Estimation of Soil Total Phosphorus Content in Coastal Areas Based on Hyperspectral Reflectance

Table 1. Statistics of soil TP and SOM contents
View table
View in Article
Table 1. Statistics of soil TP and SOM contents
土壤属性最大值/
(g·kg^-1) 最小值/
(g·kg^-1) 平均值/
(g·kg^-1) 标准差/
(g·kg^-1) 变异系数/
% 峰值K 偏度S
TP 1.30 0.22 0.68 0.19 28.02 1.01 2.19
SOM 52.56 1.39 9.18 8.74 95.21 6.72 0.61

Table 2. Sample set partitioning based on KS

View table

View in Article

Table 2. Sample set partitioning based on KS

统计参数	R		SNV		MSC		FD		SD		RL		CR
统计参数	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集
最小值/(g·kg^-1)	0.22	0.46	0.22	0.51	0.22	0.51	0.22	0.47	0.22	0.44	0.22	0.50	0.22	0.46
最大值/(g·kg^-1)	1.30	1.28	1.30	1.14	1.30	1.14	1.30	1.14	1.30	1.14	1.30	1.28	1.30	1.14
平均值/(g·kg^-1)	0.67	0.76	0.68	0.72	0.68	0.72	0.68	0.72	0.69	0.67	0.67	0.74	0.68	0.71
标准差/(g·kg^-1)	0.19	0.17	0.20	0.13	0.20	0.13	0.20	0.13	0.20	0.17	0.20	0.17	0.20	0.16
变异系数/%	29.11	22.19	30.26	17.99	30.26	17.99	30.16	18.63	28.83	25.15	29.33	22.36	29.48	22.43

Table 3. Sample set partitioning based on SPXP

View table

View in Article

Table 3. Sample set partitioning based on SPXP

统计参数	R		SNV		MSC		FD		SD		RL		CR
统计参数	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集	建模集	预测集
最小值/(g·kg^-1)	0.22	0.49	0.22	0.45	0.22	0.45	0.22	0.50	0.22	0.47	0.22	0.49	0.22	0.46
最大值/(g·kg^-1)	1.30	0.84	1.30	0.84	1.30	0.83	1.30	0.83	1.30	0.84	1.30	0.84	1.30	1.08
平均值/(g·kg^-1)	0.69	0.68	0.68	0.70	0.68	0.70	0.68	0.72	0.69	0.66	0.69	0.68	0.68	0.69
标准差/(g·kg^-1)	0.21	0.13	0.21	0.11	0.21	0.11	0.21	0.10	0.21	0.12	0.21	0.12	0.20	0.14
变异系数/%	30.01	18.61	30.58	15.57	30.57	15.67	30.89	13.50	29.91	17.82	30.09	18.07	29.83	20.20

Table 4. Statistics of partial least square regression
View table
View in Article
Table 4. Statistics of partial least square regression
Partitioning
methods RMSE_c $R_{c}^{2}$ RMSE_p $R_{p}^{2}$ RPD LVs
Min 0.09 0.29 0.07 0.01 1.02 3
RS Max 0.16 0.78 0.19 0.82 2.40 13
Mean 0.11 0.67 0.13 0.51 1.49 9.14
KS 0.11 0.67 0.13 0.42 1.34 9
SPXY 0.11 0.69 0.11 0.26 1.19 9

Table 5. Statistics of support vector machine
View table
View in Article
Table 5. Statistics of support vector machine
Partitioning
methods RMSE_c $R_{c}^{2}$ RMSE_p $R_{p}^{2}$ RPD
Min 0.06 0.73 0.10 0.00 0.86
RS Max 0.11 0.92 0.27 0.61 1.42
Mean 0.09 0.84 0.17 0.20 1.11
KS 0.11 0.80 0.16 0.41 1.09
SPXY 0.10 0.83 0.09 0.46 1.38

Table 6. PLSR calibration and prediction results of different spectral transformation methods and sample-set partitioning methods

View table

View in Article

Table 6. PLSR calibration and prediction results of different spectral transformation methods and sample-set partitioning methods

光谱变换	RS			KS			SPXY
光谱变换	$R_{c}^{2}$	$R_{p}^{2}$	LVs	$R_{c}^{2}$	$R_{p}^{2}$	LVs	$R_{c}^{2}$	$R_{p}^{2}$	LVs
R	0.67	0.50	9.13	0.67	0.42	9	0.69	0.26	9
SNV	0.64	0.47	7.12	0.67	0.28	7	0.63	0.23	6
MSC	0.66	0.48	7.94	0.68	0.29	8	0.67	0.33	8
FD	0.63	0.46	4.38	0.70	0.33	6	0.71	-0.40	6
SD	0.68	0.44	5.01	0.68	0.46	5	0.68	0.27	5
RL	0.67	0.48	8.53	0.66	0.59	9	0.70	0.12	9
CR	0.61	0.48	4.93	0.59	0.35	4	0.58	0.49	4

Table 7. SVM calibration and prediction results of different spectral transformation methods and sample-set partitioning methods

View table

View in Article

Table 7. SVM calibration and prediction results of different spectral transformation methods and sample-set partitioning methods

光谱变换	RS		KS		SPXY
光谱变换	$R_{c}^{2}$	$R_{p}^{2}$	$R_{c}^{2}$	$R_{p}^{2}$	$R_{c}^{2}$	$R_{p}^{2}$
R	0.84	0.20	0.80	0.41	0.83	0.46
SNV	0.89	0.37	0.89	0.55	0.84	0.49
MSC	0.89	0.37	0.89	0.56	0.88	0.79
FD	0.91	0.46	0.92	0.82	0.93	0.76
SD	0.90	0.43	0.90	0.45	0.92	0.78
RL	0.85	0.21	0.80	0.31	0.84	0.49
CR	0.90	0.44	0.90	0.69	0.90	0.71

Tools

Get Citation

Copy Citation Text

Dan-ping WEI, Guang-hui ZHENG. Estimation of Soil Total Phosphorus Content in Coastal Areas Based on Hyperspectral Reflectance[J]. Spectroscopy and Spectral Analysis, 2022, 42(2): 517

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites