Wind Speed Forecasting Research Articles

Multistep short‐term wind speed prediction with rank pooling and fast Fourier transformation

AbstractShort‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting.

Short-term wind speed interval prediction using improved quality-driven loss based gated multi-scale convolutional sequence model

Efficient estimation of the uncertainty associated with wind speed forecast is crucial for evaluating wind farms' power quality and operation. Typically, the performance of prediction interval (PI) generating models; is restricted in terms of computational efficiency inheritably from the sequential data processing; whereas restrictions in forecast quality are derived from the PI generation techniques. This paper presents an efficient Gated Multi-Scale Convolutional Sequence Model (GMSCSM) to forecast wind speed PIs. GMSCSM while conserving the ‘recurrence’ of LSTMs also offers ‘parallel input’ advantage of CNNs for better computational efficiency which is highly desirable for short-term forecasting models. In addition, capturing features at various scales in the sequence, GMSCSM learns both local details and global context which is vital for multi-horizon forecasts. The model generates quality PIs utilizing an improved quality-driven loss which we proposed by invoking calibration assessment in its existing definition. Forecasts generated for eight different datasets obtained from two different wind farms show an improvement of 30 % and 6 % in the average coverage width criterion index while reducing the model training time to nearly half and one third of the respective values obtained from traditional and LSTM based models which showcases the proposed model's excellent prediction capability and efficiency.

Forecasting High Wind Events in the HRRR Model over Wyoming and Colorado. Part I: Evaluation of Wind Speeds and Gusts

Abstract Strong wind events cause significant societal damage ranging from loss of property and disruption of commerce to loss of life. Over portions of the United States, the strongest winds occur in the cold season and may be driven by interactions with the terrain (downslope winds, gap flow, and mountain wave activity). In the first part of this two-part series, we evaluate the High-Resolution Rapid Refresh (HRRR) model wind speed and gust forecasts for the 2016–22 winter months over Wyoming and Colorado, an area prone to downslope windstorms and gap flows due to its complex topography. The HRRR model exhibits a positive bias for low wind speeds/gusts and a large negative bias for strong wind speeds/gusts. In general, the model misses many strong wind events, but when it does predict strong winds, there is a high false alarm probability. An analysis of proxies for surface winds is conducted. Specifically, 700- and 850-mb (1 mb = 1 hPa) geopotential height gradients are found to be good proxies for strong wind speeds and gusts at two wind-prone locations in Wyoming. Given the good agreement between low-level height gradients and surface wind speeds yet a strong negative bias for strong wind speeds and gusts, there is a potential shortcoming in the boundary layer physics in the HRRR model with regard to predicting strong winds over complex terrain, which is the focus of the second part of this two-part study. Last, the sites with the largest strong wind speed bias are found to mostly sit on the leeward side of high mountains, suggesting that the HRRR model performs poorly in the prediction of downslope windstorms. Significance Statement We investigate the performance of the High-Resolution Rapid Refresh (HRRR) model with respect to strong wintertime wind speeds and gusts over the complex terrain of Wyoming and Colorado. We show that the overall performance of the HRRR model is low with regard to strong wind speed and wind gust forecasts across the investigated winter seasons, with a large negative bias in predicted strong wind speeds and gusts and a small positive bias for weak wind speeds and gusts. The largest biases are found to be on the leeward side of high mountains, indicating poor prediction of downslope winds. This study also utilizes National Weather Service forecasting metrics to understand their performance with respect to strong wind forecasts, and we find that they provide skill in forecasting these events.

Arctic short-term wind speed forecasting based on CNN-LSTM model with CEEMDAN

Accurate wind speed forecasting is of great significance for the utilization of Arctic wind energy resources. The traditional single model is difficult to fully depict the nonlinearity of wind speed and its wide range of variations. In this paper, a hybrid model is proposed for multi-step wind speed forecasting, which combined complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), convolutional neural network (CNN) and long-short term memory neural network (LSTM). The wind speed series is firstly decomposed into several intrinsic mode functions (IMF) by CEEMDAN to provide more stable data. Secondly, four-step-ahead forecasts are realized using well-tuned CNN-LSTM model for each IMF. Finally, the forecasted wind speed is obtained by reconstruction. The effectiveness and feasibility of the proposed method is validated based on thorough evaluation and step-by-step analysis. The RMSE of the proposed model is 0.4046 m/s, which are reduced by 58 % compared with 7 benchmark models. Furthermore, the average prediction interval of the proposed model is also reduced by 20 %, 16 % and 7 % compared to CEEMDAN-FCNN, CEEMDAN-CNN and CEEMDAN-LSTM respectively. The results prove that all three parts of the proposed model contribute to a better performance in wind speed forecasting.

