Search Results (183)

The inherent variability of solar energy presents a significant challenge for grid operators, particularly when it comes to maintaining stability. Studying ramping phenomena is therefore crucial to understanding and managing fluctuations in power supply. In line with this goal, this study proposes a new classification approach for solar irradiance ramps, categorizing them into four distinct classes. We have proposed a methodology including adaptation and extension of a wind ramp classification to solar ramp classification titled the Irradiance-Based Extreme Day Identification method. Our proposal includes an agglomerative algorithm to find new ramp class boundaries. The strength of the proposed method relies on that it allows its generalization to any dataset. We assessed it on three datasets from distinct geographic regions—Oregon (northwestern United States), Hawaii (central Pacific Ocean), and Portugal (southwestern Europe)—each with varying temporal resolutions of five seconds, ten seconds, and one minute. The class boundaries for each dataset results in different limits of Z score value, as a consequence of the different climatic characteristics of each location and the time resolution of the datasets. The “low” class includes values less than 0.62 for Portugal, less than 2.17 for Oregon, and less than 2.19 for Hawaii. The “moderate” class spans values from 0.62 to 3.51 for Portugal, from 2.17 to 5.01 for Oregon, and from 2.19 to 5.88 for Hawaii. The “high” class covers values greater than 3.51 and up to 6 for Portugal, greater than 5.01 and up to 10.72 for Oregon, and greater than 5.88 and up to 8.01 for Hawaii. Lastly, the “severe” class includes values greater than 6 for Portugal, greater than 10.72 for Oregon, and greater than 8.01 for Hawaii. Under cloudy sky conditions, it is observed that the proposed algorithm is able to classify the four classes. These thresholds show how the proposed methodology adapts to the unique characteristics of each regional dataset. Full article

The unpredictable nature of renewable energy sources, such as wind and solar, makes them unreliable sources of energy for the power system. Nevertheless, with the advancement in the field of artificial intelligence (AI), one can predict the availability of solar and wind energy in the short, medium, and long term with fairly high accuracy. As such, this research work aims to develop a machine-learning-based framework for forecasting global horizontal irradiance (GHI) for Muscat, Oman. The proposed framework includes a data preprocessing stage, where the missing entries in the acquired data are imputed using the mean value imputation method. Afterward, data scaling is carried out to avoid the overfitting/underfitting of the model. Features such as the GHI cloudy sky index, the GHI clear sky index, global normal irradiance (GNI) for a cloudy sky, GNI for a clear sky, direct normal irradiance (DNI) for a cloudy sky, and DNI for a clear sky are extracted. After analyzing the correlation between the abovementioned features, model training and the testing procedure are initiated. In this research, different models, named Linear Regression (LR), Support Vector Machine (SVR), KNN Regressor, Decision Forest Regressor, XGBoost Regressor, Neural Network (NN), Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Random Forest Regressor, Categorical Boosting (CatBoost), Deep Autoregressive (DeepAR), and Facebook Prophet, are trained and tested under both identical features and a training–testing ratio. The model evaluation metrics used in this study include the mean absolute error (MAE), the root mean squared error (RMSE), R², and mean bias deviation (MBD). Based on the outcomes of this study, it is concluded that the Facebook Prophet model outperforms all of the other utilized conventional machine learning models, with MAE, RMSE, and R² values of 9.876, 18.762, and 0.991 for the cloudy conditions and 11.613, 19.951 and 0.988 for the clean weather conditions, respectively. The mentioned error values are the lowest among all of the studied models, which makes Facebook Prophet the most accurate solar irradiance forecasting model for Muscat, Oman. Full article

The statistical retrieval of atmospheric parameters will be greatly affected by the accuracy of the simulated brightness temperatures (BTs) derived from the radiative transfer model. However, it is challenging to further improve a physical-based radiative transfer model (RTM) developed based on the physical mechanisms of wave transmission through the atmosphere. We develop a deep neural network-based RTM (DNN-based RTM) to calculate the simulated BTs for the Microwave Temperature Sounder-II onboard the Fengyun-3D satellite under different weather conditions. The DNN-based RTM is compared in detail with the physical-based RTM in retrieving the atmospheric temperature profiles by the statistical retrieval scheme. Compared to the physical-based RTM, the DNN-based RTM can obtain higher accuracy for simulated BTs and enables the statistical retrieval scheme to achieve higher accuracy in temperature profile retrieval in clear, cloudy, and rainy sky conditions. Due to its ability to simulate microwave observations more accurately, the DNN-based RTM is valuable for the theoretical study of microwave remote sensing and the application of passive microwave observations. Full article

