Deep FS: A Deep Learning Approach for Surface Solar Radiation
Fatih Kihtir, Kasim Oztoprak · 2024
Read Deep FS: A Deep Learning Approach for Surface Solar Radiation by Fatih Kihtir, Kasim Oztoprak (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11679866.txt.
Description
Fatih Kihtir and Kasim Oztoprak present a deep learning method for forecasting the solar radiation that reaches the ground, in a 2024 paper. That radiation level, stated as global horizontal irradiance, drives solar energy planning and weather forecasting, and it swings with air conditions, place, and time of day. Their method, Deep FS, first picks the input features that matter most, then predicts with a convolutional network over time.
The team trained and tested on a NASA solar and climate data set. Across standard accuracy measures, the deep model beat traditional approaches. Feature selection is the heart of the design: feeding the network only the most informative inputs sharpened the forecasts. The authors conclude that pairing deep feature selection with a convolutional predictor gives a stronger tool for estimating surface sun exposure than the older models they compared against.
Catalog record
| CREATOR | Fatih Kihtir, Kasim Oztoprak |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |