Search Results (164)

This article suggests a brief and integrated methodology for enhancing the mean estimation in a finite population using the pre-specified median of the target variable in conjunction with quantile-related auxiliary measurements. Although a number of conventional ratio and regression estimators are reliant on the average of the auxiliary variable, the current study presents new exponential-type families that combine the variable’s known median under investigation with the dispersion-related characteristics of supplementary information. The estimators are constructed and analyzed theoretically, under Simple Random Sampling Without Replacement (SRSWOR), and the minimum expression of the MSE under optimal conditions is obtained. The results are confirmed using simulated Kumaraswamy–Gamma populations and through several real-world datasets, such as those on education, wheat production, U.S. cereal consumption, and solar radiation data (HI-SEAS weather station, September–December 2016). The findings consistently demonstrate that the developed estimators provide a substantially lower MSE and greater percentage relative efficiency (PRE) relative to conventional estimators. These applications indicate that the median-based unified framework can be used to give more precise and efficient mean estimation in several fields, comprising agriculture, nutrition, and education, as well as meteorological and environmental research. Full article

In this paper, we present a model for calculating the State of Health (SOH) of battery energy storage systems (BESSs) and battery capacity percentage, specifically tailored for grid-scale applications in Thailand. Unlike conventional models that rely on controlled laboratory data, the proposed approach uses actual operating temperature data for both development and validation, enabling a more correct assessment of battery performance under the high-temperature conditions typical of tropical climates. A set of coefficients derived from real operating data was incorporated, and the SOH results deviated by only 0.05% from theoretical values, proving high predictive accuracy beyond laboratory settings. Our findings revealed that capacity degradation rates in Thailand are approximately 20–60% higher than under the best conditions. Over a 10-year warranty period, battery capacity declined to approximately 80% at the lowest temperature range, 60% at the average range, and 40% at the highest range. By calculating both SOH and remaining capacity, the model provides a practical tool for lifespan prediction and system planning. Based on these findings, it is recommended that thermal management systems support battery operating temperatures between 25 and 35 °C and limit cooling losses below 10%, thereby mitigating energy yield degradation and ensuring efficient BESS operation. These results highlight the importance of incorporating real environmental data into degradation modeling. Future studies should include long-term monitoring of operating temperatures and cooling demand, economic analyses to enhance operational efficiency, and evaluation of external heat loads, particularly from solar radiation, to further refine predictions for tropical climates. Full article

The rising frequency of heat-related illnesses (HRIs) under climate change presents urgent public health challenges, particularly in urban environments. This study develops an explainable machine learning (ML) model to predict HRI risk using metrological data from seven major South Korean metropolitan cities between May and September 2021–2024. We applied eXtreme Gradient Boosting (XGBoost) to model relationships between daily meteorological variables, including maximum and mean daily temperatures, humidity, solar radiation, wind speed, and precipitation, and HRI occurrence. Model performance was validated using 2025 data and demonstrated strong predictive accuracy, with area under the curve (AUC) values 0.895. To enhance interpretability, Shapley Additive exPlanations (SHAP) analysis identified mean daily temperature, solar radiation, and minimum temperature as the strongest contributors to HRI risk. Time-series comparisons of predicted and actual HRI occurrences further validated the model’s effectiveness in real-world settings. These findings underscore the potential of eXplainable Artificial Intelligence (XAI) for localized health-risk forecasting and support a data-driven basis for developing early warning systems for climate-sensitive diseases to guide proactive public health planning amid escalating urban heat risks. Full article

The Penman–Monteith formula (P-M) is a well-established indirect method for estimating reference evapotranspiration (ET₀). The key input for this equation is global solar radiation (H). When real data are unavailable, other weather parameters are used to estimate H. In this study, sixteen years’ worth daily registers of H, sunshine duration (S), and air temperature (t) from 10 sites across Poland were used to determine coefficients for the Angström–Prescott (A-P) and Hargreaves–Sammani (H-S) equations. The H values obtained with locally calibrated, general Polish and global A-P and H-S equations were applied to the P-M formula. The ET₀ results thus obtained were compared to those derived with the P-M method and measured solar radiation data. The method of determination of the radiation component had a significant but sometimes unexpected impact on the ET₀ values. The better predictive power of the solar radiation model usually resulted in better accuracy of the evapotranspiration estimation; however, there were exceptions to this rule. Full article

