Search Results (1,964)

The Portuguese agricultural sector has suffered a profound transformation over recent decades, evolving from traditional to increasingly technology-driven systems. Throughout this transition, climate and meteorological conditions have remained key drivers of agricultural productivity. Today, Portuguese agriculture faces growing challenges associated with climate change, including more frequent and intense heatwaves, droughts, and floods. Consequently, reliable climate information and decision-support tools are essential for strengthening resilience and promoting sustainable management. To address these needs, the Portuguese Institute for the Sea and Atmosphere (IPMA) developed two complementary climate service platforms for mainland Portugal: AgroClima and DataClima. The first provides observations from IPMA’s meteorological network, ECMWF forecasts, and agroclimatic indicators such as temperature, precipitation, soil water, and so-called agroclimatic warnings. The second offers historical climate information including WRFv4.2 simulations dynamically downscaled from ERA5 (1981–present), in situ observations (1941–present), and climate normals. Evaluation of the WRFv4.2 regionalization against IPMA observations shows a systematic underestimation of precipitation and air temperature, while mean wind speed is generally overestimated. Despite these biases, the downscaled WRFv4.2 dataset demonstrates sufficient accuracy to support operational climate services, providing valuable help for environmental monitoring, climate adaptation, and decision-making in agriculture and water resource management across Portugal. Full article

Water and fertilizer management in facility and precision agriculture increasingly depends on images, soil sensors, weather records, management logs, and economic data rather than on empirical operation alone. A cross-modal decision framework is developed to align crop visual traits with soil water–salt dynamics, meteorological variation, and management operations. Image preprocessing, abnormal sensor screening, missing value interpolation, temporal resampling, multi-window alignment, and temporal augmentation are used to form comparable inputs before multimodal fusion. Using plot-blocked evaluation that keeps complete plot trajectories together, AgriWFD-RLNet obtains 93.46% status-recognition accuracy and an $R^2$ of 0.923 for yield–resource–economic response prediction. In offline policy evaluation against the logged conventional management reference, it estimates 16.92% water saving, 14.37% fertilizer saving, and 15.84% Net Return improvement while maintaining 94.68% yield stability and 96.72% safety compliance. These decision outcomes are model-based estimates from the 2024 Wuyuan dataset rather than outcomes of a prospective field deployment. Full article

Early instrumental meteorological observations are essential for identifying and characterizing extreme climate events prior to the modern observational era, particularly in regions where historical data are scarce. This study documents a remarkable late-spring heatwave using newly recovered daily temperature observations from Ferrol (northwestern Spain) for the period 1792–1795, retrieved from the Historical Archive of the Royal Institute and Observatory of the Spanish Navy. Despite the temporal limitations of this early dataset, its daily resolution enables a detailed analysis of short-term climatic variability and extreme temperature events. The analysis reveals an extraordinary warm episode in late May 1795, characterized by sustained positive temperature anomalies that stand out clearly against the surrounding days. Comparison with the modern climate indicates that the event was exceptional even by present-day standards, with mean temperatures approximately 2 °C above the current 95th percentile. To assess the spatial extent of the heatwave, we compared the Ferrol data with contemporaneous instrumental records from Madrid, Barcelona, and Cádiz. All three locations exhibit synchronous, pronounced positive anomalies, demonstrating that the 1795 event was a large-scale phenomenon affecting most of the Iberian Peninsula. This study highlights the critical value of historical data rescue for contextualizing modern climate extremes and extending our understanding of regional climate variability. Full article

Retrieving aerosol optical depth (AOD) over land remains challenging because the relatively weak aerosol signal in top-of-atmosphere (TOA) observations must be separated from strong and spatially heterogeneous surface reflectance. Here, we develop a physically informed random forest framework for global 1 km land AOD retrieval from MODIS. The framework integrates multispectral TOA reflectance, surface properties, observation geometry, meteorological conditions, topography, and physically informed aerosol–surface features. Long-term Aerosol Robotic Network (AERONET) observations from 2001 to 2017 were collocated with MODIS and ancillary datasets for model development and evaluation. Two physically informed features were introduced to improve retrieval robustness across diverse aerosol and surface conditions, including minimum AOD derived from long-term AERONET observations and time-series clear-sky reflectance (TSCR) in the blue, red, and shortwave-infrared bands derived using the 6S radiative-transfer model. Independent retrieval evaluation for 2013–2014 showed good agreement with AERONET observations, with R = 0.81, MAE = 0.063, RMSE = 0.096, and 74.93% of matched samples falling within the MODIS land expected-error envelope, although increasing underestimation was observed at high aerosol loading (AOD > 1). The proposed retrievals also showed better agreement with AERONET than the MOD04 Dark Target and Deep Blue products. These results demonstrate the value of incorporating physically interpretable aerosol-background and surface-reflectance information into data-driven retrievals for AOD over land surfaces. Full article

