Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves
This study aims to clarify the influence of photographic environments under different light sources on image-based SPAD value prediction. The input variables for the SPAD value prediction using Random Forests, XGBoost, and LightGBM were RGB values, HSL values, HSV values, light color temperature (LC...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/17/1/16 |
| _version_ | 1827369930415144960 |
|---|---|
| author | Yuto Kamiwaki Shinji Fukuda |
| author_facet | Yuto Kamiwaki Shinji Fukuda |
| author_sort | Yuto Kamiwaki |
| collection | DOAJ |
| description | This study aims to clarify the influence of photographic environments under different light sources on image-based SPAD value prediction. The input variables for the SPAD value prediction using Random Forests, XGBoost, and LightGBM were RGB values, HSL values, HSV values, light color temperature (LCT), and illuminance (ILL). Model performance was assessed using Pearson’s correlation coefficient (COR), Nash–Sutcliffe efficiency (NSE), and root mean squared error (RMSE). Especially, SPAD value prediction with Random Forests resulted in high accuracy in a stable light environment; COR<sub>RGB+ILL+LCT</sub> and COR<sub>HSL+ILL+LCT</sub> were 0.929 and 0.922, respectively. Image-based SPAD value prediction was effective under halogen light with a similar color temperature at dusk; COR<sub>RGB+ILL</sub> and COR<sub>HSL+ILL</sub> were 0.895 and 0.876, respectively. The HSL value under LED could be used to predict the SPAD value with high accuracy in all performance measures. The results supported the applicability of SPAD value prediction using Random Forests under a wide range of lighting conditions, such as dusk, by training a model based on data collected under different illuminance conditions in various light sources. Further studies are required to examine this method under outdoor conditions in spatiotemporally dynamic light environments. |
| first_indexed | 2024-03-08T09:59:52Z |
| format | Article |
| id | doaj.art-7359dffb12bb41ba821a47f7d51d506c |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-08T09:59:52Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-7359dffb12bb41ba821a47f7d51d506c2024-01-29T13:41:18ZengMDPI AGAlgorithms1999-48932023-12-011711610.3390/a17010016Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish LeavesYuto Kamiwaki0Shinji Fukuda1United Graduate School of Agricultural Science, Tokyo University of Agriculture and Technology, Tokyo 183-8509, JapanInstitute of Agriculture, Tokyo University of Agriculture and Technology, Tokyo 183-8509, JapanThis study aims to clarify the influence of photographic environments under different light sources on image-based SPAD value prediction. The input variables for the SPAD value prediction using Random Forests, XGBoost, and LightGBM were RGB values, HSL values, HSV values, light color temperature (LCT), and illuminance (ILL). Model performance was assessed using Pearson’s correlation coefficient (COR), Nash–Sutcliffe efficiency (NSE), and root mean squared error (RMSE). Especially, SPAD value prediction with Random Forests resulted in high accuracy in a stable light environment; COR<sub>RGB+ILL+LCT</sub> and COR<sub>HSL+ILL+LCT</sub> were 0.929 and 0.922, respectively. Image-based SPAD value prediction was effective under halogen light with a similar color temperature at dusk; COR<sub>RGB+ILL</sub> and COR<sub>HSL+ILL</sub> were 0.895 and 0.876, respectively. The HSL value under LED could be used to predict the SPAD value with high accuracy in all performance measures. The results supported the applicability of SPAD value prediction using Random Forests under a wide range of lighting conditions, such as dusk, by training a model based on data collected under different illuminance conditions in various light sources. Further studies are required to examine this method under outdoor conditions in spatiotemporally dynamic light environments.https://www.mdpi.com/1999-4893/17/1/16lighting conditionsleaf colorsRandom Forests<i>Raphanus sativus</i> L. var. sativusRGBSPAD value |
| spellingShingle | Yuto Kamiwaki Shinji Fukuda Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves Algorithms lighting conditions leaf colors Random Forests <i>Raphanus sativus</i> L. var. sativus RGB SPAD value |
| title | Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves |
| title_full | Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves |
| title_fullStr | Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves |
| title_full_unstemmed | Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves |
| title_short | Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves |
| title_sort | effect of the light environment on image based spad value prediction of radish leaves |
| topic | lighting conditions leaf colors Random Forests <i>Raphanus sativus</i> L. var. sativus RGB SPAD value |
| url | https://www.mdpi.com/1999-4893/17/1/16 |
| work_keys_str_mv | AT yutokamiwaki effectofthelightenvironmentonimagebasedspadvaluepredictionofradishleaves AT shinjifukuda effectofthelightenvironmentonimagebasedspadvaluepredictionofradishleaves |