Performance analysis of ARIMA Model for wind speed forecasting in Jerusalem, Palestine

Palestine lacks sufficient conventional energy sources that meet the daily needs of the Palestinian people, and consequently, it heavily relies on neighboring countries for its supply with energy compensations. Wind energy is recognized as an abundant, effective, and eco-friendly power source, but it poses several challenges in harnessing due to the inherent variability of wind characteristics. The main objective of this research study is to delve into the wind energy landscape in Palestine, and to offer some insights into the feasibility of wind speed forecasting for implementing sustainable energy solutions, with a special focus on ARIMA; a widely used statistical method for time series forecasting. It specifically explores the potential of using ARIMA models to forecast wind speed using a data captured from a meteorological station located in east Jerusalem, Palestine for a duration of 2 years—January 1, 2021 to December 31, 2022. To find the optimal values of ARIMA parameters (p, d, q) for the considered study site, a set of experiments were conducted and the model's forecasting accuracy was evaluated using three metrics: RMSE, MAE, and the coefficient of determination (R2). The results have shown that ARIMA (21,2) emerges as the most accurate structure with an input period that demonstrates superior estimation with minimal RMSE (1.74), minimal MAE (1.58) and higher R2 (0.76) values. This means that the optimal estimation is achieved when an autoregressive process is based on the previous two lagged observations and the moving average process incorporates the dependency between the observation and the residual error from a second-order moving average applied to the lagged observations. These findings give valuable insights into the feasibility and precision of wind speed forecasting models for sustainable energy solutions, and emphasize the potential for harnessing wind energy in the region as clarified by ARIMA forecasting accuracy.

Wind-Speed Multi-Step Forecasting Based on Variational Mode Decomposition, Temporal Convolutional Network, and Transformer Model

Reliable and accurate wind-speed forecasts significantly impact the efficiency of wind power utilization and the safety of power systems. In addressing the performance enhancement of transformer models in short-term wind-speed forecasting, a multi-step prediction model based on variational mode decomposition (VMD), temporal convolutional network (TCN), and a transformer is proposed. Initially, the Dung Beetle Optimizer (DBO) is utilized to optimize VMD for decomposing non-stationary wind-speed series data. Subsequently, the TCN is used to extract features from the input sequences. Finally, the processed data are fed into the transformer model for prediction. The effectiveness of this model is validated by comparison with six other prediction models across three datasets, demonstrating its superior accuracy in short-term wind-speed forecasting. Experimental findings from three distinct datasets reveal that the developed model achieves an average improvement of 52.1% for R2. To the best of our knowledge, this places our model at the leading edge of wind-speed prediction for 8 h and 12 h forecasts, demonstrating MSEs of 1.003 and 0.895, MAEs of 0.754 and 0.665, and RMSEs of 1.001 and 0.946, respectively. Therefore, this research offers significant contributions through a new framework and demonstrates the utility of the transformer in effectively predicting short-term wind speed.

Deterministic Forecasting and Probabilistic Post‐Processing of Short‐Term Wind Speed Using Statistical Methods

AbstractThere is a great need for an accurate short‐term wind speed forecast, and statistical forecasts have gained increased popularity for their computational efficiency and satisfactory skill. However, there has been no systematic research to fully explore the capabilities of statistical approaches and evaluate the applicability of probabilistic information from statistical ensemble. This study first compares the skills of different statistical methods, based on linear regression, machine learning (ML), and deep learning (DL), using three strategies (i.e., direct, recursive, and multi‐output) against the three operational numerical models and their bias‐corrections, for short‐term wind speed forecast over Pearl River Estuary during 2018–2021. Inter‐comparison between statistical forecasts reveals the dominant superiority of direct strategy. On this basis, Random Forest (RF) and Support Vector Machines (SVM) perform best compared to other statistical forecasts and bias correction of numerical forecasts throughout 48 hr lead time, while the performance of methods with simplified (linear) or more complex (DL) model structures degrades significantly. Moreover, the top 10 forecasts are utilized to account for forecast uncertainties but present a substantial under‐dispersed prediction. Two traditional methods and three modern methods are implemented to perform probabilistic post‐processing. Modern methods based on ML or DL present worse skills, while traditional methods, particularly for ensemble model output statistics, show added value in discriminating binary events due to limited enhancements in calibration. Overall, RF and SVM using direct strategy are highly recommended for short‐term wind speed forecasts, and efforts are ongoing to address the issues of strong wind prediction and ensemble calibration.