Accurate cooling load forecasting in chiller units is critical for building energy optimization, yet remains challenging due to non-stationary nonlinear dynamics driven by coupled external weather variability (solar radiation, ambient temperature) and internal thermal loads. Conventional models fail to capture the spatiotemporal coupling inherent in load time series, violating their stationarity assumptions. To address this, this research proposes OptiNet, a spatiotemporal forecasting framework integrating patch-specific dynamic filtering with graph neural networks. OptiNet partitions multi-sensor data into non-overlapping time patches to develop a dynamic spatiotemporal graph. A learnable routing mechanism then performs adaptive dependency filtering to capture time-varying temporal–spatial correlations, followed by graph convolution for load prediction. Validated on long-term industrial logs (52,075 multi-sensor samples at 20 min; district cooling plant in Zhangjiang, Shanghai, with multiple chillers, towers, pumps, building meters, and a weather station), OptiNet achieves consistently lower MAE and MSE than Graph WaveNet across 6–144-step horizons and sampling frequencies of 20–60 min; among 30 set-tings it leads in 26, with MSE reductions up to 27.8% (60 min, 72-step) and typical long-horizon (72–144 steps) gains of ≈2–18% MSE and ≈1–15% MAE. Crucially, the model provides interpretable spatial-temporal dependencies (e.g., “Zone B solar radiation influences Unit 2 load with 4-h lag”), enabling data-driven chiller sequencing strategies that reduce electricity consumption by 12.7% in real-world deployments—directly advancing energy-efficient building operations. Full article

Solar panel deployment is vital to generate clean energy and reduce carbon emissions, but sustaining energy output requires regular monitoring and maintenance. This is particularly critical in countries with harsh environmental conditions, such as Qatar, where high dust density reduces solar radiation reaching panels, thereby lowering generating efficiency and increasing maintenance costs. This paper introduces a data-driven model that uses the relationship between generated and consumed energy to track changes in solar panel performance. By applying statistical analysis to real and simulated data, the model identifies when efficiency losses are within the parameters of normal variation (e.g., daily fluctuations) and when they are likely caused by dust accumulation or system ageing. The findings demonstrate that the model provides a reliable and cost-effective way to support timely cleaning and maintenance decisions. It offers decision-makers a practical tool to improve residential solar panel management, reducing unnecessary costs, and ensuring more consistent renewable energy generation. Full article

This study develops an explainable machine learning framework for wildfire prediction across Australia, integrating region-specific models and feature attribution to identify key environmental drivers. Three wildfire indicators, Estimated Fire Area (FA), Mean Fire Brightness Temperature (FBT), and Fire Radiative Power (FRP), were modeled using Lasso, Random Forest, LightGBM, and XGBoost. Performance metrics (RMSEC, RMSECV, RMSEP) confirmed strong calibration and generalization, with Tasmania and Queensland achieving the lowest prediction errors for FA and FRP, respectively. Feature importance and SHAP analyses revealed that soil moisture, solar radiation, precipitation, and humidity variability are dominant predictors. Extremes and variance-based measures proved more influential than mean climatic values, indicating that fire dynamics respond non-linearly to environmental fluctuations. Lasso models captured stable linear dependencies in arid regions, while ensemble models effectively represented complex interactions in tropical climates. The results highlight a hierarchical process where cumulative soil and radiation stress establish fire potential, and short-term meteorological variability drives ignition and spread. Projected climate shifts, declining soil water and increased radiative load, are likely to intensify these drivers. The framework supports interpretable, region-specific mitigation planning and paves the way for incorporating generative AI and multi-source data fusion to enhance real-time wildfire forecasting. Full article

