Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea

Yeom, Jong-Min; Deo, Ravinesh C.; Adamowski, Jan; Park, Seonyoung; Lee, Chang-Suck

doi:10.1088/1748-9326/ab9467

Cited by 27 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the network exploits the data's temporal (LSTM) and spatial (convolution) dimensions. This topology is also popular among remote sensing data, in particular for a use case that benefits from both spatial and temporal dimensions such as land cover ( [37][38][39]), soil moisture ( [40,41]), solar radiation ( [42]), air quality [43], and others, including crop type mapping ( [44][45][46]). In [47], the authors propose a more efficient version of ConvLSTM, named ConvSTAR.…”

Section: Popular DL Methods For Crop Type Mappingmentioning

confidence: 99%

AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning

Selea

2023

Remote Sensing

View full text Add to dashboard Cite

With the increasing volume of collected Earth observation (EO) data, artificial intelligence (AI) methods have become state-of-the-art in processing and analyzing them. However, there is still a lack of high-quality, large-scale EO datasets for training robust networks. This paper presents AgriSen-COG, a large-scale benchmark dataset for crop type mapping based on Sentinel-2 data. AgriSen-COG deals with the challenges of remote sensing (RS) datasets. First, it includes data from five different European countries (Austria, Belgium, Spain, Denmark, and the Netherlands), targeting the problem of domain adaptation. Second, it is multitemporal and multiyear (2019–2020), therefore enabling analysis based on the growth of crops in time and yearly variability. Third, AgriSen-COG includes an anomaly detection preprocessing step, which reduces the amount of mislabeled information. AgriSen-COG comprises 6,972,485 parcels, making it the most extensive available dataset for crop type mapping. It includes two types of data: pixel-level data and parcel aggregated information. By carrying this out, we target two computer vision (CV) problems: semantic segmentation and classification. To establish the validity of the proposed dataset, we conducted several experiments using state-of-the-art deep-learning models for temporal semantic segmentation with pixel-level data (U-Net and ConvStar networks) and time-series classification with parcel aggregated information (LSTM, Transformer, TempCNN networks). The most popular models (U-Net and LSTM) achieve the best performance in the Belgium region, with a weighted F1 score of 0.956 (U-Net) and 0.918 (LSTM).The proposed data are distributed as a cloud-optimized GeoTIFF (COG), together with a SpatioTemporal Asset Catalog (STAC), which makes AgriSen-COG a findable, accessible, interoperable, and reusable (FAIR) dataset.

show abstract

Section: Popular DL Methods For Crop Type Mappingmentioning

confidence: 99%

AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning

Selea

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Several of Deo R.C. 's articles are focused on predicting solar radiation through climate models, observational predictors, and hybrid algorithms between Deep learning and machine learning (Yeom et al, 2020;Ghimire et al, 2022a;Ghimire et al, 2022b). The analysis of relationships and co-occurrences is done using the VOSviewer software, taking as a parameter that the author has at least two documents and two citations.…”

Section: Bibliometric Indicatorsmentioning

confidence: 99%

Implications of Machine Learning in the Generation of Renewable Energies in Latin America from a Globalized Vision: A Systematic Review

Hernandez-Palma,

Alvarado,

Guiliany

et al. 2024

IJEEP

View full text Add to dashboard Cite

The global energy industry fundamentally transformed towards renewable energy sources, driven by the sustainability paradigm. This shift was crucial in addressing the challenges of climate change and resource scarcity. Machine Learning (ML) played a pivotal role in enhancing the efficiency and reliability of renewable energy systems. This study conducted a comprehensive analysis of scientific production at the intersection of ML and renewable energy generation, focusing on Latin America. Employing a methodology based on documentary research and bibliometric processes, utilizing the Scopus database with the support of R and VOSviewer software, our research revealed a significant increase in interest and investment in research related to ML and renewable energies since 2020. This exponential growth scenario in this knowledge area had significant implications for Latin America and the world, fostering technological advancements and the adoption of renewable energies. Countries such as China, India, the United States, South Korea, and Saudi Arabia represented 61% of the global scientific production in this field, underscoring its global relevance. This growth indicated a growing interest and investment in ML applications in renewable energies, aligning with the 2030 Agenda for Sustainable Development. This research aligns with the Sustainable Development Goals (SDGs), particularly SDG 7 (Affordable and Clean Energy) and SDG 9 (Industry, Innovation, and Infrastructure). It contributed to progress toward a more sustainable future, benefiting society through more efficient and sustainable energy systems, the energy industry through increased innovation and the adoption of clean technologies, and Latin America, which could leverage these findings to sustainably drive its economic and environmental development.

show abstract

“…Using these insights we also utilized zero-inflated models in our research. The study "Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea" [15] introduces a novel approach using deep learning models, specifically Convolutional Long Short-Term Memory (ConvLSTM) networks, to predict short-term solar radiation by incorporating geostationary satellite images. The proposed model showed high accuracy in capturing cloud-induced variations in ground-level solar radiation compared to the conventional artificial neural network (ANN) and random forest (RF) models.…”

Section: Survey Of Literaturementioning

confidence: 99%

Predicting Solar Energy Generation with Machine Learning based on AQI and Weather Features

Shah,

Viswanath,

Gandhi

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, our goal is to determine solar power generation utilising machine learning models based on weather data and AQI(Air Quality Index). This study benchmarks the performance of these models based on three novel methodologies to identify which yields the best accuracy in terms of R2 score and simultaneously results in the lowest Mean Absolute Error(MAE) and Root Mean Square Error(RMSE). Firstly, a time-series based approach is used to accurately capture the seasonality in this solar generation. Secondly, to address the excessive zeros in the solar generation data we switched to a zero-inflated model, which accounts for the cases where there is true zero solar generation(Night-time, winter, cloud cover etc). Finally, we applied Power Transform to formulate a more efficient 1 method of addressing the skewness in the data and to transform it into a more Gaussian-like distribution. This scaling method smoothed out the solar distribution data and gave a much better R2 score and lower overall MAE and RMSE scores. These findings demonstrate the overall success of our predictive models in accurately determining solar power generation. Since precise solar energy projections can help to maximise energy generation and utilisation, these findings have major implications for energy management and planning. A comprehensive framework for precise solar energy prediction based on AQI and weather features is provided by the combination of regular time series modeling, zero-inflated modeling, and power transformation techniques, which advances forecasting and decision-making for renewable energy sources.

show abstract

Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea

Cited by 27 publications

References 47 publications

AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning

AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning

Implications of Machine Learning in the Generation of Renewable Energies in Latin America from a Globalized Vision: A Systematic Review

Predicting Solar Energy Generation with Machine Learning based on AQI and Weather Features

Contact Info

Product

Resources

About