Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties
The urban albedo is regarded as an important indicator for mitigating the urban heat island (UHI) phenomenon. The goal of this paper is to create neural network models that forecast the urban albedo of various reflection directional characteristic urban surfaces by simply inputting the sun’s positio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484723013811 |
| _version_ | 1797378653866164224 |
|---|---|
| author | Jihui Yuan Yasuhiro Shimazaki Shingo Masuko |
| author_facet | Jihui Yuan Yasuhiro Shimazaki Shingo Masuko |
| author_sort | Jihui Yuan |
| collection | DOAJ |
| description | The urban albedo is regarded as an important indicator for mitigating the urban heat island (UHI) phenomenon. The goal of this paper is to create neural network models that forecast the urban albedo of various reflection directional characteristic urban surfaces by simply inputting the sun’s position (altitude and azimuth) and solar radiation. In this study, two urban models with diffuse highly reflective (DHR) and retro-reflective (RR) urban coatings are created, and their urban albedo for two sunny days is calculated using standard (ASTM E1918A). Using the measured urban albedo for one sunny day, two predictive neural network models, Gaussian process (NNGP) and hyperbolic tangent function (NNTanH) are developed (August 1, 2021). The two developed neural network models are used to forecast the urban albedo for another sunny day (July 19, 2021). In the case of DHR urban coatings, the NNTanH model is more accurate with higher R-squared (R2) and lower root mean squared error (RMSE) than the NNGP model, and there is no significant difference between the two neural network models. However, it is demonstrated that the NNGP model is more accurate than the NNTanH model in predicting urban albedo in the case of RR urban coatings, with higher R2 and lower RMSE. |
| first_indexed | 2024-03-08T20:10:47Z |
| format | Article |
| id | doaj.art-1124ff38b8f748a998cbd637e6bb7742 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-03-08T20:10:47Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-1124ff38b8f748a998cbd637e6bb77422023-12-23T05:21:49ZengElsevierEnergy Reports2352-48472023-11-011028502864Neural network models for predicting urban albedo of urban surfaces with different reflection directional propertiesJihui Yuan0Yasuhiro Shimazaki1Shingo Masuko2Dept. of Living Environment Design, Graduate School of Human Life and Ecology, Osaka Metropolitan University, Osaka, Japan; Dept. of Architecture and Civil Eng., Graduate School of Eng., Toyohashi University of Technology, Aichi, Japan; Corresponding author at: Dept. of Living Environment Design, Graduate School of Human Life and Ecology, Osaka Metropolitan University, Osaka, Japan.Dept. of Architecture and Civil Eng., Graduate School of Eng., Toyohashi University of Technology, Aichi, JapanNOMURA Co., Ltd., JapanThe urban albedo is regarded as an important indicator for mitigating the urban heat island (UHI) phenomenon. The goal of this paper is to create neural network models that forecast the urban albedo of various reflection directional characteristic urban surfaces by simply inputting the sun’s position (altitude and azimuth) and solar radiation. In this study, two urban models with diffuse highly reflective (DHR) and retro-reflective (RR) urban coatings are created, and their urban albedo for two sunny days is calculated using standard (ASTM E1918A). Using the measured urban albedo for one sunny day, two predictive neural network models, Gaussian process (NNGP) and hyperbolic tangent function (NNTanH) are developed (August 1, 2021). The two developed neural network models are used to forecast the urban albedo for another sunny day (July 19, 2021). In the case of DHR urban coatings, the NNTanH model is more accurate with higher R-squared (R2) and lower root mean squared error (RMSE) than the NNGP model, and there is no significant difference between the two neural network models. However, it is demonstrated that the NNGP model is more accurate than the NNTanH model in predicting urban albedo in the case of RR urban coatings, with higher R2 and lower RMSE.http://www.sciencedirect.com/science/article/pii/S2352484723013811Urban albedoDifferent reflection directional characteristic urban modelActual experimental measurementsPredictive neural network models |
| spellingShingle | Jihui Yuan Yasuhiro Shimazaki Shingo Masuko Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties Energy Reports Urban albedo Different reflection directional characteristic urban model Actual experimental measurements Predictive neural network models |
| title | Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| title_full | Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| title_fullStr | Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| title_full_unstemmed | Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| title_short | Neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| title_sort | neural network models for predicting urban albedo of urban surfaces with different reflection directional properties |
| topic | Urban albedo Different reflection directional characteristic urban model Actual experimental measurements Predictive neural network models |
| url | http://www.sciencedirect.com/science/article/pii/S2352484723013811 |
| work_keys_str_mv | AT jihuiyuan neuralnetworkmodelsforpredictingurbanalbedoofurbansurfaceswithdifferentreflectiondirectionalproperties AT yasuhiroshimazaki neuralnetworkmodelsforpredictingurbanalbedoofurbansurfaceswithdifferentreflectiondirectionalproperties AT shingomasuko neuralnetworkmodelsforpredictingurbanalbedoofurbansurfaceswithdifferentreflectiondirectionalproperties |