Development of the logical system for forecasting wind characteristics in the urban conditions

This study is devoted to the development of a logical system to improve the efficiency of wind turbines with the identification of patterns and relationships between wind speeds and directions in urban conditions. The results of the study made it possible to identify approaches to use wind energy efficiently to produce electricity with minimal losses for the power supply of urban facilities. Data Mining methods were applied, the dependencies between weather data were examined. Machine Learning algorithms have also been applied to forecast wind speed and direction in order to increase the efficiency of power generation. A thorough exploratory data analysis was carried out, including visualization of meteorological data and the study of their statistical indicators. To predict wind speed, numerical indicators such as air temperature, wind direction, pressure tendency and atmospheric pressure were taken. Linear Regression, Decision Tree and Support Vector Machine were taken as Machine Learning models. The results revealed that the Random Forest turned out to be the most effective, with a mean squared error of 0.302. According to the results of the research, it was found that the initial data on the characteristics of the wind are highly distorted when it circulates in the urban environment due to the influence of urban development. However, the use of a logical system made it possible to predict and adapt the operation of wind turbines to changes in wind characteristics with minimal losses. A pivotal outcome of this study is the creation of a real-time data processing system, enabling accurate predictions of wind characteristics from speed and direction measuring devices. Additionally, a MATLAB Simulink-based computer model was developed to explore the logical system's influence on wind turbine performance. The findings underscore the efficacy of employing forecasting within a logical system framework to harness wind energy efficiently, contributing to sustainable urban energy solutions

A novel ensemble system for short-term wind speed forecasting based on hybrid decomposition approach and artificial intelligence models optimized by self-attention mechanism

Accurate wind speed forecasting is crucial for wind energy development and utilization. The non-linearity and non-stationarity of the wind speed leads to difficulties in its prediction. Recent years, plentiful forecasting approaches have been developed to improve the short-term wind speed forecasting. Among them, the ensemble system that consists of several sub-models is highly competitive. However, most of ensemble systems employ traditional data pre-processing method and integrate the outputs of sub-models with fixed weight assignment, which severely constrains the forecasting performance. To address these prevailing problems and further enhance the forecasting accuracy and stability, a novel ensemble system is proposed in this study, which comprising four modules: a data pre-processing module, an optimization module, a multiscale prediction module and a combination module. A hybrid decomposition approach is developed to fully exploit the changing modes of wind speed series in data pre-processing module. The multiscale prediction module employs advanced artificial intelligence models to conduct forecasting with the assistance of the optimization module. Finally, the self-attention mechanism is used to combine the outputs of sub-models. Measured hourly wind speed from four stations are adopted as datasets, and four metrics are used to evaluate the forecasting performance. Three comprehensive experiments are designed to explore the functionality and validate the predictive capability of the proposed ensemble system. The experimental results indicate that the proposed ensemble system significantly outperformed single models. The superiority of the proposed ensemble system is also demonstrated in comparisons with hybrid models and other ensemble systems. Overall, the proposed ensemble system can provide more accurate and reliable forecasting for the scheduling and management of wind power systems than other benchmark models.

Implementation of AI for forecasting of wind speed and solar irradiation using different Machine Learning techniques

High penetration of solar and wind power in the electricity system provides a number of challenges to the grid such as grid stability and security, system operation, and market economics. Ones of the considerable problems of solar and wind systems, they depend on the weather, as compared to the conventional generation. As we know, the balance in managing load and generated power in energy system is very import ant. If the power which is supplied from solar and wind perfectly predictable, the extra cost of operating power system with a large penetration of renewable energy will be reduced. Since, the accurate and reliable forecasting system for renewable sources represents an important topic as a major contribution for increasing non-programmable renewable on over the world. The target of this research is to describe the advanced hybrid evolutionary techniques of computational intelligence applied for PV as well as wind power forecast. The evaluation of this investigation is obtained by comparing different definitions of the forecasting error. Moreover, the meaning of NWP (numerical weather prediction) values based on meteorological information on solar and wind power forecasting at Indore has been highlighted in this research.

