Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves

• DOI: 10.20944/preprints202311.0168.v1
• Publication Date: 2023-11-06T01:52:58Z
• Authors: Yuto Kamiwaki; Shinji Fukuda
• Keywords: Halogen lamp; Value (mathematics); Noon; RGB color model

This study aims to clarify the influence of photographic environments under different light sources on image-based SPAD value prediction. Radish leaf patches 1.5 cm diameter were photographed halogen or LED light. The input variables for prediction using random forests RGB values, HSL and HSV values. Additionally, color temperature (LCT) illuminance (ILL) used as variables. Model performance was assessed Pearson’s correlation coefficient (COR), Nash-Sutcliffe efficiency (NSE), root mean squared error (RMSE). resulted in high accuracy a stable environment; CORRGB+ILL+LCT CORHSL+ILL+LCT 0.929 0.922, respectively. Image-based effective with similar at dusk; CORRGB+ILL CORHSL+ILL 0.895 0.876, could be predict accuracy; COR, NSE, RMSE 0.972, 0.944, 2.07, partial dependence plots H indicate change from blue green increasing Further studies are required examine this method outdoor conditions spatiotemporally dynamic environments.