Accurate photovoltaic (PV) power forecasting is crucial for stable grid integration, particularly under rapidly changing weather conditions. This study presents an ultra-short-term forecasting model that integrates sky imager data and meteorological radar data, achieving significant improvements in forecasting accuracy. By dynamically tracking cloud movement and estimating cloud coverage, the model enhances performance under both clear and cloudy conditions. Over an 8-day evaluation period, the average forecasting accuracy improved from 67.26% to 77.47% (+15%), with MSE reduced by 39.2% (from 481.5 to 292.6), $R^2$ increased from 0.724 to 0.855, NSE improved from 0.725 to 0.851, and Theil’s U reduced from 0.42 to 0.32. Notable improvements were observed during abrupt weather transitions, particularly on 1 July and 3 July, where the combination of MCR and sky imager data demonstrated superior adaptability. This integrated approach provides a robust foundation for advancing ultra-short-term PV power forecasting. Full article

Lidar is the primary tool used to determine the vertical distribution of aerosol optical characteristics. Based on the observation characteristics of the mountain’s gradient, a validation analysis of the remote sensing and in situ observations of the aerosol optical characteristics and research on seasonal, monthly, and daily variations in aerosol optical depth (AOD) were performed using the dual-wavelength Lidar deployed at the foot of Mt. Lu and the aerosol particle-size spectrometer at the top of Mt. Lu. The validation results show that at the comparison heights, under cloudy-sky conditions with strong winds (>3.4 m/s) and high relative humidity (RH) (>70%), the aerosol extinction coefficients between the two sites are in good agreement; thus, the observations at the top of the mountain are more suitable for in situ validation under cloudy-sky conditions; however, the local circulations under clear-sky conditions lead to large differences in the aerosol properties at the same altitude between the two sites and are unsuitable for validation. An analysis of the AOD data from Mt. Lu reveals the following: (1) The AOD seasonal distribution frequencies under both clear-sky and cloudy-sky conditions are unimodal, with a values of 0.2∼0.6, and the inhomogeneity of the aerosol distribution in winter is evident; the seasonal difference in the AOD under clear-sky conditions is more significant, following the order of spring > summer > winter > autumn, and the AOD seasonal difference under cloudy-sky conditions is not obvious. (2) In the analysis of the AOD monthly variations, due to the influence of the meteorological conditions (high humidity, low wind speed) and pollutant transport, the AOD reached its peak in February (clear-sky: 0.63, cloudy-sky: 0.82). (3) Under clear-sky conditions, the negative correlation between the daily variations in AOD, and visibility is more significant during the daytime, and after 12:00, the AOD is positively correlated with $P{M}_{2.5}$; these results indicate that the AOD is affected mainly by pollutants and the boundary layer height. Under cloudy-sky conditions, the peaks in the daytime AOD are related to the morning and evening rush hours, the correlations with the visibility and $P{M}_{2.5}$ are low, and the accumulation of pollutants during the nighttime. And (4) overall, the AOD is greater under cloudy-sky conditions than under clear-sky conditions; this result is likely related to the more favorable subcloud humidity conditions for aerosol hygroscopic growth. Full article

The accurate prediction of photovoltaic (PV) power generation is crucial for improving virtual power plant (VPP) efficiency and power system stability. However, short-term PV power forecasting remains highly challenging due to the significant impact of weather changes, especially the complexity of cloud motion. To this end, this paper proposes an end-to-end innovative deep learning framework for data fusion based on multimodal learning, which utilizes a new auto cross modal correlation attention (ACMCA) mechanism designed in this paper for feature extraction and fusion by combining historical PV power generation time-series data and sky image data, thereby enhancing the model’s prediction performance under complex weather conditions. In this paper, the effectiveness of the proposed model was verified through a large number of experiments, and the experimental results showed that the model’s forecast skill (FS) reached 24.2% under all weather conditions 15 min in advance, and 24.32% under cloudy conditions with the largest fluctuations. This paper also compared the model with a variety of existing unimodal and multimodal models, respectively. The experimental results showed that the model in this paper outperformed other benchmark methods in all indices under different weather conditions, demonstrating stronger adaptability and robustness. Full article

