Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386986737> ?p ?o ?g. }
- W4386986737 endingPage "107814" @default.
- W4386986737 startingPage "107814" @default.
- W4386986737 abstract "With their superior performance in capturing complex relationships between input and output variables, deep learning models have gained popularity in the field of solar radiation prediction. However, the use of deep learning models as a predictive tool is often constrained by their inherent complexity, which can limit the interpretability and usability of the model in practical scenarios, such as model predictive control (MPC) in energy systems. In this study, time series are transformed into an image, and the hourly solar radiation prediction is realized through a convolutional neural network (CNN). The experiments demonstrate that the proposed CNN model enhances interpretability at the cost of a minor 6 % reduction in prediction accuracy, compared to the baseline model. Analogous to the deconvolution operation for image classification, feature maps of CNN networks can thus be used for model interpretability, whereby the closer the feature maps are to the input (In the context of forward propagation, this means that the layers of a CNN closer to the input data), the higher is the interpretability. In extracting the feature map using CNN, solar radiation and radiation time played the most important roles in the entire prediction process." @default.
- W4386986737 created "2023-09-24" @default.
- W4386986737 creator A5029465129 @default.
- W4386986737 creator A5051830537 @default.
- W4386986737 creator A5055954787 @default.
- W4386986737 date "2023-11-01" @default.
- W4386986737 modified "2023-09-30" @default.
- W4386986737 title "Interpretable deep learning for hourly solar radiation prediction: A real measured data case study in Tokyo" @default.
- W4386986737 cites W1977489332 @default.
- W4386986737 cites W2017147805 @default.
- W4386986737 cites W2034764191 @default.
- W4386986737 cites W2042511026 @default.
- W4386986737 cites W2194187530 @default.
- W4386986737 cites W2194775991 @default.
- W4386986737 cites W2282821441 @default.
- W4386986737 cites W2553152989 @default.
- W4386986737 cites W2614843160 @default.
- W4386986737 cites W2615529263 @default.
- W4386986737 cites W2737654582 @default.
- W4386986737 cites W2789880759 @default.
- W4386986737 cites W2792259330 @default.
- W4386986737 cites W2802476978 @default.
- W4386986737 cites W2913949647 @default.
- W4386986737 cites W2945723146 @default.
- W4386986737 cites W2955229286 @default.
- W4386986737 cites W2963626582 @default.
- W4386986737 cites W2968103966 @default.
- W4386986737 cites W2981731882 @default.
- W4386986737 cites W2997654184 @default.
- W4386986737 cites W3033993664 @default.
- W4386986737 cites W3043185719 @default.
- W4386986737 cites W3097850930 @default.
- W4386986737 cites W3111639609 @default.
- W4386986737 cites W3122286801 @default.
- W4386986737 cites W3138234178 @default.
- W4386986737 cites W3139651213 @default.
- W4386986737 cites W3166156627 @default.
- W4386986737 cites W3173890096 @default.
- W4386986737 cites W3194559478 @default.
- W4386986737 cites W4210605514 @default.
- W4386986737 cites W4211076903 @default.
- W4386986737 cites W4224262388 @default.
- W4386986737 cites W4226364595 @default.
- W4386986737 cites W4281672534 @default.
- W4386986737 cites W4303684714 @default.
- W4386986737 cites W4313472418 @default.
- W4386986737 cites W4313839703 @default.
- W4386986737 cites W911343586 @default.
- W4386986737 doi "https://doi.org/10.1016/j.jobe.2023.107814" @default.
- W4386986737 hasPublicationYear "2023" @default.
- W4386986737 type Work @default.
- W4386986737 citedByCount "0" @default.
- W4386986737 crossrefType "journal-article" @default.
- W4386986737 hasAuthorship W4386986737A5029465129 @default.
- W4386986737 hasAuthorship W4386986737A5051830537 @default.
- W4386986737 hasAuthorship W4386986737A5055954787 @default.
- W4386986737 hasConcept C108583219 @default.
- W4386986737 hasConcept C11413529 @default.
- W4386986737 hasConcept C119857082 @default.
- W4386986737 hasConcept C138885662 @default.
- W4386986737 hasConcept C151730666 @default.
- W4386986737 hasConcept C153180895 @default.
- W4386986737 hasConcept C154945302 @default.
- W4386986737 hasConcept C174576160 @default.
- W4386986737 hasConcept C202444582 @default.
- W4386986737 hasConcept C2776401178 @default.
- W4386986737 hasConcept C2779343474 @default.
- W4386986737 hasConcept C2781067378 @default.
- W4386986737 hasConcept C33923547 @default.
- W4386986737 hasConcept C41008148 @default.
- W4386986737 hasConcept C41895202 @default.
- W4386986737 hasConcept C45804977 @default.
- W4386986737 hasConcept C50644808 @default.
- W4386986737 hasConcept C81363708 @default.
- W4386986737 hasConcept C86803240 @default.
- W4386986737 hasConcept C9652623 @default.
- W4386986737 hasConceptScore W4386986737C108583219 @default.
- W4386986737 hasConceptScore W4386986737C11413529 @default.
- W4386986737 hasConceptScore W4386986737C119857082 @default.
- W4386986737 hasConceptScore W4386986737C138885662 @default.
- W4386986737 hasConceptScore W4386986737C151730666 @default.
- W4386986737 hasConceptScore W4386986737C153180895 @default.
- W4386986737 hasConceptScore W4386986737C154945302 @default.
- W4386986737 hasConceptScore W4386986737C174576160 @default.
- W4386986737 hasConceptScore W4386986737C202444582 @default.
- W4386986737 hasConceptScore W4386986737C2776401178 @default.
- W4386986737 hasConceptScore W4386986737C2779343474 @default.
- W4386986737 hasConceptScore W4386986737C2781067378 @default.
- W4386986737 hasConceptScore W4386986737C33923547 @default.
- W4386986737 hasConceptScore W4386986737C41008148 @default.
- W4386986737 hasConceptScore W4386986737C41895202 @default.
- W4386986737 hasConceptScore W4386986737C45804977 @default.
- W4386986737 hasConceptScore W4386986737C50644808 @default.
- W4386986737 hasConceptScore W4386986737C81363708 @default.
- W4386986737 hasConceptScore W4386986737C86803240 @default.
- W4386986737 hasConceptScore W4386986737C9652623 @default.
- W4386986737 hasFunder F4320334764 @default.
- W4386986737 hasLocation W43869867371 @default.