Reverse osmosis (RO) desalination is a major technology for freshwater production in arid regions, but its energy demand becomes more challenging when the system is supplied by variable renewable energy. This study presents an offline digital-twin-assisted decision-support framework for dynamic RO under Kuwait solar-availability conditions. Within this framework, the predictive models are driven primarily by the dynamic RO process variables, while NASA Prediction Of Worldwide Energy Resources (POWER) data provide the Kuwait solar-availability context, and the PV power margin serves as a scenario-level energy indicator. The purpose is to predict instantaneous permeate flow rate, estimate specific energy consumption, and identify energy-efficient operating conditions using machine learning. Kuwait City was used as the solar case-study location. Hourly solar and meteorological data were obtained from NASA POWER, while dynamic RO membrane data were obtained from the open experimental wave desalination dataset published by the National Renewable Energy Laboratory (NREL) through Data.gov and the Marine and Hydrokinetic Data Repository. The RO dataset includes steady-state, ramp, sinusoidal, and Wave Energy Converter SIMulator (WEC-Sim) pressure/flow experiments. The process-flow image used in the system description was also taken from the same NREL dataset and is cited in the figure caption. The raw RO files were cleaned, harmonized, and transformed into a process-informed modeling dataset. Derived features included pressure rate, recovery ratio, salt rejection, estimated pump power, specific energy consumption (SEC), PV power margin, and rolling pressure/flow features. Three supervised regression models were tested: Gradient Boosting, Random Forest, and XGBoost. A representative subset of 60,000 records was used to preserve the main experimental conditions while reducing redundancy in the densely sampled sequential data. Results show that permeate flow rate can be predicted with high accuracy using Gradient Boosting (R² = 0.981; RMSE = 0.161 L/min). The moderate energy prediction performance yielded an R² of 0.654 and RMSE of 7.570 kWh/m³ for Random Forest. The accuracy of permeate conductivity predictions was lower (R² = 0.257; RMSE = 245.44 µS/cm) because membrane and feed characterizing parameters should be included for an adequate water quality control. The proposed approach is best suited as an offline decision-support framework for dynamic RO process analysis. Full article

Xylem sap is increasingly recognized as a dynamic biological matrix reflecting whole-plant physiological status, but its biochemical variation under field conditions remains insufficiently characterized. We investigated oxidative stress markers, osmolytes, antioxidant enzymes, and redox-related enzymes in xylem sap from three focal tree individuals representing Fraxinus excelsior, Populus nigra, and Pinus sylvestris. Sap was collected by passive stem tapping using a custom-built apparatus, and biochemical patterns were evaluated using multivariate statistical and machine-learning approaches. The three focal trees showed distinct biochemical profiles within the present dataset. The focal P. nigra individual was associated with relatively higher antioxidant enzyme activities, whereas the focal F. excelsior and P. sylvestris individuals were more closely associated with oxidative-damage and metabolic-adjustment traits. Precipitation and wind direction were retained as the main meteorological variables associated with biochemical variation, with wind direction interpreted as an atmospheric correlate rather than a direct physiological driver. Exploratory machine-learning analyses highlighted catalase and selected meteorological variables as influential predictors. Overall, the findings support the potential of xylem sap for integrative ecophysiological monitoring while emphasizing the exploratory nature of patterns derived from repeated measurements of three focal trees. Full article

Accurately forecasting waypoint-level tropical cyclone (TC) intensity, defined as the local wind speed at specific maritime route waypoints under TC influence, is crucial for navigation safety and voyage planning. Conventional studies mainly focus on the central intensity of TC systems and underutilize the complementary value of multimodal meteorological data with inconsistent sampling intervals. To address these challenges, this study proposes a multimodal-augmented conditional diffusion model (MADiff) for waypoint-level TC intensity prediction. To exploit the potential of multimodal inputs, we first design a temporal-adaptive dynamic convolution module (TDConv) to capture multi-timescale features, mitigating multimodal sampling discrepancies without rigid temporal alignment. Second, we develop a discriminative cross-fusion module (DisCF) to aggregate multi-timescale features across diverse modalities, quantifying multimodal heterogeneity and integrating valuable modality-specific features while suppressing noise interference. Fused features are fed into a diffusion model with physics-informed regularization to generate final intensity forecasts. Extensive experiments on four Western North Pacific datasets show that MADiff achieves average MAE and RMSE values of 2.08 kt and 2.37 kt, respectively, for 12 h intensity forecasting. Compared with the state-of-the-art baseline (TC-Clouds-DP), MADiff yields substantial performance improvements, reducing MAE by 16.3% and RMSE by 10.6% on average. This study provides an effective framework for fine-grained TC intensity forecasting, offering valuable insights for extreme marine weather early warning and intelligent navigation decision-making. Full article

Airborne microplastics (AMPs) are increasingly recognized as an emerging air pollutant. However, observational data remain scarce in Southeast Asia. This study provides the first observations of AMPs in Phnom Penh, Cambodia, using µFTIR-ATR imaging. Number concentration, morphology, polymer composition, aerodynamic size distribution, Feret diameter, and surface aging characteristics were investigated together with meteorological parameters, gaseous pollutants, water-soluble ionic tracers, and HYSPLIT backward trajectories to examine possible source attribution. AMPs were dominated by polyethylene (PE), polypropylene (PP), and polyethylene terephthalate (PET), with 52% classified as fragments and 82% having Feret diameter smaller than 30 µm. Across four independent 72-h sampling periods (n = 4), AMP concentrations ranged from 0.55 to 1.27 MP m⁻³ in TSP, with a mean ± standard deviation of 0.97 ± 0.30 MP m⁻³, and from 0.23 to 0.49 MP m⁻³ in the PM_2.5 fraction, with a mean ± standard deviation of 0.33 ± 0.10 MP m⁻³. In total, 134 particles were identified in TSP, of which 46 were detected in the PM_2.5 fraction. Carbonyl and hydroxyl indices indicated that PE and PP were relatively fresh and in low-to-moderate surface aging states. Pearson correlations suggested that the abundances of individual polymers were varied differently in relation to local environmental and precipitation-related variables; however, the limited number of sampling periods precludes source or process attribution. In addition, HYSPLIT backward trajectories showed that some air masses arriving in Phnom Penh had passed over marine regions under southwest monsoon flow. These findings provide the first baseline dataset for AMP pollution in Phnom Penh, Cambodia, and highlight the combined importance of local emissions and regional atmospheric transport in Southeast Asia. Full article

Feature selection is a critical step in regression problems where a large number of continuous explanatory variables explain the same target through different dependency structures. Classical filters may remain sensitive to a single form of dependence, a single scale, or a specific discretization scheme; generalized entropy measures, on the other hand, typically require the parameters to be fixed at a single point. This study proposes a framework that evaluates the Sharma–Mittal entropy volumetrically across a two-dimensional parameter region rather than for a single parameter pair. For the continuous target and explanatory variables, the marginal, joint, and conditional densities are obtained using a Gaussian kernel density estimation; the conditional entropy and information gain surfaces are integrated across the region Ω = [0.05, 0.95]² in the α-β plane to define three indices: PICSME, which measures the conditional uncertainty volume; PIGSME, which measures the gain volume; and NIGSME, which is the ratio of this gain to the total entropy volume of the target. The method is supported by bandwidth consistency and the renormalization of conditional densities; thus, the issue of negative gain that can occur in the continuous variables is resolved, yielding positive and interpretable scores across all six datasets. It is formally demonstrated that the fact that the three indices produce the same ranking is not an empirical observation but rather the result of a monotonicity relationship valid under a fixed target entropy volume. The method is compared with Pearson and Spearman correlations, the Shannon information gain, mutual information, and random forest variable importance across six regression datasets (Airfoil Self-Noise, AirQualityUCI, BodyFat, Meteorology, Concrete, and WineQualityWhite) that differ in their sample size, dimensions, and application domain. The evaluation is not limited to ranking consistency; the out-of-sample prediction performance is measured using least-squares models on the top-k subsets, with rankings calculated from the training partition. The findings show that NIGSME exhibits a performance comparable to that of built-in filters, outperforms them on the Concrete and Meteorology datasets, and never ranks as the weakest method on any dataset. The results demonstrate that volumetric entropy metrics defined across the entire parameter space provide a feature-ranking tool that is independent of parameter selection for continuous variables. Full article