The bionic polarization compass is a fascinating subject in the navigation domain. Existing polarization navigation models are primarily based on Rayleigh scattering theory, which is applicable to high-altitude, dry, and clear weather conditions. In most scenarios, it is difficult to meet such ideal clear conditions. This paper proposes a bionic navigation method based on atmospheric polarization optimization to improve heading accuracy under non-ideal clear conditions. A signal model under non-ideal clear conditions was firstly established to introduce disturbances of aerosols and other particles into the raw signal function acquired by a camera. Then, an energy functional optimization model was constructed to eliminate the disturbances caused by large particle scattering and restore the original sky polarization pattern. Subsequently, the heading angle was calculated using astronomical data, enhancing accuracy under non-ideal conditions. Finally, we constructed a polarization compass system and conducted field experiments. The results demonstrate that the proposed algorithm effectively mitigates the impact of scattering from aerosols and other particles, reducing the heading angle error to within 2° under sunny, cloudy, overcast and sandy conditions. Full article

The latest-generation geostationary meteorological satellite, Fengyun-4B (FY-4B), equipped with the Geostationary Interferometric Infrared Sounder (GIIRS), offers high-spatiotemporal-resolution three-dimensional temperature structures. Its deployment serves as a critical complement to atmospheric temperature profile (ATP) observation in the Tibetan Plateau (TP). Based on radiosonde observation (RAOB) and the fifth-generation ECMWF global climate atmospheric reanalysis (ERA5), this study validates the availability and representativeness of FY-4B/GIIRS ATP products in the eastern TP region. Due to the issue of satellite zenith, this study focuses solely on examining the eastern TP region. Under a clear sky, FY-4B/GIIRS ATP exhibits good consistency with RAOB compared to cloudy conditions, with an average root mean square error (RMSE) of 2.57 K. FY-4B/GIIRS tends to underestimate temperatures in the lower layers while overestimating temperatures in the upper layers. The bias varies across seasons. Except for summer, the horizontal and vertical bias distribution patterns are similar, though there are slight differences in values. Despite the presence of bias, FY-4B/GIIRS ATP maintains a good consistency with observations and reanalysis data, indicating commendable product quality. These results demonstrate that it can play a vital role in augmenting the ATP observation network limited by sparse radiosonde stations in the eastern TP, offering crucial data support for numerical weather prediction, weather monitoring, and related meteorological research in this region. Full article

Several studies proposed relationships linking irradiances in the photosynthetically active radiation (PAR) range and broadband irradiances. A previous study published in 2024 by the same authors proposes a linear model relating clear-sky indices in the PAR and broadband ranges that has been validated in clear and overcast conditions only. The present work extends this study for broken-cloud conditions by using ground-based measurements obtained from the Surface Radiation Budget Network in the U.S.A. mainland. As expected, the clear-sky indices are highly correlated and are linked by affine functions whose parameters depend on the fractional sky cover (FSC), the year, and the site. The previous linear model is also efficient in broken-cloud conditions, with the same level of accuracy as in overcast conditions. When this model is combined with a PAR clear-sky model, the result tends to overestimate the PAR as the FSC decreases, i.e., when fewer and fewer scattered clouds are present. The bias is equal to 1 W m⁻² in overcast conditions, up to 18 W m⁻² when the FSC is small, and 6 W m⁻² when all cloudy conditions are merged. The RMSEs are, respectively, 5, 24, and 15 W m⁻². The linear and the clear-sky models can be combined with estimates of the broadband irradiance from satellites to yield estimates of PAR. Full article