In recent years, the widespread adoption of photovoltaic (PV) panels for electricity generation has provided significant momentum toward sustainable energy goals. However, it has been observed that the accumulation of dust and contaminants on panel surfaces markedly reduces efficiency by blocking solar radiation from reaching the surface. Consequently, dust detection has become a critical area of research into the energy efficiency of PV systems. This study proposes SolPowNet, a novel Convolutional Neural Network (CNN) model based on deep learning with a lightweight architecture that is capable of reliably distinguishing between images of clean and dusty panels. The performance of the proposed model was evaluated by testing it on a dataset containing images of 502 clean panels and 340 dusty panels and comprehensively comparing it with state-of-the-art CNN-based approaches. The experimental results demonstrate that SolPowNet achieves an accuracy of 98.82%, providing 5.88%, 3.57%, 4.7%, 18.82%, and 0.02% higher accuracy than the AlexNet, VGG16, VGG19, ResNet50, and Inception V3 models, respectively. These experimental results reveal that the proposed architecture exhibits more effective classification performance than other CNN models. In conclusion, SolPowNet, with its low computational cost and lightweight structure, enables integration into embedded and real-time applications. Thus, it offers a practical solution for optimizing maintenance planning in photovoltaic systems, managing panel cleaning intervals based on data, and minimizing energy production losses. Full article

Model-based simulation of farmland evapotranspiration and crop growth facilitates precise monitoring of crop and farmland dynamics with high efficiency, real-time responsiveness, and continuity. However, there are still significant limitations in using crop models to simulate the dynamic process of evapotranspiration and cotton growth in mulched drip-irrigated cotton fields under different irrigation gradients. The SWAP crop growth model effectively simulates crop growth. However, the original SWAP model lacks a dedicated module to consider the impact of mulching on cotton field evapotranspiration and cotton dry matter mass. Therefore, in this study, the source codes of the soil moisture, evapotranspiration, and crop growth modules of the SWAP model were improved. The evapotranspiration and cotton growth data of the mulched drip-irrigated cotton fields under three irrigation treatments (W1 = 3360 m³·hm⁻², W2 = 4200 m³·hm⁻², and W3 = 5040 m³·hm⁻²) in 2023 and 2024 at the Xinjiang Modern Water-saving Irrigation Key Experimental Station of the Corps were used to verify the simulation accuracy of the improved SWAP model. Research shows the following: (1) The average relative errors of the simulated evapotranspiration, leaf area index, and dry matter weight of cotton in the improved SWAP crop growth model are all <20% compared with the measured values. The root means square errors of the three treatments (W1, W2, and W3) ranged from 0.85 to 1.38 mm, from 0.03 to 0.18 kg·hm⁻², and 55.01 to 69 kg·hm⁻², respectively. The accuracy of the improved model in simulating evapotranspiration and cotton growth in the mulched cotton field increased by 37.49% and 68.25%, respectively. (2) The evapotranspiration rate of cotton fields is positively correlated with the irrigation water volume and is most influenced by meteorological factors such as temperature and solar radiation. During the flowering stage, evapotranspiration accounted for 62.83%, 62.09%, 61.21%, 26.46%, 40.01%, and 38.8% of the total evapotranspiration. Therefore, the improved SWAP model can effectively simulate the evaporation and transpiration of the mulched drip-irrigated cotton fields in the Manas River Basin. This study provides a scientific basis for the digital simulation of mulched farmland in the arid regions of Northwest China. Full article

