Deep learning based solar radiation micro forecast by fusion of infrared cloud images and radiation data

Ajith, Meenu; Martínez‐Ramón, Manel

doi:10.1016/j.apenergy.2021.117014

Cited by 58 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the signal processing domain, recognition [403] and analysis [404] each have 1; in the gender domain, classification [405] and recognition [406] each also have 1 article. The industry, fashion, e-commerce, energy, mapping, academia, product, food, cooking, plant, language, chemistry and mobile application domains have 1 relevant article in the following applications accordingly: prediction [407], retrieval [408], classification [409], classification [410], prediction [411], recognition [412], recognition [413], inspection [414], retrieval [415], segmentation [416], translation [417], analysis [418], and detection [419].…”

Section: Inclusion Criteriamentioning

confidence: 99%

“…[98], [100], [104], [116], [125], [127], [187], [206], [241], [326], [365], [395], [411], Image & Numerical [62], [75], [119], [126], [167], [313], [331], [353], [405], [410], Audio & Text & Sensor [384], Audio & Text [180], [282], [377], [391], [392], Text & Signal [109], Text & Numerical [304], [349], Sensor & Signal [240], [242], [258], [389], Sensor & Numerical [183], Signal & Numerical [205], [257], [260], [318]. Figure 10 displays the extracted information related to each modality and data type with the links between them.…”

Section: B Taskmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

2023

View full text Add to dashboard Cite

Multimodal machine learning (MML) is a tempting multidisciplinary research area where heterogeneous data from multiple modalities and machine learning (ML) are combined to solve critical problems. Usually, research works use data from a single modality, such as images, audio, text, and signals. However, real-world issues have become critical now, and handling them using multiple modalities of data instead of a single modality can significantly impact finding solutions. ML algorithms play an essential role by tuning parameters in developing MML models. This paper reviews recent advancements in the challenges of MML, namely: representation, translation, alignment, fusion and co-learning, and presents the gaps and challenges. A systematic literature review (SLR) applied to define the progress and trends on those challenges in the MML domain. In total, 1032 articles were examined in this review to extract features like source, domain, application, modality, etc. This research article will help researchers understand the constant state of MML and navigate the selection of future research directions.

show abstract

Section: Inclusion Criteriamentioning

confidence: 99%

Section: B Taskmentioning

confidence: 99%

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

2023

View full text Add to dashboard Cite

show abstract

“…Among them, the intensity of solar irradiation reaching the PV modules plays a dominant role in determining the PV energy yield . In general, the cloud characteristics are considered the primary factors modifying surface solar irradiation. − However, the impact of increasing air pollution on surface solar irradiation cannot be negligible. High concentrations of atmospheric pollutants could significantly attenuate incoming irradiation by absorbing and scattering the sunlight, especially in heavy polluted areas such as Indo-Gangetic plains and North China. − For instance, Zhang et al found that the annual surface solar irradiation attenuation ranges from 2.69 to 6.56% during 2014–2016 in five cities with high levels of air pollution in China.…”

Section: Introductionmentioning

confidence: 99%

“… 4 In general, the cloud characteristics are considered the primary factors modifying surface solar irradiation. 5 − 7 However, the impact of increasing air pollution on surface solar irradiation cannot be negligible. High concentrations of atmospheric pollutants could significantly attenuate incoming irradiation by absorbing and scattering the sunlight, especially in heavy polluted areas such as Indo-Gangetic plains and North China.…”

Section: Introductionmentioning

confidence: 99%

Quantification of the Impact of Fine Particulate Matter on Solar Energy Resources and Energy Performance of Different Photovoltaic Technologies

2022

View full text Add to dashboard Cite

Ambient fine particulate matter (PM2.5) could be a potential environmental risk for decreasing the available solar energy resources and solar photovoltaic (PV) power generation. This study quantifies the attenuation effects of PM2.5 on surface solar irradiance and system performance of different solar PV technologies in Hong Kong. The analysis based on observational irradiation data shows that the global horizontal irradiance decreased by more than 5% in most months under the conditions of PM2.5 concentration exceeding 33.5 μg/m 3 . During the experiment, the average PM2.5-related losses in the energy output of crystalline silicon and thin-film PV systems could be up to 7.00 and 9.73%, respectively. The measured energy outputs of the experimental PV modules suggest that PM2.5 affects the energy performance of thin-film solar cells with a larger band gap more significantly than that of crystalline silicon PV modules. Moreover, an increasing trend in the performance ratio of monocrystalline silicon, polycrystalline silicon, and copper indium gallium selenide PV systems with the increase of PM2.5 concentration is observed. In contrast, the amorphous silicon and cadmium telluride PV systems with a narrower spectral response range show a decreasing trend in the performance ratio over the experiment. Results indicate that the losses in the available solar energy resources and PV energy potential are expected to increase in areas where heavier PM2.5 pollution exists.

show abstract

“…Other studies focused on the prediction of solar radiation using images. Ajith and Martínez-Ramón [11] aimed at forecasting solar radiation using deep learning and the fusion of infrared cloud imagery and radiation data. The work used the metrics MAPE, R 2 , RMSE, MAE, and the t-statistic for the proposed networks and other reference models for cloudy days.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning for Solar Resource Assessment Using Satellite Images

2022

View full text Add to dashboard Cite

Understanding solar energy has become crucial for the development of modern societies. For this reason, significant effort has been placed on building models of solar resource assessment. Here, we analyzed satellite imagery and solar radiation data of three years (2012, 2013, and 2014) to build seven predictive models of the solar energy obtained at different altitudes above sea level. The performance of four machine learning algorithms was evaluated using four evaluation metrics, MBE, R2, RMSE, and MAPE. Random Forest showed the best performance in the model with data obtained at altitudes below 800 m.a.s.l. The results achieved by the algorithm were: 4.89, 0.82, 107.25, and 41.08%, respectively. In general, the differences in the results of the machine learning algorithms in the different models were not very significant; however, the results provide evidence showing that the estimation of solar radiation from satellite images anywhere on the planet is feasible.

show abstract

Deep learning based solar radiation micro forecast by fusion of infrared cloud images and radiation data

Cited by 58 publications

References 39 publications

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

Quantification of the Impact of Fine Particulate Matter on Solar Energy Resources and Energy Performance of Different Photovoltaic Technologies

Machine Learning for Solar Resource Assessment Using Satellite Images

Contact Info

Product

Resources

About