Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods

Abstract

<jats:p>Leaf area index (LAI) is an essential vegetation parameter that represents the light energy utilization and vegetation canopy structure. As the only in-operation hyperspectral satellite launched by China, GF-5 is potentially useful for accurate LAI estimation. However, there is no research focus on evaluating GF-5 data for LAI estimation. Hyperspectral remote sensing data contains abundant information about the reflective characteristics of vegetation canopies, but these abound data also easily result in a dimensionality curse. Therefore, feature selection (FS) is necessary to reduce data redundancy to achieve more reliable estimations. Currently, machine learning (ML) algorithms have been widely used for FS. Moreover, the same ML algorithm is usually conducted for both FS and regression in LAI estimation. However, no evidence suggests that this is the optimal solution. Therefore, this study focuses on evaluating the capacity of GF-5 spectral reflectance for estimating LAI and the performances of different combination of FS and ML algorithms. Firstly, the PROSAIL model, which coupled leaf optical properties model PROSPECT and the scattering by arbitrarily inclined leaves (SAIL) model, was used to generate simulated GF-5 reflectance data under different vegetation and soil conditions, and then three FS methods, including random forest (RF), K-means clustering (K-means) and mean impact value (MIV), and three ML algorithms, including random forest regression (RFR), back propagation neural network (BPNN) and K-nearest neighbor (KNN) were used to develop nine LAI estimation models. The FS process was conducted twice using different strategies: Firstly, three FS methods were conducted to search the lowest dimension number, which maintained the estimation accuracy of all bands. Then, the sequential backward selection (SBS) method was used to eliminate the bands having minimal impact on LAI estimation accuracy. Finally, three best estimation models were selected and evaluated using reference LAI. The results showed that although the RF_RFR model (RF used for feature selection and RFR used for regression) achieved reliable LAI estimates (coefficient of determination (R2) = 0.828, root mean square error (RMSE) = 0.839), the poor performance (R2 = 0.763, RMSE = 0.987) of the MIV_BPNN model (MIV used for feature selection and BPNN used for regression) suggested using feature selection and regression conducted by the same ML algorithm could not always ensure an optimal estimation. Moreover, RF selection preserved the most informative bands for LAI estimation so that each ML regression method could achieve satisfactory estimation results. Finally, the results indicated that the RF_KNN model (RF used as feature selection and KNN used for regression) with seven GF-5 spectral band reflectance achieved the better estimation results than others when validated by simulated data (R2 = 0.834, RMSE = 0.824) and actual reference LAI (R2 = 0.659, RMSE = 0.697).</jats:p>

Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods

“…In aforementioned studies, the extracted spectral parameters and ML algorithms are combined to construct inversion models of physiological parameters. In recent years, algorithms for spectral features extraction such as principal component analysis (PCA), variable projection importance (VIP), genetic algorithm (GA), and continuous projection algorithm (SPA) have been widely used in studies of ground monitoring or satellite remote sensing [ 21 , 22 ]. These algorithms can effectively remove the redundancy in hyperspectral data, thus reduce the risk of overfitting, and finally obtained a model of robust and high prediction accuracy [ 23 – 25 ].…”

Combination of Feature Selection and CatBoost for Prediction: The First Application to the Estimation of Aboveground Biomass

“…Previous studies on LAI estimation also reported that using the same machine learning algorithm for both feature selection and regression was not always the optimal solution. It is interesting to note that Chen et al found the VSURF-RFR model to be the best, although in this case, the study object and the method of comparison were different [38]. Overall, our experiment indicates that using the same machine learning algorithm for feature selection and regression does not improve AGB estimation accuracy.…”

“…Machine learning algorithms such as RF have their own built-in feature selection functions that can be used for simultaneous feature selection and regression [38]. However, there is little evidence to indicate that a greater accuracy of AGB estimation is achieved when feature selection and regression are performed with the same algorithm.…”

Genome-Wide Association Studies of Soybean Yield-Related Hyperspectral Reflectance Bands Using Machine Learning-Mediated Data Integration Methods

“…Several studies reported the high potential of using spectral reflectance to estimate and classify the yield ( Yoosefzadeh-Najafabadi et al, 2021a ), leaf area index ( Chen et al, 2020 ), plant stress ( Feng et al, 2020 ), and carbon and nitrogen contents ( Omidi et al, 2020 ). In a study done by Zhang et al (2019) , significant association of red and NIR regions with yield are reported.…”