The accurate forecasting of solar power generation is becoming increasingly important in the context of renewable energy integration and intelligent energy management. The variability of solar radiation, caused by changing meteorological conditions and diurnal cycles, complicates the planning and control of photovoltaic systems and may lead to imbalances in supply and demand. This study aims to identify the most effective exponential smoothing approach for real-world PV power forecasting using actual hourly generation data from a 9 MW solar power plant in the Kyiv region, Ukraine. Four exponential smoothing techniques are analysed: Classic, a Modified classic adapted to daily generation patterns, Holt’s linear trend method, and the Holt–Winters seasonal method. The models were implemented in Microsoft Excel (Microsoft 365, version 2408) using real measurement data collected over six months. Forecasts were generated one hour ahead, and optimal smoothing constants were identified via RMSE minimisation using the Solver Add-in. Substantial differences in forecasting accuracy were observed. The Classic simple exponential smoothing model performed worst, with an RMSE of 1413.58 kW and nMAE of 9.22%. Holt’s method improved trend responsiveness (RMSE = 1052.79 kW, nMAE = 5.96%), but still lacked seasonality modelling. Holt–Winters, which incorporates both trend and seasonality, achieved a strong balance (RMSE = 1031.00 kW, nMAE = 3.7%). The best performance was observed with the modified simple exponential smoothing method, which captured the daily cycle more effectively (RMSE = 166.45 kW, nMAE = 0.84%). These results pertain to a one-step-ahead evaluation on a single plant and an extended validation window; accuracy is dependent on meteorological conditions, with larger errors during rapid cloud transi. The study identifies forecasting models that combine high accuracy with structural simplicity, intuitive implementation, and minimal parameter tuning—features that make them well-suited for integration into lightweight real-time energy control systems, despite not being evaluated in terms of runtime or memory usage. The modified simple exponential smoothing model, in particular, offers a high degree of precision and interpretability, supporting its integration into operational PV forecasting tools. Full article

This paper proposes a new family of robust estimators of means, depending on the Orthogonalized Gnanadesikan–Kettenring (OGK) covariance matrix. These estimators are computationally feasible and robust replacements of the Minimum Covariance Determinant (MCD) estimator in survey sampling contexts involving auxiliary information. With the growing popularity of outliers in environmental data, as in the case of measuring solar radiation, conventional estimators like the sample mean or the Ordinary Least Squares (OLS) regression-based estimators are both biased and unreliable. The suggested OGK-based exponential-type estimators combine robust measures of location and dispersion and have a considerable advantage in the estimation of the population mean when auxiliary variables such as temperature are highly correlated with the variable of interest. The MSE property of OGK-based estimators is also obtained through a detailed theoretical derivation with the expressions of optimal weights. Performance was further proved using real-world and simulated data on solar radiation, as well as by demonstrating lower MSEs and higher PREs in comparison to MCD-based estimators. These results show that OGK-based estimators are highly efficient and robust in actual and artificially contaminated situations and hence are a good option in robust survey sampling and environmental data analysis. Full article

Advances in machine learning have improved the ability to predict critical environmental conditions, including solar radiation levels that, while essential for life, can pose serious risks to human health. In Ecuador, due to its geographical location and altitude, UV radiation reaches extreme levels. This study presents the development of a chatbot system driven by a hybrid artificial intelligence model, combining Random Forest, CatBoost, Gradient Boosting, and a 1D Convolutional Neural Network. The model was trained with meteorological data, optimized using hyperparameters (iterations: 500–1500, depth: 4–8, learning rate: 0.01–0.3), and evaluated through MAE, MSE, R², and F1-Score. The hybrid model achieved superior accuracy (MAE = 13.77 W/m², MSE = 849.96, R² = 0.98), outperforming traditional methods. A 15% error margin was observed without significantly affecting classification. The chatbot, implemented via Telegram and hosted on Heroku, provided real-time personalized alerts, demonstrating an effective, accessible, and scalable solution for health safety and environmental awareness. Furthermore, it facilitates decision-making in the efficient generation of renewable energy and supports a more sustainable energy transition. It offers a tool that strengthens the relationship between artificial intelligence and sustainability by providing a practical instrument for integrating clean energy and mitigating climate change. Full article

Conventional grain monitoring systems often rely on isolated data points (e.g., point-based temperature measurements), limiting holistic condition assessment. This study proposes a novel Mechanism and Data Driven (MDD) framework that integrates physical mechanisms with real-time sensor data. The framework quantitatively analyzes solar radiation and external air temperature effects on silo boundaries and introduces a novel interpolation-optimized model parameter initialization technique to enable comprehensive grain condition perception. Rigorous multidimensional validation confirms the method’s accuracy: The novel initialization technique achieved high precision, demonstrating only 1.89% error in Day-2 low-temperature zone predictions (27.02 m² measured vs. 26.52 m² simulated). Temperature fields were accurately reconstructed (≤0.5 °C deviation in YOZ planes), capturing spatiotemporal dynamics with ≤0.45 m² maximum low-temperature zone deviation. Cloud map comparisons showed superior simulation fidelity (SSIM > 0.97). Further analysis revealed a 22.97% reduction in total low-temperature zone area (XOZ plane), with Zone 1 (near south exterior wall) declining 27.64%, Zone 2 (center) 25.30%, and Zone 3 20.35%. For dynamic evolution patterns, high-temperature zones exhibit low moisture (<14%), while low-temperature zones retain elevated moisture (>14%). A strong positive correlation between temperature and relative humidity fields; temperature homogenization drives humidity uniformity. The framework enables holistic monitoring, providing actionable insights for smart ventilation control, condensation risk warnings, and mold prevention. It establishes a robust foundation for intelligent grain storage management, ultimately reducing post-harvest losses. Full article

