high-precision precipitation products (GPM IMERG Final V6, MSWEP V2, CMFD 2.0, TerraClimate), a monthly fused precipitation dataset (XGB-RF) for China’s drylands was produced during the 2001–2020 period at the 0.1° resolution. The validation results showed that the XGB-RF had a monthly Kling–Gupta Efficiency (KGE) of 0.941, and it improved 20.6–62.2% relatively with that of input individual products. For the dataset as a whole, we found very consistent, reliable performance in all seasons and topography, in particular in winter time and data-scarce western areas where individual products have large biases. More importantly, the XGB-RF was employed for drought monitoring based on the 1-month Standardized Precipitation Index that calculated the median KGE of 0.888, which made good drought trend tracking and drought features possible. Notably, the KGE for the mean drought intensity was 0.757, which was higher than that of independent original products. This study provides a high-resolution precipitation forcing dataset and demonstrates the effectiveness of two-stage machine learning strategies in enhancing hydroclimatic monitoring and drought risk assessment in arid and semi-arid regions. Full article

Controlling operation-stage carbon emissions (CE) from transport buildings is crucial for China’s dual-carbon goals and the ecological security of the Qinghai–Tibet Plateau (QTP), and the sustainable development of plateau transport infrastructure. For plateau railway passenger stations (RPS), limited monitoring and distinctive high-altitude, cold-climate operations make daily CE prediction difficult with conventional measurement- or simulation-based methods. This study develops a machine-learning approach based on a Monte Carlo synthetic database and derives engineering-standard formulas for direct use. Building scale, meteorology and passenger flow volume (PFV) were compiled for 12 representative RPS, and a large synthetic database of daily carbon emission was generated under multiple distribution constraints. With daily mean temperature, heating degree days, altitude, station floor area and PFV as inputs, four models were trained and assessed using mean absolute error, root mean square error, mean absolute percentage error (MAPE) and R². The results show that random forest (RF) performed best, achieving ~6% MAPE and R² > 0.99 on the test set, and markedly lower errors than multivariable linear regression. Interpretation of RF via feature importance and partial dependence shows that floor area, altitude and PFV dominate emissions and exhibit nonlinear response patterns. To improve transparency and transferability, ridge regression was used to fit a linear surrogate to RF predictions, producing engineering-standard formulas for daily and annual operation-stage CE. The formulas retain most predictive accuracy while requiring only readily obtainable variables, enabling rapid estimation and scenario analysis for cold, high-altitude RPS. The proposed workflow provides a replicable pathway for operational CE assessment in data-scarce regions and supports low-carbon planning, design and operation of RPS on the QTP, thereby contributing to more sustainable infrastructure development in high-altitude regions. Full article

Precipitation is a fundamental element in terrestrial water circulation and ecosystem hydrological balance. The occurrence of concentrated precipitation is closely linked to vegetation growth and soil fertility rather than accumulated or averaged precipitation. Despite its importance, the characteristics of continuous precipitation and its specific effects on vegetation cover remain uncertain. In this study, we formulated a new continuous precipitation index system, including $C{P}_d$ (continuous precipitation days); $AC{P}_t$ (annual continuous precipitation times); $C{P}_a$ (continuous precipitation amount); and $FCP$ (frequency in different ranges of $AC{P}_a$). We utilized daily precipitation data from 467 meteorological stations across China, which were divided into eight vegetation type regions. We observed that the spatial distribution of continuous precipitation differed to varying degrees from accumulated precipitation. The national average of $MAC{P}_a$ for a single event was 16.7 mm, ranging from 3.8 mm in the temperate desert region to 37.1 mm in the tropical monsoon forest and rainforest region. Similarly, the national average of $MC{P}_d$ ($MMC{P}_d$) for a single event was approximately 2.3 or 9 days. At the regional level, the tropical monsoon forest and rainforest region experienced the longest $MMC{P}_d$. Furthermore, the national average of $MAC{P}_t$ occurrences for 1 year was 57.7 times, varying from 29.8 times in the temperate desert region to 77.9 times in the tropical monsoon forest and rainforest region. Vegetation responses to precipitation regimes exhibit significant regional heterogeneity across China. Our analysis reveals that $MAC{P}_t$ and $M{P}_a$ show markedly positive correlations with vegetation growth. In subtropical monsoon climate zones, particularly the Yunnan–Guizhou Plateau and Qinling Mountains, $MAC{P}_t$ demonstrates strong positive correlations (r = 0.6–1.0) with NDVI, where sustained rainfall provides stable moisture availability for vegetation. While a positive correlation between vegetation (NDVI) and mean annual consecutive precipitation is observed in some arid northern regions, in ecosystems such as the Loess Plateau (TG/TM), vegetation growth shows greater dependence on $M{P}_a$, highlighting the crucial role of total precipitation amount in water-limited ecosystems. Notably, extreme precipitation events display dual effects on vegetation dynamics. Prolonged heavy rainfall ($MMC{P}_d$/$MMC{P}_a$) exhibits significant negative impacts on NDVI (r = −1.0 to −0.6) in topographically complex regions, including the Hengduan Mountains and Yangtze River Basin (SE), likely due to induced soil erosion and waterlogging stress. Our findings underscore the importance of incorporating continuous precipitation indices to evaluate and forecast the influence of precipitation on ecosystem stability. This understanding is vital for developing informed conservation and management strategies to address current and future climate challenges. Full article