Near-surface air temperature (T_a) estimation by geostationary meteorological satellites is mainly carried out under clear-sky conditions. In this study, we propose an all-weather T_a estimation method utilizing FY-4A Advanced Geostationary Radiation Imager (AGRI) and the Global Forecast System (GFS), along with additional auxiliary data. The method includes two neural-network-based T_a estimation models for clear and cloudy skies, respectively. For clear skies, AGRI LST was utilized to estimate the T_a (T_a,clear), whereas cloud top temperature and cloud top height were employed to estimate the T_a for cloudy skies (T_a,cloudy). The estimated T_a was validated using the 2020 data from 1211 stations in China, and the RMSE values of the T_a,clear and T_a,cloudy were 1.80 °C and 1.72 °C, while the correlation coefficients were 0.99 and 0.986, respectively. The performance of the all-weather T_a estimation model showed clear temporal and spatial variation characteristics, with higher accuracy in summer (RMSE = 1.53 °C) and lower accuracy in winter (RMSE = 1.88 °C). The accuracy in southeastern China was substantially better than in western and northern China. In addition, the dependence of the accuracy of the T_a estimation model for LST, CTT, CTH, elevation, and air temperature were analyzed. The global sensitivity analysis shows that AGRI and GFS data are the most important factors for accurate T_a estimation. The AGRI-estimated T_a showed higher accuracy compared to the ERA5-Land data. The proposed models demonstrated potential for T_a estimation under all-weather conditions and are adaptable to other geostationary satellites. Full article

The detection of ship fires is a critical aspect of maritime safety and surveillance, demanding high accuracy in both identification and response mechanisms. However, the scarcity of ship fire images poses a significant challenge to the development and training of effective machine learning models. This research paper addresses this challenge by exploring advanced data augmentation techniques aimed at enhancing the training datasets for ship and ship fire detection. We have curated a dataset comprising ship images (both fire and non-fire) and various oceanic images, which serve as target and source images. By employing diverse image blending methods, we randomly integrate target images of ships with source images of oceanic environments under various conditions, such as windy, rainy, hazy, cloudy, or open-sky scenarios. This approach not only increases the quantity but also the diversity of the training data, thus improving the robustness and performance of machine learning models in detecting ship fires across different contexts. Furthermore, we developed a Gradio web interface application that facilitates selective augmentation of images. The key contribution of this work is related to object extraction-based blending. We propose basic and advanced data augmentation techniques while applying blending and selective randomness. Overall, we cover eight critical steps for dataset creation. We collected 9200 ship fire and 4100 ship non-fire images. From the images, we augmented 90 ship fire images with 13 background images and achieved 11,440 augmented images. To test the augmented dataset performance, we trained Yolo-v8 and Yolo-v10 models with “Fire” and “No-fire” augmented ship images. In the Yolo-v8 case, the precision-recall curve achieved 96.6% (Fire), 98.2% (No-fire), and 97.4% mAP score achievement in all classes at a 0.5 rate. In Yolo-v10 model training achievement, we got 90.3% (Fire), 93.7 (No-fire), and 92% mAP score achievement in all classes at 0.5 rate. In comparison, both trained models’ performance is outperforming other Yolo-based SOTA ship fire detection models in overall and mAP scores. Full article

Surface downward longwave radiation (SDLR) is crucial for maintaining the global radiative budget balance. Due to their ease of practicality, SDLR parameterization models are widely used, making their objective evaluation essential. In this study, against comprehensive ground measurements collected from more than 300 globally distributed sites, four SDLR parameterization models, including three popular existing ones and a newly proposed model, were evaluated under clear- and cloudy-sky conditions at hourly (daytime and nighttime) and daily scales, respectively. The validation results indicated that the new model, namely the Peng model, originally proposed for SDLR estimation at the sea surface and applied for the first time to the land surface, outperformed all three existing models in nearly all cases, especially under cloudy-sky conditions. Moreover, the Peng model demonstrated robustness across various land cover types, elevation zones, and seasons. All four SDLR models outperformed the Global Land Surface Satellite product from Advanced Very High-Resolution Radiometer Data (GLASS-AVHRR), ERA5, and CERES_SYN1de-g_Ed4A products. The Peng model achieved the highest accuracy, with validated RMSE values of 13.552 and 14.055 W/m² and biases of −0.25 and −0.025 W/m² under clear- and cloudy-sky conditions at daily scale, respectively. Its superior performance can be attributed to the inclusion of two cloud parameters, total column cloud liquid water and ice water, besides the cloud fraction. However, the optimal combination of these three parameters may vary depending on specific cases. In addition, all SDLR models require improvements for wetlands, bare soil, ice-covered surfaces, and high-elevation regions. Overall, the Peng model demonstrates significant potential for widespread use in SDLR estimation for both land and sea surfaces. Full article