Bifacial Photovoltaic (bPV) technology is rapidly becoming the standard in the solar photovoltaic (PV) industry due to its ability to capture reflected radiation and generate additional energy. This experimental study analyses the electrical performance of bPV modules under specific installation conditions, including varying heights, module tilt angles (MTA), and surface reflectivity. The methodology combines controlled indoor testing with outdoor experiments that replicate real-world operating environments. The outdoor test setup was carefully designed and included dual data acquisition systems: one with independent sensors and another with wireless telemetry for data transfer from the inverter. A thermal performance model was used to estimate energy output and was benchmarked against experimental measurements. All electrical parameters were obtained in accordance with international standards, including current-voltage characteristic (I–V curve) corrections, using calibrated instruments to monitor irradiance and temperature. Indoor measurements under Standard Test Conditions yielded at bifaciality coefficient $\phi =0.732$, a rear bifacial power gain $BiFi=0.285$, and a relative bifacial gain $BiF{i}_{rel}=9.4\%$. The outdoor configuration employed volcanic red stone (Tezontle) as a reflective surface, simulating a typical mid-latitude installation with modules mounted 1.5 m above ground, tilted from 0° to 90° regarding floor and oriented true south. The study was conducted at a site located at 18.8° N latitude during the early summer season. Results revealed significant non-uniformity in rear-side irradiance, with a 32% variation between the lower edge and the centre of the bPV module. The thermal model used to determine electrical performance provides power values higher than those measured in the time interval between 10 a.m. and 3 p.m. Maximum energy output was observed at a MTA of $0°$, which closely aligns with the optimal summer tilt angle for the site’s latitude. Bifacial energy gain decreased as the MTA increased from $0°$ to $90°$. These findings offer practical, data-driven insights for optimizing bPV installations, particularly in regions between $15°$ and $30°$ north latitude, and emphasize the importance of tailored surface designs to maximize performance. Full article

Heat stress is one of the main welfare and productivity problems faced by dairy cattle in Mediterranean climates. The main objective of this work is to predict heat stress in livestock from shade-seeking behavior captured by computer vision, combined with some climatic features, in a completely non-invasive way. To this end, we evaluate two soft computing algorithms—Random Forests and Neural Networks—clarifying the trade-off between accuracy and interpretability for real-world farm deployment. Data were gathered at a commercial dairy farm in Titaguas (Valencia, Spain) using overhead cameras that counted cows in the shade every 5–10 min during summer 2023. Each record contains the shaded-cow count, ambient temperature, relative humidity, and an exact timestamp. From here, three thermal indices were derived: the current THI, the previous-night mean THI, and the day-time accumulated THI. The resulting dataset covers 75 days and 6907 day-time observations. To evaluate the models’ performance a 5-fold cross-validation is also used. The results show that both soft computing models outperform a single Decision Tree baseline. The best Neural Network (3 hidden layers, 16 neurons each, learning rate $={10}^{-3}$) reaches an average RMSE of $14.78$, while a Random Forest (10 trees, depth $=5$) achieves $14.97$ and offers the best interpretability. Daily error distributions reveal a median RMSE of $13.84$ and confirm that predictions deviate less than one hour from observed shade-seeking peaks. Although the dataset came from a single farm, the results generalized well within the observed range. However, the models could not accurately predict the exact number of cows in the shade. This suggests the influence of other variables not included in the analysis (such as solar radiation or wind data), which opens the door for future research. Full article