Search Results (231)

Determining/predicting the environment dominates a variety of marine operations, such as route planning and offshore installation. Significant wave height (Hs) is a critical parameter-defining wave, a dominating marine load. Data-driven machine learning methods have been increasingly applied to Hs prediction, but challenges remain in hyperparameter tuning and spatial generalization. This study explores a novel effective approach for intelligent Hs forecasting for marine operations. Multiple automated machine learning (AutoML) frameworks, namely H2O, PyCaret, AutoGluon, and TPOT, have been systematically evaluated on buoy-based Hs prediction tasks, which reveal their advantages and limitations under various forecast horizons and data quality scenarios. The results indicate that PyCaret achieves superior accuracy in short-term forecasts, while AutoGluon demonstrates better robustness in medium-term and long-term predictions. To address the limitations of single-point prediction models, which often exhibit high dependence on localized data and limited spatial generalization, a multi-point data fusion framework incorporating Principal Component Analysis (PCA) is proposed. The framework utilizes Hs data from two stations near the California coast to predict Hs at another adjacent station. The results indicate that it is possible to realize cross-station predictions based on the data from adjacent (high relevance) stations. Full article

This article presents a comprehensive review of methods used for forecasting electricity consumption. The studies analyzed by the authors encompass both classical statistical models and modern approaches based on artificial intelligence, including machine-learning and deep-learning techniques. Electricity load forecasting is categorized into four time horizons: very short term, short term, medium term, and long term. The authors conducted a comparative analysis of various models, such as autoregressive models, neural networks, fuzzy logic systems, hybrid models, and evolutionary algorithms. Particular attention was paid to the effectiveness of these methods in the context of variable input data, such as weather conditions, seasonal fluctuations, and changes in energy consumption patterns. The article emphasizes the growing importance of accurate forecasts in the context of the energy transition, integration of renewable energy sources, and the management of the evolving electricity system, shaped by decentralization, renewable integration, and data-intensive forecasting demands. In conclusion, the authors highlight the lack of a universal forecasting approach and the need for further research on hybrid models that combine interpretability with high predictive accuracy. This review can serve as a valuable resource for decision-makers, grid operators, and researchers involved in energy system planning. Full article

This research focuses on medium-term load forecasting in a tropical region post-pandemic. This study presents one of the first attempts to analyze medium-term forecasting using half-hourly resolution in the Java-Bali power system post-COVID-19 period. The dataset comprises load measurements recorded every 30 min (48 data points per day) from 2014 to 2022. Three distinct methods, namely polynomial regression, split polynomial regression, and Long Short-Term Memory (LSTM) networks, were employed and compared to predict the electricity load demand. The analysis found that LSTM outperformed the other methods, exhibiting the lowest error rates with Mean Absolute Percentage Error (MAPE) at 3.86% and Root Mean Squared Error (RMSE) at 1247.93. Additionally, a consistent observation emerged, showing that all methods performed better in predicting load demand during nighttime hours (6 p.m. to 6 a.m.). The hypothesis is that data stability during nighttime, with fewer significant fluctuations, contributed to the improved prediction accuracy. These findings provide valuable insights for improving load forecasting in the post-pandemic tropical region and offer opportunities for enhancing power grid efficiency and reliability. Full article

The rapid proliferation of electric vehicles necessitates accurate forecasting of charging pile capacity for urban power system planning, yet existing methods for medium- to long-term prediction lack effective mechanisms to capture complex multi-factor relationships. To address this gap, a hybrid cointegration–BiLSTM framework is proposed for medium- to long-term load forecasting. Cointegration theory is leveraged to identify long-term equilibrium relationships between EV charging capacity and socioeconomic factors, effectively mitigating spurious regression risks. The extracted cointegration features and error correction terms are integrated into a bidirectional LSTM network to capture complex temporal dependencies. Validation using data from 14 cities in Hunan Province demonstrated that cointegration analysis surpassed linear correlation methods in feature preprocessing effectiveness, while the proposed model achieved enhanced forecasting accuracy relative to conventional temporal convolutional networks, support vector machines, and gated recurrent units. Furthermore, a 49% reduction in MAE and RMSE was observed when ECT-enhanced features were adopted instead of unenhanced groups, confirming the critical role of comprehensive feature engineering. Compared with the GRU baseline, the BiLSTM model yielded a 26% decrease in MAE and a 24% decrease in RMSE. The robustness of the model was confirmed through five-fold cross-validation, with ECT-enhanced features yielding optimal results. This approach provides a scientifically grounded framework for EV charging infrastructure planning, with potential extensions to photovoltaic capacity forecasting. Full article

Sea level rise (SLR) and increased urbanisation of coastal areas have exacerbated coastal flood threats, making them even more severe in important cultural sites. In this context, the role of hard coastal defences such as promenades and embankments needs to be carefully assessed. Here, a thorough investigation is conducted in Grado, one of the most significant coastal and historical towns in the Friuli Venezia Giulia region of Italy. Grado is located on a barrier island of the homonymous lagoon, the northernmost of the Adriatic Sea, and is prone to flooding from both the sea and the back lagoon. The mean and maximum sea levels from the historical dataset of Venice (1950–2023) were analysed using the Gumbel-type distribution, allowing for the identification of annual extremes based on their respective return periods (RPs). Grado and Trieste sea level datasets (1991–2023) were used to calibrate the statistics of the extremes and to calculate the local component (subsidence) of relative SLR. The research examined the occurrence of annual exceedance of the minimum threshold water level of 110 cm, indicating Grado’s initial notable marine ingression. The study includes a detailed analysis of flood impacts on the urban fabric, categorised into sectors based on the promenade elevation on the lagoon side, the most vulnerable to flooding. Inundated areas were obtained using a high-resolution digital terrain model through a GIS-based technique, assessing both the magnitude and exposure of the urban environment to flood risk due to storm surges, also considering relative SLR projections for 2050 and 2100. Currently, approximately 42% of Grado’s inhabited area is inundated with a sea level threshold value of 151 cm, which occurs during surge episodes with a 30-year RP. By 2100, with an optimistic forecast (SSP1-2.6) of local SLR of around +53 cm, the same threshold will be met with a surge of ca. 100 cm, which occurs once a year. Thus, extreme levels linked with more catastrophic events with current secular RPs will be achieved with a multi-year frequency, inundating more than 60% of the urbanized area. Grado, like Venice, exemplifies trends that may impact other coastal regions and historically significant towns of national importance. As a result, the generated simulations, as well as detailed analyses of urban sectors where coastal flooding may occur, are critical for medium- to long-term urban planning aimed at adopting proper adaptation measures. Full article

Nature-based solutions (NBS) have attracted increasing attention in local air quality and climate change adaptation plans as suitable measures to reduce health risks. Although several studies have reported health benefits from short-term urban cooling effects of NBS, medium- to long-term health benefits are still poorly understood. In this study, we assess the changes in long-term mortality related to temperature fluctuations induced by city-scale vegetation actuations in three Southern European cities. We performed two annual high-resolution simulations with the Weather Research and Forecasting model to anticipate the impact of future revegetation strategies on temperature in these urban areas. Further, we assessed the impact of temperature changes on health using a country-specific minimum mortality temperature (MMT) reported in scientific literature. It was found that NBS could provide non-negligible reductions of long-term mortality related to temperature regulation (central estimate of 4.1, 1.2, and 3.4 cases avoided per year in Madrid, Milano, and Bologna, respectively). The effect of vegetation is site-dependent, and the cooling effect explains most of the benefits, especially in densely built-up areas of the cities analyzed. Future research should combine short/long-term temperature effects with other indirect implications (air quality, mental health) in the context of climate change. Full article

