Prediction System of Cloud Distribution Image Using Fully Convolutional Networks
-
- Akiyama Koki
- Graduate School of Sciences and Technology for Innovation, Tokushima University
-
- Suzuki Hiroshi
- Graduate School of Sciences and Technology for Innovation, Tokushima University
-
- Kitajima Takahiro
- Graduate School of Sciences and Technology for Innovation, Tokushima University
-
- Yasuno Takashi
- Graduate School of Sciences and Technology for Innovation, Tokushima University
Description
<p>In this paper, we propose a cloud distribution prediction model in which fully convolutional networks are used to improve the prediction accuracy for photovoltaic power generation systems. The model learns the cloud distribution from meteorological satellite images and predicts the cloud image 60 min later. We examined the applicability of Day Microphysics RGB as input to the cloud image prediction model. Day Microphysics RGB is a type of RGB composite image based on the observation image of Himawari-8. It is used for daytime cloud analysis and can perform detailed cloud analysis, for example, the discrimination of cloud areas such as upper and lower clouds. The performance of the proposed method is evaluated on the basis of the root mean square error of the prediction and ground truth images.</p>
Journal
-
- Journal of Signal Processing
-
Journal of Signal Processing 26 (4), 127-130, 2022-07-01
Research Institute of Signal Processing, Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390011108717964544
-
- ISSN
- 18801013
- 13426230
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- OpenAIRE
-
- Abstract License Flag
- Disallowed