UAV- and Machine Learning-Based Retrieval of Wheat SPAD Values at the Overwintering Stage for Variety Screening

Abstract

In recent years, the delay in sowing has become a major obstacle to high wheat yield in Jiangsu Province, one of the major wheat producing areas in China; hence, it is necessary to screen wheat varieties are resilient for late sowing. This study aimed to provide an effective, fast, and non-destructive monitoring method of soil plant analysis development (SPAD) values, which can represent leaf chlorophyll contents, for late-sown winter wheat variety screening. This study acquired multispectral images using an unmanned aerial vehicle (UAV) at the overwintering stage of winter wheat growth, and further processed these images to extract reflectance of five single spectral bands and calculated 26 spectral vegetation indices. Based on these 31 variables, this study combined three variable selection methods (i.e., recursive feature elimination (RFE), random forest (RF), and Pearson correlation coefficient (r)) with four machine learning algorithms (i.e., random forest regression (RFR), linear kernel-based support vector regression (SVR), radial basis function (RBF) kernel-based SVR, and sigmoid kernel-based SVR), resulted in seven SVR models (i.e., RFE-SVR_linear, RF-SVR_linear, RF-SVR_RBF, RF-SVR_sigmoid, r-SVR_linear, r-SVR_RBF, and r-SVR_sigmoid) and three RFR models (i.e., RFE-RFR, RF-RFR, and r-RFR). The performances of the 10 machine learning models were evaluated and compared with each other according to the achieved coefficient of determination (R2), residual prediction deviation (RPD), root mean square error (RMSE), and relative RMSE (RRMSE) in SPAD estimation. Of the 10 models, the best one was the RF-SVR_sigmoid model, which was the combination of the RF variable selection method and the sigmoid kernel-based SVR algorithm. It achieved high accuracy in estimating SPAD values of the wheat canopy (R2 = 0.754, RPD = 2.017, RMSE = 1.716 and RRMSE = 4.504%). The newly developed UAV- and machine learning-based model provided a promising and real time method to monitor chlorophyll contents at the overwintering stage, which can benefit late-sown winter wheat variety screening.

Estimation of grain yield in wheat using source–sink datasets derived from RGB and thermal infrared imaging

“…Furthermore, a comparison in terms of the optimal number of variables selected revealed that PCA selected 35 variables, LASSO selected 35 variables, and RFE selected 31 variables (Table 6). The number of optimal variables selected using RFE is relatively small, which is consistent with the research of (Wang et al, 2021), but the smallest number of variables selected does not represent the best performance of model estimation. Additional studies should be conducted to assess the association between the number of variable choices and model estimation performance.…”

“…Specifically, to further evaluate the effects of source and bank organs on the AGB estimation model and the GY estimation model, experiments with multiple wheat genotypes as well as other crop types under different environmental conditions are also needed (Geipel et al, 2014; Gong et al, 2018; Peng et al, 2019; Wan et al, 2020). On the contrary, due to the limitations of proximity sensors, UAV technology is becoming more and more commonly used for crop phenotype monitoring (Wan et al, 2020; Wang et al, 2021; Xu et al, 2021; Yu et al, 2022; Zhu et al, 2019), so in the next research, UAV technology and proximity sensors can be combined to obtain ultra‐high‐resolution images in multiple directions for more accurate crop yield estimation.…”

“…Recursive feature elimination is the third variable selection algorithm selected in this study. RFE is a well‐known filter feature selection method (Chen et al, 2022; Han et al, 2019; Wang et al, 2021). It designs a “correlation statistic” to measure the importance of features: firstly searching a subset of variables from all variables in the training dataset, each corresponding to an initial feature, removing the least important variables according to the variable ranking, and then fitting the base model with the remaining subset of features (Wang et al, 2021).…”

Oil Palm Yield Prediction Across Blocks Using Multi-Source Data and Machine Learning

“…Reflectance at a green wavelength (used in GCVI and GNDVI) was more sensitive to fluctuation in leaf chlorophyll, which was closely correlated with canopy nitrogen concentration when compared to reflectance at a red wavelength (Zhao et al 2018;Lobell et al 2020;Wang et al 2021). In comparison to standard EVI and NDVI, GCVI and GNDVI are better at capturing nutritional status which accounts for final yield (Burke and Lobell 2017).…”

Soybean leaf estimation based on RGB images and machine learning methods

“…With the ongoing development of sensor and image processing technologies, machine learning-an essential area of computer science-is now extensively applied in all facets of precision agriculture research, including leaf dynamic monitoring [24]. Moreover, machine learning methods are more precise and effective than conventional linear regression models and have been frequently utilized to create prediction models to link image data and biological parameters [25]. There have been few soybean studies to explore the prediction effect of various machine learning models on the leaf parameters of a single plant throughout its entire growth period.…”