Added Value of Three‐Dimensional Horizontal Winds From Geostationary Interferometric Infrared Sounder for Typhoon Forecast in a Regional NWP Model

AbstractHigh temporal resolution geostationary hyperspectral infrared sounders can simultaneously profile atmospheric temperature and moisture, and track moisture features to provide 3D horizontal winds in clear and partially cloudy scenarios. The thermodynamic information obtained has been integral to enhancing tropical cyclone (TC) forecasts. However, the potential benefits derived from the dynamic information provided by geostationary hyperspectral infrared sounders (GeoHIS) are yet to be fully comprehended for numerical weather prediction (NWP). With the re‐estimated observation error and multivariate hydrometeor background error covariance, the 3D horizontal winds from the Geostationary Interferometric Infrared Sounder (GIIRS) are synergistically assimilated with the hydrometeor information. The impact of the GIIRS‐derived 3D horizontal wind assimilation on Typhoon Maria (2018) and Lekima (2019) analysis and forecast are evaluated. The results show that the assimilating GIIRS‐derived 3D horizontal wind notably reduces the RMSEs of analysis and forecast, particularly in the U and V components. The improvement in accuracy of large‐scale fields substantially enhances the forecasts of typhoons' track and maximum wind speed, as well as the central sea‐level pressure. Moreover, the prediction of the spatial distribution and intensity for landfall precipitation is also improved. The detailed diagnoses of the Maria show that a more southerly subtropical high generated by the additional horizontal wind assimilation improves the rainfall spatial distribution, and the reasonable water vapor transportation caused by the improved dynamic conditions corrects the precipitation intensity. This work highlights the importance of dynamic information in TC forecasting and emphasizes the need for efficient and high‐precision 3D wind measurements to improve NWP.

Evaluation of LSTM and Wavelet Methods for Wind Speed Forecasting in Bahia, Brazil

The pursuit of sustainable development is intricately linked to the effective management of renewable energy resources, with wind energy emerging as a key player on the global stage. However, the inherent volatility and intermittency of wind patterns pose significant challenges to accurate wind speed forecasting, which is crucial for the stable operation of wind turbines. Our study presents a novel forecasting model that integrates cuttingedge data decomposition techniques with Long Short-Term Memory (LSTM) networks in this context. Our approach leverages advanced methodologies such as Wavelet Transform (WT), Empirical Mode Decomposition (EMD), and Enhanced Empirical Mode Decomposition (EEMD) to segment time series data into distinct high and low-frequency components. These segmented signals are then individually forecasted using Bidirectional LSTM (BiLSTM) networks, with the amalgamation of these predictions providing the final forecast output. Our empirical findings demonstrate that the hybrid model, particularly utilizing EMD and EEMD, exhibits superior performance compared to existing forecasting models in terms of both accuracy and stability. By effectively combining sophisticated data decomposition techniques with state-of-the-art deep learning algorithms, our proposed model offers a robust solution for wind speed forecasting. This facilitates the efficient management of renewable energy resources and advances the cause of sustainable development initiatives worldwide.

Simultaneous forecasting of wind speed for multiple stations based on attribute-augmented spatiotemporal graph convolutional network and tree-structured parzen estimator

The global increase in energy demand and environmental concerns have made the development of wind energy increasingly important. Accurate wind speed prediction is crucial for maximizing the benefits of wind energy. In order to further improve the accuracy of multi-site wind speed prediction, this study adopts an evolutionary algorithm-based deep learning model that fully considers the spatiotemporal relationships among multiple station's wind speed data. Firstly, the mutual information (MI) method is used to select variables with stronger correlations to wind speed as auxiliary input factors. Then, an improved version of Attribute-Augmented Spatiotemporal Graph Convolutional Network (IASTGCN) is employed to process data from multiple stations, taking into account both temporal and spatial factors. Additionally, an MI-based wind speed data relationship matrix between multiple stations is calculated to replace the original distance relationship matrix in the model, enabling the model to better capture and utilize the relationships between stations. Next, the Tree-structured Parzen Estimator (TPE) is used to optimize the hyperparameters of the model. This ultimately achieves multi-site multi-step wind speed prediction. Experimental results demonstrate that the proposed model outperforms baseline models and models that only consider either temporal or spatial factors in various scenarios, exhibiting better predictive performance.

