A Comparison of Regression Techniques for Estimation of Above-Ground Winter Wheat Biomass Using Near-Surface Spectroscopy

Abstract

Above-ground biomass (AGB) provides a vital link between solar energy consumption and yield, so its correct estimation is crucial to accurately monitor crop growth and predict yield. In this work, we estimate AGB by using 54 vegetation indexes (e.g., Normalized Difference Vegetation Index, Soil-Adjusted Vegetation Index) and eight statistical regression techniques: artificial neural network (ANN), multivariable linear regression (MLR), decision-tree regression (DT), boosted binary regression tree (BBRT), partial least squares regression (PLSR), random forest regression (RF), support vector machine regression (SVM), and principal component regression (PCR), which are used to analyze hyperspectral data acquired by using a field spectrophotometer. The vegetation indexes (VIs) determined from the spectra were first used to train regression techniques for modeling and validation to select the best VI input, and then summed with white Gaussian noise to study how remote sensing errors affect the regression techniques. Next, the VIs were divided into groups of different sizes by using various sampling methods for modeling and validation to test the stability of the techniques. Finally, the AGB was estimated by using a leave-one-out cross validation with these powerful techniques. The results of the study demonstrate that, of the eight techniques investigated, PLSR and MLR perform best in terms of stability and are most suitable when high-accuracy and stable estimates are required from relatively few samples. In addition, RF is extremely robust against noise and is best suited to deal with repeated observations involving remote-sensing data (i.e., data affected by atmosphere, clouds, observation times, and/or sensor noise). Finally, the leave-one-out cross-validation method indicates that PLSR provides the highest accuracy (R 2 = 0.89, RMSE = 1.20 t/ha, MAE = 0.90 t/ha, NRMSE = 0.07, CV (RMSE) = 0.18); thus, PLSR is best suited for works requiring high-accuracy estimation models. The results indicate that all these techniques provide impressive accuracy. The comparison and analysis provided herein thus reveals the advantages and disadvantages of the ANN, MLR, DT, BBRT, PLSR, RF, SVM, and PCR techniques and can help researchers to build efficient AGB-estimation models.

Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features

“…They suggested that hyperspectral data could improve the estimation results, and our study showed that this was a valid assumption in many situations. Yue et al [51] compared eight different regression techniques for the winter wheat biomass estimation, using near-surface spectroscopy and achieved R 2 values of 0.79-0.89. They concluded that machine learning techniques such as RF were less sensitive to noise than conventional regression techniques.…”

“…feature importance order), and it is less sensitive to overfitting and in parameter selection [45][46][47]. In biomass estimation, RF has shown competitive accuracy among other estimation methods applied in forestry [43,48] and in agricultural [32,[49][50][51] applications. Only some studies have used RF in crop parameter estimations.…”

“…Liu et al [50] used RF to estimate the nitrogen level of wheat using multispectral data. Li et al [32] and Yue et al [51] used successfully RF for estimating the biomass of maize and winter wheat. Previously, Viljanen et al [5] used RF for the fresh and dry matter biomass estimation of grass silage, using 3D and multispectral features.…”

A frequency-domain machine learning method for dual-calibrated fMRI mapping of oxygen extraction fraction (OEF) and cerebral metabolic rate of oxygen consumption (CMRO2)

“…An alternative approach to reduce the prediction error is the use of 70 noise insensitive machine learning regression methods. Decision tree based regression methods, for 71 example random forest (Breiman, 2001) and extremely randomized trees (Geurts et al, 2006), are 72 robust to both output (Breiman, 2001;Geurts et al, 2006) and input noise (Yue et al, 2018) and are 73 able to capture non-linear relationships between input features and target parameters. This noise 74 immunity is likely due to the randomization included in the choices of features at splitting nodes 75 (random forest) and cut-points (extremely randomized trees), which improve the generalizability of 76 the regressors.…”

Mapping Spatial Variations of Structure and Function Parameters for Forest Condition Assessment of the Changbai Mountain National Nature Reserve

“…Whereas, complex forest parameters such as biomass, soil fertility, and forest age are generally estimated by multi-sensor data [26][27][28][29].Modeling vegetation parameters based on remote sensing can be divided into physically based models and empirical regression algorithms [18,21,30]. Physically based models depend on numerous factors to simulate canopy reflectance, such as leaf geometry, chlorophyll concentration, water and matter contents, soil reflectance, and bidirectional reflectance distribution function, which may not be readily available [31,32]. Those are built conventionally as semi-physical models by simplifying factors based on prerequisite assumptions and using machine learning or regression methods trained with radiative transfer, which achieve robust performance [33,34].…”