Predicting Grassland Leaf Area Index in the Meadow Steppes of Northern China: A Comparative Study of Regression Approaches and Hybrid Geostatistical Methods

Abstract

Leaf area index (LAI) is a key parameter used to describe vegetation structures and is widely used in ecosystem biophysical process and vegetation productivity models. Many algorithms have been developed for the estimation of LAI based on remote sensing images. Our goal was to produce accurate and timely predictions of grassland LAI for the meadow steppes of northern China. Here, we compare the predictive power of regression approaches and hybrid geostatistical methods using Chinese Huanjing (HJ) satellite charge coupled device (CCD) data. The regression methods evaluated include partial least squares regression (PLSR), artificial neural networks (ANNs) and random forests (RFs). The two hybrid geostatistical methods were regression kriging (RK) and random forests residuals kriging (RFRK). The predictions were validated for different grassland types and different growing stages, and their performances were also examined by adding several groups of vegetation indices (VIs). The two hybrid geostatistical models (RK and RFRK) yielded the most accurate predictions (root mean squared error (RMSE) = 0.21 m 2 /m 2 and 0.23 m 2 /m 2 for RK and RFRK, respectively), followed by the RF model (RMSE = 0.27 m 2 /m 2 ), which was the most accurate among the regression models. These three models also exhibited the best temporal performance across the duration of the growing season. The PLSR and ANN models were less accurate (RMSE = 0.33 m 2 /m 2 and 0.35 m 2 /m 2 for ANN and PLSR, respectively), and the PLSR model performed the worst (exhibiting varied temporal performance and unreliable prediction accuracy that was susceptible to ground conditions). By adding VIs to the predictor variables, the predictions of the PLSR and ANN models were obviously improved (RMSE improved from 0.35 m 2 /m 2 to 0.28 m 2 /m 2 for PLSR and from 0.33 m 2 /m 2 to 0.28 m 2 /m 2 for ANN); the RF and RFRK models did not generate more accurate predictions and the performance of the RK model declined (RMSE decreased from 0.21 m 2 /m 2 to 0.32 m 2 /m 2 ).

Estimation of Rice Growth Parameters Based on Linear Mixed-Effect Model Using Multispectral Images from Fixed-Wing Unmanned Aerial Vehicles

“…ANN regression models have been successfully applied to estimate crop properties, such as crop biomass [18], LAI [19] and foliage nitrogen concentrations [22]. A range of studies used the RF regression model to map crop attributes, for example, biomass retrieval [23], LAI retrieval [24] and nitrogen status monitoring [25].…”

Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models

“…Suitable principal components for the PLS model were chosen based on the variance explained by the independent variable. The optimal number of principal components was 5, and the cumulative rate of variables was 94% for the whole growth period; the optimal number of principal components and cumulative rate of variables were 5 and 80% for the single growth period [32]. The parameters of the final model after parameter optimization and multiple training are shown in Table 2.…”

“…The RF regression model references parameters reported in previous literature [23,32], and the tree number was set to 500 for the whole and single growth periods. The ANN regression model used a training subset and multiple iterations to derive the appropriate parameters [32]. The "tune.svm" function in R3.2.0 was used to find the optimal parameters for the SVM regression model [11,23].…”

“…LAI was measured with an LAI-2200C canopy analyzer (produced by the USA Li-Cor, Lincoln, NE, USA) [32]. The instrument uses a "fish-eye" optical sensor with a 270 • vertical field of view and a 360 • horizontal field of view to measure transmitted light at 5 angles above and below the canopy.…”

Comparison of the retrieving precision of potato leaf area index derived from several vegetation indices and spectral parameters of the continuum removal method

“…Therefore, it may be a simpler and more inexpensive method for laypersons other than researchers in remote sensing to estimate crop LAI. Certainly, for some multispectral data, machine learning methods, such as decision tree learning, artificial neural networks (ANNs) (Kimes, Nelson, Manry, & Fung, 1998), support vector machines (SVMs, Durbha, King, & Younan, 2007), and random forests (RFs) (Liang et al, 2015) are also increasingly employed to optimize the use of spectral information with the goal of minimizing prediction uncertainty (Li et al, 2016).…”