AUTHOR=Feng Zi-Heng , Wang Lu-Yuan , Yang Zhe-Qing , Zhang Yan-Yan , Li Xiao , Song Li , He Li , Duan Jian-Zhao , Feng Wei 

TITLE=Hyperspectral Monitoring of Powdery Mildew Disease Severity in Wheat Based on Machine Learning

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.828454

DOI=10.3389/fpls.2022.828454

ISSN=1664-462X

ABSTRACT=Powdery mildew has a negative impact on wheat growth and restricts yield formation. Therefore, accurate monitoring of the disease is of great significance for the prevention and control of powdery mildew to protect world food security. The canopy spectral reflectance was obtained using a ground feature hyperspectrometer during the flowering and filling periods of wheat. Based on the Savitzky-Golay smoothing of the spectral data, the original reflectivity (OR) was spectrally transformed using the mean centralization (MC), multivariate scattering correction (MSC), and standard normal variate transform (SNV) methods. The feature bands of the four transformed spectral data were extracted through a combination of the CARS and SPA algorithms, and then partial least square regression (PLSR), support vector regression (SVR), and random forest regression (RFR) were used to construct an optimal monitoring model for wheat powdery mildew disease index (mDI). The results showed that after Pearson correlation, two-band optimization combinations and machine learning method modeling comparisons, the comprehensive performance of the MC spectrum data was the best, and it was a better method for pretreating disease spectrum data. The transformed spectral data combined with the CARS-SPA algorithm was able to extract the characteristic bands more effectively. In our comparison of different machine learning modeling methods, the RFR model performed the best (R2=0.741-0.852), while the SVR and PLSR models performed similarly (R2=0.733-0.836). Taken together, the estimation accuracy of spectral data transformation using the MC method combined with the RFR model (MC-RFR) was the highest, the model R2 was 0.849-0.852, and the RMSE and MAE ranged from 2.084-2.177 and 1.684-1.777, respectively. Compared with the OR combined with the RFR model (OR-RFR), the R2 increased by 14.39%, and the R2 of RMSE and MAE decreased by 23.9% and 27.87%. It can be seen that the use of MC to preprocess spectral data, the use of CARS and SPA algorithms to extract characteristic bands, and the use of RFR modeling methods can improve the accuracy of remote sensing monitoring of powdery mildew disease in wheat. The research results from our study provide ideas and methods for realizing high-precision remote sensing monitoring of crop disease status.