Short term wind speed forecasting using artificial and wavelet neural networks with and without wavelet filtered data based on feature selections technique

Wind speed forecasting plays a crucial role in enhancing the efficiency, reliability, and profitability of renewable energy systems. Accurate wind speed forecasting optimizes energy production and grid integration in renewable energy systems. It assists in maintenance scheduling, decision-making in energy markets, and supports risk management for financial planning. This paper investigates the difficult balance between model complexity and forecasting accuracy in wind speed forecasting using Artificial Neural Networks (ANNs) and Wavelet Neural Networks (WNNs). Employing a time series approach, the study develops models for 1-h-ahead wind speed forecasting, utilizing recent averaged data and exploiting correlations between consecutive wind speeds for improved short-term predictions. Models training involve the Backpropagation algorithm, with careful input variable selection to minimize errors. This study emphasizes that simpler ANN and WNN models can outperform complex ones and explores the effectiveness of wavelet filtering techniques and demonstrates the benefits of using wavelet filtering to enhance forecasting accuracy. The robustness of the developed models is validated through K-fold cross-validation, confirming the efficacy of the proposed models. Evaluation across two datasets demonstrates the superiority of the proposed models over the persistence model, with enhancements of 7–14% in RMSE. Additionally, the efficacy of wavelet transforms in enhancing forecasting accuracy compared to regular neural network predictions is emphasized, underscoring the effectiveness of wavelet filtering offering a strategic approach for optimizing wind power management in electrical grids.

Short-Term Marine Wind Speed Forecasting Based on Dynamic Graph Embedding and Spatiotemporal Information

Predicting wind speed over the ocean is difficult due to the unequal distribution of buoy stations and the occasional fluctuations in the wind field. This study proposes a dynamic graph embedding-based graph neural network—long short-term memory joint framework (DGE-GAT-LSTM) to estimate wind speed at numerous stations by considering their spatio-temporal information properties. To begin, the buoys that are pertinent to the target station are chosen based on their geographic position. Then, the local graph structures connecting the stations are represented using cosine similarity at each time interval. Subsequently, the graph neural network captures intricate spatial characteristics, while the LSTM module acquires knowledge of temporal interdependence. The graph neural network and LSTM module are sequentially interconnected to collectively capture spatio-temporal correlations. Ultimately, the multi-step prediction outcomes are produced in a sequential way, where each step relies on the previous predictions. The empirical data are derived from direct measurements made by NDBC buoys. The results indicate that the suggested method achieves a mean absolute error reduction ranging from 1% to 36% when compared to other benchmark methods. This improvement in accuracy is statistically significant. This approach effectively addresses the challenges of inadequate information integration and the complexity of modeling temporal correlations in the forecast of ocean wind speed. It offers valuable insights for optimizing the selection of offshore wind farm locations and enhancing operational and management capabilities.

Wind speed prediction using LSTM and ARIMA time series analysis models: A case study of Gelibolu

Wind energy stands out as a prominent renewable energy source, characterized by its high efficiency, feasibility, and wide applicability. Nonetheless, the integration of wind energy into the electrical system encounters significant obstacles due to the unpredictability and variability of wind speed. Accurate wind speed prediction is essential for estimating the short-, medium-, and long-term power output of wind turbines. Various methodologies and models exist for wind speed time series prediction. This research paper proposes a combination of two approaches to enhance forecasting accuracy: deep learning, particularly Long Short-Term Memory (LSTM), and the Autoregressive Integrated Moving Average (ARIMA) model. LSTM, by retaining patterns over longer periods, improves prediction rates. Meanwhile, the ARIMA model enhances the likelihood of staying within predefined boundaries. The study utilizes daily average wind speed data from the Gelibolu district of Çanakkale province spanning 2014 to 2021. Evaluation using the root mean square error (RMSE) shows the superior forecast accuracy of the LSTM model compared to ARIMA. The LSTM model achieved an RMSE of 6.3% and a mean absolute error of 16.67%. These results indicate the potential utility of the proposed approach in wind speed forecasting, offering performance comparable to or exceeding other studies in the literature.

