SPAD value estimation model using lighting information

We constructed a SPAD value estimation model using Random Forests, XGBoost, and LightGBM based on RGB values obtained from images of radish leaves, as well as HSV and HSL values obtained by conversion from RGB values, and color temperature and illuminance as input variables. We focus on the effect of the light environment at the time of photography on the pixel values of digital images and model the relationship between leaf color and SPAD values under varying photographic conditions with respect to the color temperature and illuminance of the light source. Furthermore, based on information such as the variable importance calculated by Random Forests, we examined the influence of photographic conditions on the prediction of SPAD values for agriculture where domain knowledge remains qualitative.

葉の色情報(RGB、HSLおよびHSV)に加えて光環境情報(色温度と照度)を入力変数としたSPAD値推定モデルです。機械学習手法であるRandom Forests、XGBoostおよびLightGBMを用いてモデルを構築し、ピアソン相関係数(COR)、ナッシューサトクリフ係数(NSE)、二乗平均平方根誤差(RMSE)でモデル性能の評価をしています。また、SHapley Additive exPlanations(SHAP)、Partial Dependence plotおよびIndividual Conditional Expectation plotを用いて各モデルにおける変数の貢献度と応答曲線からSPAD値推定における光環境の影響について考察しました。

Yuto Kamiwaki and Shinji Fukuda. 2024. Effect of the Light Environment on Image-Based SPAD Value Prediction of Radish Leaves. Algorithms. 17(2). 16.