In the context of increasingly severe climate change, studying the relationship between climate factors and vegetation dynamics is crucial for ecological conservation and sustainable development. This study focuses on the Oujiang River Basin from 1981 to 2022, aiming to quantitatively model the interactions among temperature, precipitation, the NDVI, and the LAI. Addressing the lack of approaches for forecasting high-resolution LAI data and existing LAI data that are usually interpreted from NDVI data, we proposed a two-step inversion framework: first, modeling the response of the NDVI to climate variables; second, predicting the LAI using the NDVI as a mediating variable. By integrating long-term remote sensing datasets (GIMMS and MODIS NDVI) with meteorological data and applying trend analysis, spatial correlation analysis, and clustering techniques (K-Means and Possibilistic C-Means), we identified spatial heterogeneity in vegetation response patterns. The study results showed that (1) climate factors have a distinctly spatially heterogeneous impact on the NDVI and LAI; (2) temperature is identified as the dominant factor in most regions; and (3) the LAI prediction model based on the climate factors NDVI and NDVI–LAI relationships shows good accuracy in the medium-to-high range of the LAI, with an R² value ranging from 0.516 to 0.824. This study provides a scalable approach to improve LAI estimation and monitor vegetation dynamics in complex terrain under changing climate conditions. Full article

This study investigates the theoretical foundations and practical advantages of fractional-order optimization in computational machine learning, with a particular focus on stock price forecasting using long short-term memory (LSTM) networks. We extend several widely used optimization algorithms—including Adam, RMSprop, SGD, Adadelta, FTRL, Adamax, and Adagrad—by incorporating fractional derivatives into their update rules. This novel approach leverages the memory-retentive properties of fractional calculus to improve convergence behavior and model efficiency. Our experimental analysis evaluates the performance of fractional-order optimizers on LSTM networks tasked with forecasting stock prices for major companies such as AAPL, MSFT, GOOGL, AMZN, META, NVDA, JPM, V, and UNH. Considering four metrics (Sharpe ratio, directional accuracy, cumulative return, and MSE), the results show that fractional orders can significantly enhance prediction accuracy for moderately volatile stocks, especially among lower-cap assets. However, for highly volatile stocks, performance tends to degrade with higher fractional orders, leading to erratic and inconsistent forecasts. In addition, fractional optimizers with short-memory truncation offer a favorable trade-off between computational efficiency and modeling accuracy in medium-frequency financial applications. Their enhanced capacity to capture long-range dependencies and robust performance in noisy environments further justify their adoption in such contexts. These results suggest that fractional-order optimization holds significant promise for improving financial forecasting models—provided that the fractional parameters are carefully tuned to balance memory effects with system stability. Full article

This research presents an advanced methodology for smart management of energy losses in electrical distribution networks by leveraging deep neural network architectures. The primary objective is to enhance the accuracy of short-term forecasting for nodal loads and corresponding energy losses, enabling more efficient and intelligent grid operation. Two predictive approaches were explored: the first involves separate forecasting of nodal loads followed by loss calculations, while the second directly estimates network-wide energy losses. For model implementation, Long Short-Term Memory (LSTM) networks and the enhanced Residual Network (eResNet) architecture, developed at the Institute of Electrodynamics of the National Academy of Sciences of Ukraine, were utilized. The models were validated using retrospective data from a Ukrainian Distribution System Operator (DSO) covering the period from 2017 to 2019 with 30 min sampling intervals. An adapted CIGRE benchmark medium-voltage network was employed to simulate real-world conditions. Given the presence of anomalies and missing values in the operational data, a two-stage preprocessing algorithm incorporating DBSCAN clustering was applied for data cleansing and imputation. The results indicate a Mean Absolute Percentage Error (MAPE) of just 3.29% for nodal load forecasts, which significantly outperforms conventional methods. These findings affirm the feasibility of integrating such models into Smart Grid infrastructures to improve decision-making, minimize operational losses, and reduce the costs associated with energy loss compensation. This study provides a practical framework for data-driven energy loss management, emphasizing the growing role of artificial intelligence in modern power systems. Full article

