Combining novel feature selection strategy and hyperspectral vegetation indices to predict crop yield

• Published in: Plant methods Vol. 18; no. 1; pp. 1 - 119
• Main Authors: Fei, Shuaipeng, Li, Lei, Han, Zhiguo, Chen, Zhen, Xiao, Yonggui
• Format: Journal Article
• Language: English
• Published: London BioMed Central Ltd 08-11-2022; BioMed Central; BMC
• Subjects: Accuracy; Agricultural production; Analysis; Artificial neural networks; Cereal crops; Classification; Crop yield; Crop yields; Crops; Cultivars; Decision making; Deep learning; Deep neural network; Feature extraction; Feature selection; Flowering; Genetic improvement; Grain; Growth; Hyperspectral; Irrigation; Linear models (Statistics); Linear regression models; Machine learning; Methods; Neural networks; Physiology; Plant breeding; Predictions; Reflectance; Remote sensing; Sensors; Software; Spectrum analysis; Vegetation; Vegetation index; Wheat; Wheat yield; China; United States > US
• ISSN: 1746-4811; 1746-4811
• DOI: 10.1186/s13007-022-00949-0

Wheat is an important food crop globally, and timely prediction of wheat yield in breeding efforts can improve selection efficiency. Traditional yield prediction method based on secondary traits is time-consuming, costly, and destructive. It is urgent to develop innovative methods to improve selection efficiency and accelerate genetic gains in the breeding cycle. Crop yield prediction using remote sensing has gained popularity in recent years. This paper proposed a novel ensemble feature selection (EFS) method to improve yield prediction from hyperspectral data. For this, 207 wheat cultivars and breeding lines were grown under full and limited irrigation treatments respectively, and their canopy hyperspectral reflectance was measured at the flowering, early grain filling (EGF), mid grain filling (MGF), and late grain filling (LGF) stages. Then, 115 vegetation indices were extracted from the hyperspectral reflectance and combined with four feature selection methods, i.e., mean decrease impurity (MDI), Boruta, FeaLect, and RReliefF to train deep neural network (DNN) models for yield prediction. Next, a learning framework was developed by combining the predicted values of the selected and the full features using multiple linear regression (MLR). The results show that the selected features contributed to higher yield prediction accuracy than the full features, and the MDI method performed well across growth stages, with a mean R.sup.2 ranging from 0.634 to 0.666 (mean RMSE = 0.926-0.967 t ha.sup.-1). Also, the proposed EFS method outperformed all the individual feature selection methods across growth stages, with a mean R.sup.2 ranging from 0.648 to 0.679 (mean RMSE = 0.911-0.950 t ha.sup.-1). The proposed EFS method can improve grain yield prediction from hyperspectral data and can be used to assist wheat breeders in earlier decision-making.