Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network

Abstract

Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.

Evaluating pearl millet and mungbean intercropping in the semi‐arid regions of Senegal

“…High biomass production and low grain yield in millet is known as an adaptative response under stress conditions such as mineral deficiency, pest damage, and weed pressure (Andrews, Rajewski, & Kumar, 1993). In droughtprone environments, high biomass production for rain-fed crops such as millet is attributed to high-tillering capacity (Van Oosterom et al, 2002;Ausiku et al, 2020) and rapid leaf area expansion (Winkel, Payne, & Renno, 2001).…”

Salt tolerance and foliar spectral responses in seedlings of four ornamental herbaceous species

“…This same pattern was observed at 670 nm, which represents the red region. The deeper this valley is -that is, the lower the reflectance factor (RF) -the greater the presence of chlorophylls a and b available for photosynthesis (Xiaoyan et al, 2020). In addition, we can speculate that no difference was detected in water concentrations in the samples of all treatments because a greater water status for leaf tissues is manifested by greater depths in shortwave infrared -SWIR I and II, mainly in the absorption valleys at 1450 nm and 1900 nm (Quemada et al, 2021).…”

Simultaneous determination of pigments of spinach (Spinacia oleracea L.) leaf for quality inspection using hyperspectral imaging and multi-task deep learning regression approaches

“…Various studies have been reported for leaf pigment content prediction using hyperspectral imaging with deep learning models. In most studies, the CNN models have shown better or equivalent performances compared with the conventional machine learning methods ( Wang, Li, Wang, & Wang, 2020 , Ye et al, 2024 , Zhang et al, 2023 , Zhang et al, 2022 ). In these researches, the prediction performances of pigment content varied largely, due to the differences on the acquired samples and data.…”