Balancing electricity production and distribution remains a central challenge in modern energy systems, especially with the increasing penetration of renewable sources that introduce variability and uncertainty. In this context, accurate forecasting of electricity demand is essential for grid stability and operational efficiency. This study addresses the problem of hourly electricity demand forecasting in Italy using recurrent neural networks (RNNs), particularly long short-term memory (LSTM) models, which are designed to capture complex temporal dependencies in time series data. Utilizing real consumption data from Terna—Rete Elettrica Nazionale S.p.A.—for the years 2022 and 2023, we developed and tested an LSTM model capable of predicting national hourly demand with Root Mean Squared Error (RMSE) consistently below 2%. The model’s forecasts show strong agreement with official data provided by Terna, accurately capturing demand peaks and seasonal trends over both short- and medium-term horizons. In addition to evaluating predictive performance, this work proposes a reproducible methodology applicable to other national contexts or similar forecasting problems. Our findings suggest that, while data-driven models offer robust and replicable results, further improvements may require the integration of system-specific knowledge to address persistent limitations in forecasting extreme events or structural anomalies. Full article

Climate change requires efficient water resource management, especially in regions where viticulture is developing. This study evaluates the water requirements, precipitation deficits, and irrigation needs of vineyards in two locations in southern Poland. The analysis covers both a reference period (1931–2020) and a forecast period (2030–2100), based on two climate change scenarios: RCP 4.5 and RCP 8.5. Grapevine water requirements were estimated using a crop coefficient tailored to Poland’s agroclimatic conditions, combined with meteorological data on air temperature and precipitation. Monthly crop coefficient values were calculated as the ratio of grapevine potential evapotranspiration, estimated using the Penman–Monteith method, to reference evapotranspiration, calculated using the Treder approach for the period 1981–2010. Precipitation deficits were assessed for normal, medium dry, and very dry years using the Ostromęcki method. Irrigation water demand was estimated for light, medium, and heavy soils using the Pittenger method. The results indicate a significant increase in both water demand and precipitation deficits in the forecast period, regardless of the scenario. In very dry years, irrigation will be necessary for all soil types. In medium dry years, water deficits will primarily affect vineyards on light soils. These findings underscore the urgent need for improvements in irrigation planning, especially in areas with low soil water. They offer practical insights for estimating future water storage needs and implementing precision irrigation adapted to changing climate conditions. Adopting such adaptive strategies is essential for sustaining vineyard productivity and improving water use efficiency. This study also supports the integration of climate projections into regional planning and calls for investment in innovative, water-saving technologies to strengthen the long-term resilience of Poland’s wine industry. Full article

Ocean forecasting is critical for various applications and is essential for understanding air–sea interactions, which contribute to mitigating the impacts of extreme events. While data-driven forecasting models have demonstrated considerable potential and speed, they often primarily focus on spatial variations while neglecting temporal dynamics. This paper presents the TSformer, a novel non-autoregressive spatio-temporal transformer designed for medium-range ocean eddy-resolving forecasting, enabling forecasts of up to 30 days in advance. We introduce an innovative hierarchical U-Net encoder–decoder architecture based on 3D Swin Transformer blocks, which extends the scope of local attention computation from spatial to spatio-temporal contexts to reduce accumulation errors. The TSformer is trained on 28 years of homogeneous, high-dimensional 3D ocean reanalysis datasets, supplemented by three 2D remote sensing datasets for surface forcing. Based on the near-real-time operational forecast results from 2023, comparative performance assessments against in situ profiles and satellite observation data indicate that the TSformer exhibits forecast performance comparable to leading numerical ocean forecasting models while being orders of magnitude faster. Unlike autoregressive models, the TSformer maintains 3D consistency in physical motion, ensuring long-term coherence and stability. Furthermore, the TSformer model, which incorporates surface auxiliary observational data, effectively simulates the vertical cooling and mixing effects induced by Super Typhoon Saola. Full article

