Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method

Qingling Bao; Jianli Ding; Jingzhe Wang

doi:10.3788/LOP55.113002

Journals >Laser & Optoelectronics Progress >Volume 55 >Issue 11 >Page 113002 > Article

Laser & Optoelectronics Progress
Vol. 55, Issue 11, 113002 (2018)

Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method

Qingling Bao^1、2, Jianli Ding^1、2、*, and Jingzhe Wang^1、2

Author Affiliations

¹ Key Laboratory of Wisdom City and Environmental Modeling, College of Resource and Environment Sciences, Xinjiang University, Urumqi, Xinjiang 830046, China

² Key Laboratory of Oasis Ecology, Ministry of Education, Xinjiang University, Urumqi, Xinjiang 830046, China

show less

DOI: 10.3788/LOP55.113002 Cite this Article Set citation alerts

Qingling Bao, Jianli Ding, Jingzhe Wang. Prediction of Soil Moisture Content by Selecting Spectral Characteristics Using Random Forest Method[J]. Laser & Optoelectronics Progress, 2018, 55(11): 113002 Copy Citation Text

show less

Fig. 1. Schematic of spectral acquisition experiment

Download full size

Spectral reflectance curves and spectral absorption characteristic curves of sample with different soil moisture contents. (a) Spectral reflectance curves; (b) spectral absorption characteristic curves

Fig. 2. Spectral reflectance curves and spectral absorption characteristic curves of sample with different soil moisture contents. (a) Spectral reflectance curves; (b) spectral absorption characteristic curves

Download full size

Fig. 3. Contribution degree of 18 spectral absorbance characteristic parameters on SMC

Download full size

Fig. 4. Measured and predicted values of SMC

Download full size

Sample set	Sample size	Mean value	Standard deviation	Maximum value	Minimum value	CV /%
Whole set	38	14.59	5.76	23.94	1.48	39.48
Calibration set	25	15.10	5.44	23.94	1.48	36.01
Validation set	13	13.61	6.45	21.15	1.95	47.38

Table 1. Statistical characteristics of soil sample moisture content

Spectral absorptioncharacteristic parameter	SMC absorptionband /nm	Correlationcoefficient
D	1400	0.90^**
A	1400	0.95^**
D_A	1400	-0.68^**
L_a	1400	0.95^**
R_a	1400	0.93^**
S	1400	-0.13
D	1900	0.86^**
A	1900	0.73^**
D_A	1900	0.49^**
L_a	1900	0.72^**
R_a	1900	0.71^**
S	1900	-0.05
D	2200	0.93^**
A	2200	0.90^**
D_A	2200	-0.04
L_a	2200	0.90^**
R_a	2200	0.90^**
S	2200	0.30

Table 2. Correlation analysis between spectral absorption characteristic parameters and SMC

Model	Training set		Test set
Model	R²	e_RMSE	R²	e_RMSE
Random forest	0.87	1.82	0.83	2.46

Table 3. Simulation accuracy of SMC at surface layer

Model	Regression equation	Calibration set		Validation set
Model	Regression equation	$\begin{matrix} R_{c}^{2} \end{matrix}$	e_RMSEC	$\begin{matrix} R_{p}^{2} \end{matrix}$	e_RMSEP	R_PD
MLSR	Y=3.68+2.16A₂₂₀₀+96.29D₂₂₀₀	0.88	2.08	0.89	2.21	2.80

Table 4. Predicted SMC

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information