The deployment of photovoltaic (PV) systems has increased globally to meet renewable energy targets. Intermittent PV power generated due to cloud-induced variability introduces reliability and grid stability issues at higher penetration levels. Variability in power generation can induce voltage fluctuations within the distribution system and cause adverse effects on power quality. Therefore, it is essential to quantify resource variability to mitigate an intermittent power supply. In this study, we propose a new scheme to classify the sky conditions that are based on two common variability metrices: daily clear-sky index and normalized aggregate ramp rates. The daily clear-sky index estimates the cloudiness in the sky, and ramp rates account for the variability introduced in the system generation due to sudden cloud movements. This classification scheme can identify clear-sky, highly variable, low intermittent, high intermittent and overcast days. By performing a Chi-square test on the training and test sets, we obtain Chi-square statistic values greater than 3 with p-value > 0.05. This indicates that the distribution of the training and test clusters are similar, indicating the robustness of the proposed sky classification scheme. We have demonstrated the applicability of the scheme with diverse datasets to show that the proposed classification scheme can be homogenously applied to any dataset globally despite their temporal resolution. Using various case studies, we demonstrate the potential applications of the scheme for understanding resource allocation, site selection, estimating future intermittency due to climate change, and cloud enhancement effects. The proposed sky classification scheme enhances the precision and reliability of solar energy forecasts, optimizing system performance and maximizing energy production efficiency. This improved accuracy is crucial for variability control and planning, ensuring optimal output from PV plants. Full article

This work explores the prediction of daily Global Horizontal Irradiance (GHI) patterns in the region of Zacatecas, Mexico, using a diverse range of predictive models, encompassing traditional regressors and advanced neural networks like Evolutionary Neural Architecture Search (ENAS), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Meta’s Prophet. This work addressing a notable gap in regional research, and aims to democratize access to accurate solar radiation forecasting methodologies. The evaluations carried out using the time series data obtained by Comisión Nacional del Agua (Conagua) covering the period from 2015 to 2018 reveal different performances of the model in different sky conditions, showcasing strengths in forecasting clear and partially cloudy days while encountering challenges with cloudy conditions. Overall, correlation coefficients (r) ranged between 0.55 and 0.72, with Root Mean Square Error % (RMSE %) values spanning from 20.05% to 20.54%, indicating moderate to good predictive accuracy. This study underscores the need for longer datasets to bolster future predictive capabilities. By democratizing access to these predictive tools, this research facilitates informed decision-making in renewable energy planning and sustainable development strategies tailored to the unique environmental dynamics of the region of Zacatecas and comparable regions. Full article

Precipitable water vapor (PWV) is one of the most dynamic components of the atmosphere, playing a critical role in precipitation formation, the hydrological cycle, and climate change. This study used SuomiNet Global Positioning System (GPS) data from April 2021 to June 2023 in the United States to comprehensively evaluate 3 and 6 h Global Forecast System (GFS) PWV products (i.e., PWV_3h and PWV_6h). There was high consistency between the GFS PWV and GPS PWV data, with correlation coefficients (Rs) higher than 0.98 and a root mean square error (RMSE) of about 0.23 cm. The PWV_3h product performed slightly better than PWV_6h. PWV tended to be underestimated when PWV > 4 cm, and the degree of underestimation increased with increasing water vapor value. The RMSE showed obvious seasonal and diurnal variations, with the RMSE value in summer (i.e., 0.280 cm) considerably higher than in winter (i.e., 0.158 cm), and nighttime were RMSEs higher than daytime RMSEs. Clear-sky conditions showed smaller RMSEs, while cloudy-sky conditions exhibited a smaller range of monthly RMSEs and higher Rs. PWV demonstrated a clear spatial pattern, with both Rs and RMSEs decreasing with increasing elevation and latitude. Based on these temporal and spatial patterns, Back Propagation neural network and random forest (RF) models were employed, using PWV, Julian day, and geographic information (i.e., latitude, longitude, and elevation) as input data to correct the GFS PWV products. The results indicated that the RF model was more advantageous for water vapor correction, improving overall accuracy by 12.08%. In addition, the accuracy of GFS PWV forecasts during hurricane weather was also evaluated. In this extreme weather, the RMSE of the GFS PWV forecast increased comparably to normal weather, but it remained less than 0.4 cm in most cases. Full article