The forecasting of high-water-cut oil well production faces challenges of strong nonlinearity and nonstationarity due to reservoir heterogeneity and multiscale dynamic characteristics. This study proposes a hybrid CEEMDAN-SR-BiLSTM framework based on a “decomposition-feature enhancement-integration” architecture. The framework employs Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to suppress mode mixing, reconstructs high-, medium-, and low-frequency subsequences using Hilbert-Huang Transform (HHT) combined with tercile thresholding, and finally achieves multiscale feature fusion prediction through a Bayesian-optimized bidirectional long short-term memory network (BiLSTM). Interpretability analysis based on SHapley Additive exPlanations (SHAP) values reveals the contribution degrees of parameters such as water injection volume and flowing pressure to different frequency components, establishing a mapping between production data features and physical mechanisms of oil well production. This mapping, integrated with physical mechanisms including wellbore transient flow, injection-production response lag, and reservoir pressure evolution, enables mechanistic interpretation of production phenomena and quantitative decoupling and prediction of multiscale dynamics. Experimental results show that the framework achieves a root-mean-square error (RMSE) of 3.75 in forecasting a high-water-cut well (water cut = 87.6%) in the Qaidam Basin, reducing errors by 26.0% and 50.0% compared to CEEMDAN-BiLSTM and BiLSTM models, respectively, with a coefficient of determination (R²) reaching 0.954. Full article

Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–decoder model, to forecast PV power generation. TiDE compresses historical time series and covariates into latent representations via residual connections and reconstructs future values through a temporal decoder, capturing both long- and short-term dependencies. We trained the model using data from 2020 to 2022 from Australia’s Desert Knowledge Australia Solar Centre (DKASC), with 2023 data used for testing. Forecast accuracy was evaluated using the $R^2$ coefficient of determination, mean absolute error (MAE), and root mean square error (RMSE). In the 5 min ahead forecasting test, TiDE demonstrated high short-term accuracy with an $R^2$ of 0.952, MAE of 0.150, and RMSE of 0.349, though performance declines for longer horizons, such as the 1 h ahead forecast, compared to other algorithms. For one-day-ahead forecasts, it achieved an $R^2$ of 0.712, an MAE of 0.507, and an RMSE of 0.856, effectively capturing medium-term weather trends but showing limited responsiveness to sudden weather changes. Further analysis indicated improved performance in cloudy and rainy weather, and seasonal analysis reveals higher accuracy in spring and autumn, with reduced accuracy in summer and winter due to extreme conditions. Additionally, we explore the TiDE model’s sensitivity to input environmental variables, algorithmic versatility, and the implications of forecasting errors on PV grid integration. These findings highlight TiDE’s superior forecasting accuracy and robust adaptability across weather conditions, while also revealing its limitations under abrupt changes. Full article

Accurate and reliable precipitation prediction remains a significant challenge due to an incomplete understanding of regional meteorological dynamics and limitations in forecasting routine weather events. To overcome these challenges, we propose a novel model, DC-CNN-BiLSTM, which integrates a dilation causal convolutional neural network (DC-CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network. The DC-CNN component, by fusing causal and dilated convolutions, extracts multi-scale spatial features from time series data. In parallel, the BiLSTM module leverages bidirectional memory cells to capture long-term temporal dependencies. This integrated approach effectively links localized meteorological inputs with broader hydrological responses. Experimental evaluation demonstrates that the DC-CNN-BiLSTM model significantly outperforms traditional models. Specifically, the model improves the Root Mean Square Error (RMSE) by 9.05% compared to ConvLSTM and by 32.3% compared to ConvGRU, particularly in forecasting medium- to long-term precipitation. In conclusion, our results validate the benefits of incorporating advanced spatio-temporal feature extraction techniques for precipitation forecasting, ultimately improving disaster preparedness and resource management. Full article