CARS Algorithm-Based Detection of Wheat Moisture Content before Harvest

Abstract

To rapidly detect the wheat moisture content (WMC) without harm to the wheat and before harvest, this paper measured wheat and panicle moisture content (PMC) and the corresponding spectral reflectance of panicle before harvest at the Beijing Tongzhou experimental station of China Agricultural University. Firstly, we used correlation analysis to determine the optimal regression model of WMC and PMC. Secondly, we derived the spectral sensitive band of PMC before filtering the redundant variables competitive adaptive reweighted sampling (CARS) to select the variable subset with the least error. Finally, partial least squares regression (PLSR) was used to build and analyze the prediction model of PMC. At the early stage of wheat harvest, a high correlation existed between WMC and PMC. Among all regression models such as exponential, univariate linear, polynomial models, and the power function regression model, the logarithm regression model was the best. The determination coefficients of the modeling sample were: R2 = 0.9284, the significance F = 362.957, the determination coefficient of calibration sample R2v = 0.987, the root mean square error RMSEv = 3.859, and the relative error REv = 7.532. Within the range of 350–2500 nm, bands of 728–907 nm, 1407–1809 nm, and 1940–2459 nm had a correlation coefficient of PMC and wavelength reflectivity higher than 0.6. This paper used the CARS algorithm to optimize the variables and obtained the best variable subset, which included 30 wavelength variables. The PLSR model was established based on 30 variables optimized by the CARS algorithm. Compared with the all-sensitive band, which had 1103 variables, the PLSR model not only reduced the number of variables by 1073, but also had a higher accuracy in terms of prediction. The results showed that: RMSEC = 0.9301, R2c = 0.995, RMSEP = 2.676, R2p = 0.945, and RPD = 3.362, indicating that the CARS algorithm could effectively remove the variables of spectral redundant information. The CARS algorithm provided a new way of thinking for the non-destructive and rapid detection of WMC before harvest.

A Framework for Retrieving Soil Organic Matter by Coupling Multi-Temporal Remote Sensing Images and Variable Selection in the Sanjiang Plain, China

“…As it does not require any demanding mathematical formulation, RF is easy to implement [27]. CARS is an effective spectral variable selection algorithm that selects key variables using an exponentially decreasing function and adaptive reweighted sampling [28]. These were combined with Partial Least Squares Regression (PLSR) to build SOM retrieval models, and the optimal model was used for SOM mapping in the study area.…”

Selection of the Most Informative Wavenumbers to Improve Prediction Accuracy of Milk Fatty Acid Profile Based on Milk Mid-Infrared Spectra Data

“…Another practical approach to improve model robustness is to select optimal variables before modeling MIR spectra data, such as removing the regions associated with water or less informative MIR spectra regions (i.e., 1,600 to 1,700 and 3,000 to 3,500 cm -1 ) to reduce the data noise [21]. Some feature selection algorithms have been shown to accurately screen for informative variables and generate significant improvements in the prediction accuracy for milk titratable acidity and calcium content [22] protein fractions [23], A1 and A2 milk [24], and cow's live weight [25] by combining the PLS method with the Uninformative Variable Elimination (UVE) or Competitive Adaptive Reweighted Sampling (CARS) methods based on MIR spectra [26,27]. Therefore, a feature selection algorithm is recommended to build simpler but more robust models to avoid overfitting or deleting valid variables, improve the prediction ability of MIR spectra, and identify the wavenumbers or their combinations that are more related to the target traits.…”