Rainfall, Wind Speed, and Temperature Forecast Using Triple Exponential Smoothing and Gradient Descent

Rainfall, Wind Speed, and Temperature Forecast Using Triple Exponential Smoothing and Gradient Descent

Explainable machine learning techniques based on attention gate recurrent unit and local interpretable model‐agnostic explanations for multivariate wind speed forecasting

AbstractWind power has emerged as a successful component within power systems. The ability to reliably and accurately forecast wind speed is of great importance in maintaining the security and stability of the power grid. However, the significance of explaining prediction models has often been overlooked by researchers. To address this gap, this study introduces a novel approach to wind speed forecasting that incorporates a significant decomposition method, attention‐based machine learning, and local explanation techniques. The proposed model utilizes grid search variational mode decomposition to decompose the wind speed sequence into different modes while employing gate recurrent unit with an attention mechanism to achieve superior forecasting performance. Experimental evaluations conducted on eight real‐world wind speed datasets demonstrate that the proposed approach outperforms other popular models across multiple performance criteria. In two specific experiments, the proposed approach achieved a minimal mean absolute percentage error of 2.74% and 1.70%, respectively. Furthermore, local interpretable model‐agnostic explanations (LIME) were employed to assess the influence of factors, highlighting whether they positively or negatively affected the predicted values.

Analyzing flexibility options for microgrid management from economical operational and environmental perspectives

Power grids have undergone a massive transformation due to increasing number of renewable/non renewable distributed generators, storage technologies and electrical vehicles. This paper focuses on the flexible energy management of grid connected microgrid (MG) in order to analyze the effects of the flexibility options such as electric vehicle with demand response (EV-DR), battery storage system (BSS), hydrogen storage system (HSS) and dynamic line rating (DLR) in presence of renewable sources. In addition, microturbine (MT), fuel cell (FC), biomass (BIO), geothermal (GEO), and diesel engine (DIE) whose output is controllable are also considered as flexible sources. In this paper, optimum operation of grid-connected MG is modeled as a mixed-integer linear programming problem considering uncertainties of wind turbine (WT) and photovoltaic (PV) sources. A day-ahead forecasting of irradiance and wind speed are performed with Decision Tree Regression (DTR) and Long Short Term Memory (LSTM) algorithms for sensitive calculation of PV and WT output. The cost function merges operating costs including fuel, operation & maintains (O&M), depletion costs with emission cost of CO2, SO2, and NOx. Obtained numerical results show that total cost of the MG is reduced by 9.40% and emission cost is diminished by 5.59% with inclusion of all considered flexibility options. Further, load factor is improved from 0.7932 to 0.8236 with 100% flexibility condition for MG.

A hybrid model based on STL with simple exponential smoothing and ARMA for wind forecast in a Brazilian nuclear power plant site

In the event of a nuclear accident with release of radioactive effluents into the environment, the Environmental Control System (ECS) at the Central Nuclear Almirante Álvaro Alberto (CNAAA) nuclear complex estimates the movement of the radioactive plume produced and provides forecast for one and two hours ahead. The prediction is based on the current accident and atmospheric data collected from meteorological stations spread across the site. In this way, the ECS estimates the spatial dose and dose rates distribution at ground level. The one- and two-hour forecast made by the ECS use the naïve method, which repeats the last known value. Its results are satisfactory if the next value to be collected does not differ substantially from the last known value. However, observing real data, acquired in loco, this fact does not occur in practice, which can make the forecast considerably erroneous.The purpose of this work is to investigate new approaches to improve ECS forecasting method, making it more accurate in real situations. To this end, the Seasonal and Trend decomposition using Loess (STL) was used together with the Simple Exponential Smoothing (SES) method and the Autoregressive Moving Average (ARMA) model to forecast weather parameters at the Angra site. The STL method was chosen since it has a robust mathematical decomposition method, capable of satisfactorily dealing with time series that have a high frequency of acquisition, the so-called intraday series. This model uses the Loess method, which is a smoothing technique based on locally adjusted regressions. The SES method and ARMA model are the techniques that most adequately fit the trend and remainder components generated by the STL decomposition, respectively. In the scope of this work, the method is applied to forecast wind speed measurements made at one of the meteorological towers used by the ECS. Using the hybrid model developed, an increase the of 101.39% in the Mean Absolute Percentage Error (MAPE), was achieved when compared to the ECS forecast method.