冬小麦叶片光合特征高光谱遥感估算模型的比较研究

张卓,龙慧灵,王崇倡,杨贵军

Comparison of Hyperspectral Remote Sensing Estimation Models Based on Photosynthetic Characteristics of Winter Wheat Leaves

ZHANG Zhuo,LONG HuiLing,WANG ChongChang,YANG GuiJun

表2 利用MLR、ANN、PLS和SVM模拟光合特征参量结果

Table 2 Simulation results summary of photosynthetic characteristic parameters by using MLR, ANN, PLS, and SVM methods

光谱类型 Type of spectrum 模拟结果 Amax Fv′/Fm′ qP MLR ANN SVM PLS MLR ANN SVM PLS MLR ANN SVM PLS 原始光谱 Original spectrum 建模R2 Modeling precision R2 0.75 0.66 0.57 0.67 0.58 0.60 0.94 0.48 0.65 0.45 0.49 0.35 建模RMSE Modeling precision RMSE 5.10 6.13 6.77 5.90 0.03 0.03 0.01 0.04 0.07 0.10 0.09 0.10 验证R2 Validation precision R2 0.50 0.56 0.58 0.66 0.55 0.65 0.44 0.67 0.44 0.21 0.21 0.12 验证RMSE Validation precision RMSE 7.25 7.18 6.60 5.74 0.03 0.03 0.03 0.02 0.09 0.10 0.10 0.10 倒数光谱 Reciprocal of spectrum 建模R2 Modeling precision R2 0.75 0.67 0.57 0.66 0.62 0.57 0.68 0.51 0.54 0.45 0.46 0.44 建模RMSE Modeling precision RMSE 5.12 6.19 6.75 5.93 0.03 0.03 0.03 0.03 0.09 0.10 0.10 0.09 验证R2 Validation precision R2 0.73 0.66 0.56 0.63 0.43 0.63 0.33 0.72 0.40 0.21 0.14 0.16 验证RMSE Validation precision RMSE 5.10 6.52 6.79 6.21 0.03 0.03 0.03 0.02 0.09 0.10 0.10 0.10 对数光谱 Logarithm of spectrum 建模R2 Modeling precision R2 0.74 0.69 0.56 0.65 0.60 0.58 0.62 0.51 0.48 0.43 0.58 0.41 建模RMSE Modeling precision RMSE 5.24 6.17 6.84 6.03 0.03 0.03 0.03 0.03 0.09 0.10 0.09 0.10 验证R2 Validation precision R2 0.75 0.68 0.57 0.59 0.55 0.67 0.41 0.75 0.12 0.15 0.24 0.10 验证RMSE Validation precision RMSE 5.62 6.53 6.74 6.34 0.03 0.03 0.03 0.02 0.10 0.10 0.09 0.10 一阶微分光谱 First derivative of spectrum 建模R2 Modeling precision R2 0.64 0.55 0.70 0.69 0.65 0.75 0.50 0.54 0.38 0.52 0.32 0.38 建模RMSE Modeling precision RMSE 6.11 6.94 5.70 5.70 0.03 0.03 0.04 0.03 0.10 0.10 0.11 0.10 验证R2 Validation precision R2 0.57 0.51 0.50 0.47 0.59 0.51 0.74 0.68 0.02 0.40 0.18 0.11 验证RMSE Validation precision RMSE 6.47 7.02 7.10 7.35 0.02 0.02 0.02 0.02 0.12 0.09 0.09 0.10