Suspended sediment concentration (SSC) and sediment flux (SF) are critical indicators of sediment delivery in the Lower Mekong and underpin deltaic geomorphic stability and ecosystem services. With recent evidence of declining sediment supply caused by upstream regulation and intensive in-channel extraction, there is a pressing need for data-efficient tools to reproduce non-linear sediment dynamics and assist management in the Vietnamese Mekong Delta (VMD). This study evaluates three machine-learning algorithms—Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost)—for data-driven prediction of SSC (2009–2023) and SF (2009–2021) at Tan Chau (Viet Nam). The predictive models were developed using daily discharge inputs from Kratie (Cambodia) and local hydrological data, including water levels and discharge, from the Tan Chau station. Across the held-out testing dataset, all models captured substantial variability in both targets, with consistently higher performance for SF than for SSC. RF achieved the highest skill (SSC: R² = 0.783; SF: R² = 0.867), followed by XGBoost and then SVM. Variable-importance analysis indicates that upstream discharge at Kratie is the most influential predictor for both SSC and SF, consistent with basin-scale hydrological forcing governing downstream sediment transport capacity. The observed record at Tan Chau further suggests an attenuation of wet-season SSC peaks during 2018–2022 relative to earlier years, signalling potential sediment-starvation dynamics that warrant continued monitoring. Overall, the results demonstrate the utility of ML-based sediment prediction models as a complement to conventional monitoring and as an evidence base to inform sediment-aware river–delta management and risk mitigation in the Lower Mekong. Full article

This study examines how assessments of coastal extreme sea levels depend on the separability and reconstructability of the astronomical tide in hourly sea-level records. Using a global tide-gauge network, it proposes an ensemble-learning correction framework that integrates a physical-baseline threshold with multi-criteria consistency testing to determine whether machine-learning enhancement is genuinely effective across stations and time windows. The analysis uses hourly records from 528 UHSLC tide gauges, with 31-day short sequences used to reconstruct 180-day sea-level variability. Taking the physical tidal model as the baseline, residuals are corrected using Extremely Randomized Trees, Random Forest, and Gradient Boosting. To avoid false improvement driven solely by error reduction, a hierarchical decision framework is established. Baseline model quality is first screened using NSE and the coefficient of determination, after which mathematical artefacts are identified through diagnostics of peak suppression and variance shrinkage. A five-level classification is then derived from the convergent evidence of twelve performance metrics and four statistical significance tests. The results show a consistent global pattern across all three algorithms. Approximately 57% of stations meet the criterion for genuine improvement, whereas about 42% are associated with an unreliable physical baseline, indicating that the dominant source of failure arises not from the ensemble-learning algorithms themselves, but from spatially varying limitations in the underlying physical baseline. Spatially, the credibility of machine-learning correction is strongly conditioned by baseline quality: stations with effective correction are more continuous along the eastern North Atlantic and European coasts, whereas stations with ineffective correction are more concentrated in the Gulf of Mexico, the Caribbean, and the marginal seas and archipelagic regions of the western Pacific. These results indicate that the observed spatial heterogeneity primarily reflects geographically varying physical and dynamical conditions that control baseline reliability and residual learnability, rather than a standalone difference in the intrinsic capability of ensemble learning itself. Full article

