Leaf Nitrogen Concentration Retrieval Based on Polarization Reflectance Model and Random Forest Regression

Zi-han ZHANG; Lei YAN; Si-yuan LIU; Yu FU; Kai-wen JIANG; Bin YANG; Sui-hua LIU; Fei-zhou ZHANG

doi:10.3964/j.issn.1000-0593(2021)09-2911-07

Journals >Spectroscopy and Spectral Analysis >Volume 41 >Issue 9 >Page 2911 > Article

Spectroscopy and Spectral Analysis
Vol. 41, Issue 9, 2911 (2021)

Leaf Nitrogen Concentration Retrieval Based on Polarization Reflectance Model and Random Forest Regression

Zi-han ZHANG^1、*, Lei YAN^{1、1; 2;}, Si-yuan LIU^1、1;, Yu FU^1、1;, Kai-wen JIANG^1、1;, Bin YANG^3、3;, Sui-hua LIU^4、4;, and Fei-zhou ZHANG^{1、1; *;}

Author Affiliations

¹1. Beijing Key Lab of Spatial Information Integration and 3S Application, Institute of Remote Sensing and Geographic Information System, School of Earth and Space Science, Peking University, Beijing 100871, China

³3. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China

⁴4. School of Geography and Environmental Science, Guizhou Normal University, Guiyang 550001, China

show less

DOI: 10.3964/j.issn.1000-0593(2021)09-2911-07 Cite this Article

Zi-han ZHANG, Lei YAN, Si-yuan LIU, Yu FU, Kai-wen JIANG, Bin YANG, Sui-hua LIU, Fei-zhou ZHANG. Leaf Nitrogen Concentration Retrieval Based on Polarization Reflectance Model and Random Forest Regression[J]. Spectroscopy and Spectral Analysis, 2021, 41(9): 2911 Copy Citation Text

show less

Fig. 1. Spatial distribution of foliar nitrogen content retrieval plot

Download full size | View in the Article

Fig. 2. Flowchart of data utilization

Download full size | View in the Article

Fig. 3. Ratio of PBRF to BRF
In this figure, the × in the box represents the mean value, and the transverse line in the box represents the median value

Download full size | View in the Article

树种	IGBP类别	类名
欧洲云杉	IGBP01	常绿针叶林
欧洲山毛榉	IGBP04	落叶阔叶林
欧洲冷杉	IGBP01	常绿针叶林
假挪威槭	IGBP04	落叶阔叶林
欧洲花楸	IGBP04	落叶阔叶林

Table 1. IGBP classes of dominant vegetation in Bavarian Forest National Park

View in the Article

模型名称	公式	应用场景	自由参数
Nadal模型	$PBRF = A [1 - \exp (- B \frac{F_{p} (γ, N)}{μ_{S} + μ_{V}})]$	森林、灌木林和低植被地表覆盖类型	A, B
Waquet模型	$PBRF = A F_{p} (γ, N) S (θ_{S}) S (θ_{V})$ [其中,S(θ)为后向散射中最大值的遮蔽函数]	森林、作物种植地和城市地表覆盖类别	A, B
Maignan模型	$PBRF = A \frac{\exp (- \tan α_{I}) \exp (- NDVI) F_{p} (γ, N)}{4 (μ_{S} + μ_{V})}$	植被地表覆盖类型	A
Litvinov模型	$\begin{array}{l} PBRF = A \frac{π F_{p} (γ, N)}{4 (μ_{S} + μ_{V}) \cos θ_{H}} S (γ, C) f (B, θ_{H}) \end{array}$ [其中,$f(B,{θ}_{H}) $表征的是地表在空间中的高斯分布,S(γ,C)是遮蔽函数]	植被和土壤地表覆盖类型	A, B, C
Diner模型	$PBRF = A \frac{F_{p} (γ, N)}{8 π μ_{S} μ_{V} \cos θ_{H}}$	草地地表覆盖类型	A

Table 2. Formulas of 5 BPDF models

View in the Article

类别	Nadal模型		Waquet模型		Maignan模型		Litvinov模型		Diner模型
类别	RSQ	RMSE	RSQ	RMSE	RSQ	RMSE	RSQ	RMSE	RSQ	RMSE
IGBP01	0.697	0.003	0.690	0.003	0.695	0.003	0.688	0.003	0.655	0.003
IGBP04	0.875	0.002	0.857	0.002	0.871	0.002	0.878	0.002	0.821	0.002
IGBP05	0.812	0.002	0.789	0.002	0.818	0.002	0.808	0.002	0.759	0.002