Accurate wind speed forecasting plays a crucial role in the safe and stable operation of wind farms and the efficient integration of renewable energy into modern power systems. However, wind speed exhibits complex spatiotemporal variations affected by diverse meteorological conditions, making high-precision prediction a long-standing bottleneck in wind power scheduling. This paper develops a U-shaped spatiotemporal feature fusion network named U-STNet, which realizes joint modeling of inter-turbine spatial correlations and multi-period long-range temporal dependencies. The model maps raw wind speed series to high-dimensional embeddings and adopts an encoder–decoder U-shaped architecture to complete feature encoding, reconstruction and multi-scale feature extraction, which effectively captures the inherent periodic and seasonal patterns of wind speed. Experiments on the SDWPF wind farm dataset show that U-STNet obtains competitive prediction accuracy across all multi-step forecasting horizons. Compared with traditional statistical models, recurrent neural networks and state-of-the-art Transformer baselines, the proposed method exhibits more stable error accumulation characteristics and superior long-step prediction performance. This verifies the effectiveness of jointly modeling turbine spatial topology and multi-scale temporal dependencies for wind speed forecasting. Full article

Accurately estimating latent heat flux (LE) across water-limited grassland ecosystems is critically hampered by strong land-surface heterogeneity and pronounced intra-annual variability. Here, we proposed a ConvTransformer framework by integrating MODIS remote sensing products, China Meteorological Forcing Dataset (CMFD) data, and eddy covariance observations from six grassland sites to estimate daily LE across the Inner Mongolia grasslands. The model was evaluated using a leave-one-site-out cross-validation strategy and compared with three widely used machine learning models, including random forest (RF), gradient boosting regression trees (GBRT), and support vector regression (SVR). Across the six validation sites, the ConvTransformer achieved an average R² of 0.69, an RMSE of 12.56 W m⁻², a Bias of 0.67 W m⁻², and an average KGE of 0.82. Although RF produced slightly higher R² values at several individual sites, the ConvTransformer exhibited the highest overall KGE and the most stable performance, indicating superior cross-site generalization. Based on the trained model, a 1 km daily LE dataset for the Inner Mongolia grasslands during 2003–2018 was generated. The estimated LE revealed a distinct decreasing gradient from southeast to northwest and marked seasonality, with summer dominating the annual latent heat exchange. These results suggest that the ConvTransformer constitutes an effective framework for regional LE estimation, while also offering a valuable alternative for ecohydrological studies and regional water-resource assessment in water-limited grassland ecosystems. Full article

Doppler Light Detection and Ranging (LIDAR) systems and a mesoscale meteorological model coupled with computational fluid dynamics (CFD) for the monitoring of low-level wind and turbulence have been extensively applied for the Hong Kong International Airport. This study represents the first application in Hong Kong to apply such techniques for the exploration of providing meteorological support for the operation of Unmanned Aircraft Systems (UASs) in a sandbox project in Hong Kong. The flight route under consideration is between the western coast of Hong Kong Island and an outlying island called Lamma Island, with a sea channel in between. Based on the LIDAR observations in three different prevailing wind directions, low-level turbulence may arise from wind flow disruptions by natural terrain and human-made buildings. Simulations of the wind and turbulence are attempted using the GPU-based FastEddy, with the turbulent kinetic energy equation being used to output the eddy dissipation rate (EDR). Comparisons between observed and simulated fields showed broadly consistent patterns across wind speed, wind direction, and EDR. Quantitative validation yielded RMSE of 1.35 m/s for wind speed, 28.4° for wind direction, and 0.032 m²/s² for EDR, with corresponding R² values of 0.72, 0.48, and 0.07, respectively. However, point-to-point comparison as in the scatter plot of the two datasets is still challenging, due to low correlation for EDR. Nonetheless, FastEddy is found to shed preliminary insights to generate reasonable simulations of low-level winds and turbulence to support the operation of UASs for the cases under study. These findings should be considered preliminary and exploratory given the limited number of case studies analyzed. More cases would need to be studied to find out the performance of FastEddy in other meteorological conditions. Full article

Accurate short-term building energy consumption forecasting is crucial for energy-system operational efficiency and demand-side management. Existing deep learning models heavily rely on historical data, making them costly for data-scarce buildings. Furthermore, their cross-building generalization ability is limited, requiring building-specific tuning that hinders large-scale deployment. To address these issues, this study proposes a novel framework based on large language models for short-term building energy consumption forecasting. It adapts large language models through parameter-efficient LoRA fine-tuning and incorporates building domain knowledge by using enhanced feature extraction modules and prompt design. Specifically, a prompt template rich in building physical semantics was designed to leverage the abundant pre-training knowledge of the large language model (LLM). This enables the model to avoid blindly fitting the data, directly aligning with building operating rules, providing a reasonable prediction basis even with limited data, and enhancing cross-building generalization. In addition, a cross-feature attention mechanism is designed to analyze the impact of dynamic meteorological features on energy consumption, thereby improving cross-climate scenario adaptability. Finally, to handle non-typical mutations in actual building operations, depthwise separable convolutional layers decompose residual components to filter out noise while preserving key features of anomalous occupancy patterns, thereby enhancing model robustness. Experiments on five real-world datasets have shown that the proposed framework outperforms state-of-the-art baselines, achieving an average improvement of 6.06% in the MAE and 4.80% in the RMSE. More importantly, it exhibits strong few-shot learning capabilities and extends to zero-shot forecasting. By reducing data dependency and enabling cross-building generalization, the framework developed in this work achieves scalable, low adaptation cost energy consumption forecasting from single buildings to clusters. Full article

Reliable modelling of monthly air temperature is relevant to station-scale climate assessment and the evaluation of meteorological data-driven models. However, station-scale monthly meteorological datasets often contain correlated and partially redundant predictors because thermal, moisture, precipitation, wind, and seasonal variables are jointly controlled by atmospheric and seasonal forcing. This study conducts an integrated comparative analysis of established regression and machine learning models for monthly mean air temperature modelling in Zonguldak, a humid coastal province in the Western Black Sea Region of Türkiye. Monthly meteorological observations from 2000 to 2022 were used to evaluate eight primary regression and machine-learning models: Partial Least Squares regression, Ridge, Lasso, ElasticNet, Support Vector Regression, Random Forest, Gradient Boosting, and Extreme Gradient Boosting. Ordinary Least Squares (OLS) and Huber regression were additionally included as reference models. The analysis retained the original meteorological predictors and jointly evaluated predictive accuracy, model stability, ablation sensitivity, and model-specific predictor relevance. Reduced-predictor and seasonality-only scenarios were examined to distinguish direct thermal reconstruction from broader climatological predictability. Model performance was assessed using repeated nested cross-validation, bootstrap summaries of performance variability, supplementary rolling-origin validation, and Wilcoxon signed-rank tests with Holm correction. Although the full-predictor models achieved high predictive accuracy, this performance largely reflected the direct thermal information contained in minimum and maximum air temperature. When these thermal predictors were excluded, MAE increased to approximately 1.13–1.22 °C and $R^2$ decreased to approximately 0.93–0.94. The seasonality-only scenario yielded MAE values of approximately 1.27–1.34 °C and R² values of approximately 0.92, indicating that the annual cycle accounted for a substantial proportion of monthly temperature predictability. The additional non-thermal meteorological predictors provided only limited improvement beyond the strong seasonal baseline. Overall, model performance depended on the predictor information available, and no single model family showed a consistent advantage across the evaluated scenarios. These findings highlight the importance of considering predictive accuracy together with model stability and predictor dependence in data-limited station-scale temperature modelling. Full article

Accurate aboveground biomass (AGB) estimation in subtropical forests is critical for regional carbon accounting and sustainable forest management. However, standardized multi-source feature screening and integrated machine learning–geostatistical analysis of AGB remain limited. This study integrated six heterogeneous datasets: Landsat-8 optical imagery, Sentinel-1 SAR, topographic, meteorological, soil data and the 2014 National Forest Inventory (NFI), and established 48 predictors in subtropical forests of Anhui Province, China. A two-stage variable selection framework was applied, with Pearson correlation screening reducing the initial 48 predictors to 36 less-correlated variables, followed by the recursive feature elimination (RFE) with 5-fold spatial block cross-validation for further predictor selection. Random Forest (RF), eXtreme Gradient Boosting (XGB), Empirical Bayesian Kriging Regression Prediction (EBKRP), hybrid RF_EBKRP and XGB_EBKRP models were evaluated. Stand age and stand density were dominant predictors in both RF and XGB, contributing 33.6% and 24.0% in RF and 36.5% and 17.3% in XGB, respectively. Elevation, precipitation, and canopy cover showed secondary importance, whereas vegetation indices contributed relatively little. RF_EBKRP achieved the highest prediction accuracy (R² = 0.77), reducing RMSE by 17.20% and 43.75% compared with RF and EBKRP, respectively. This study provides a reproducible RF–EBKRP workflow integrating nonlinear machine-learning prediction with geostatistical residual correction, supporting improved subtropical forest AGB mapping and management. Full article