This study has explored the effectiveness of machine learning methods for high-precision spatial interpolation of meteorological variables, aiming to provide accurate atmospheric delay corrections for high-precision edge and corner nets observation in complex-terrain environments such as the Xiluodu Hydropower Station, thereby enhancing the accuracy of deformation monitoring. Considering the significant limitations of traditional interpolation methods such as Inverse Distance Weighting (IDW) and Ordinary Kriging (OK) in capturing spatial variability under complex topographic conditions, we systematically introduced machine learning algorithms including Random Forest (RF)and eXtreme Gradient Boosting (XGBoost, XGB) to compare their performance with traditional methods for high-density interpolation of sparsely distributed temperature, relative humidity, and surface pressure, respectively. Concurrently, we proposed an enhanced XGB model incorporating center-point features (XGB-C) which frames spatial interpolation as a supervised learning problem that learns physical mapping from synoptic backgrounds to local microclimates instead of relying on geometric distances alone. The interpolation performance indices (RMSE, MAE, and R²) were evaluated with daily meteorological observations from 47 stations (38 for training, 9 for testing) during 2023–2024. Results demonstrate that machine learning methods significantly outperform traditional approaches, with XGB-C achieving the highest accuracy (R² ≈ 1.00 for pressure, 0.97 for humidity, 0.83 for temperature). Moreover, the interpolation performance also exhibits a dependence on seasons and the station location. Greater challenges are shown in the summer season and in the “Urban and Built-Up” and “Croplands” areas. These findings highlight the substantial advantages of machine learning, particularly the proposed XGB-C, for meteorological interpolation in mountainous hydropower station environments where accurate atmospheric correction is crucial for deformation monitoring. This also lays a solid foundation for developing operational ML-based interpolation models trained with high-quality labels derived from unmanned aerial vehicle (UAV) remote sensing data. Full article

Low-cost air quality sensors enable dense urban monitoring networks but require calibration against reference-grade instruments. While machine learning calibration is well-established for co-located sensor pairs, applying these calibrations to sensors deployed far from any reference station—the operational reality for most network sensors—lacks systematic methodology. We address this gap using 24 months of hourly data (August 2023–July 2025) from Sofia, Bulgaria, where five official reference stations (Executive Environmental Agency) operate alongside 22 AirThings low-cost sensors, four of which are co-located. Random Forest models achieved $R^2\in (0.53,0.75)$ across PM_2.5, PM₁₀, NO₂, and O₃, representing from 40% (for O₃) to 408% (for PM_2.5) improvement over Multiple Linear Regression baselines. Using leave-one-station-out spatial cross-validation, we derived pollutant-specific uncertainty growth rates ($\alpha$) from 3.84% to 5.62% per km, characterizing how calibration uncertainty increases with distance from reference stations (statistically significant for PM₁₀ and O₃, $p<0.05$). Applied to 18 non-co-located sensors, the framework generated 1.2 million calibrated hourly measurements with 95% prediction intervals over the study period. Co-location sites spaced 6 km apart achieve a less than 30% uncertainty increase at network midpoints, within EU Air Quality Directive thresholds for indicative monitoring. These empirically derived $\alpha$ parameters enable network planners to predict measurement reliability at arbitrary sensor locations without ground-truth validation, providing evidence-based guidance for cost-effective hybrid monitoring network design. Full article

Hydropower is a cornerstone of global renewable energy; however, reservoir sedimentation directly undermines its benefits and operational lifespan. A critical, often overlooked, aspect of sedimentation is the compaction of fine-grained deposits, which introduces systematic discrepancies between standard siltation calculation methods. This study addresses this gap by developing a machine learning-based model to quantify sediment compaction and correct siltation estimates using the Xiluodu Hydropower Station on the Jinsha River, China, as a case study from 2014 to 2020. Based on hydrological, sediment, and fixed-section monitoring data, we applied five machine learning algorithms (Linear Regression, Neural Network, Random Forest, Gradient Boosting, and Support Vector Regression) to establish a relationship between the compaction thickness and the following key predictors: Year, Cumulative Sediment Thickness, Annual Sediment Thickness, and Distance to the Dam. The results demonstrate that the Neural Network (NN) model significantly outperforms traditional models, effectively capturing complex, nonlinear compaction dynamics with strong predictive accuracy (test R² = 0.766, RMSE = 0.047 m) and no significant overfitting. SHAP analysis revealed the dominant influences of consolidation time (years) and overburden stress (Cumulative Sediment Thickness), linking the model’s predictions to fundamental geotechnical principles. Applying the NN model to correct for the cross-sectional volume method markedly improved its consistency with the independent sediment transport method, reducing the average relative difference from −33.7% to −6.5% (2016–2020). This study provides the first quantitative, continuous (198 km, 221 sections) assessment of reservoir-scale sediment compaction, confirming its widespread existence and demonstrating its critical role in the long-standing methodological discrepancies. Our study transformed compaction from an acknowledged phenomenon into a quantifiable correction, offering a novel, data-driven framework to enhance the accuracy of reservoir sedimentation assessments globally. Full article