Chlorophyll is an important indicator for monitoring crop growth and is vital for agricultural management. Therefore, rapid and accurate estimation of chlorophyll content is important for decision support in precision agriculture to accurately monitor the SPAD (Soil and Plant Analyzer Development) values of winter wheat. This study used winter wheat to obtain canopy reflectance based on UAV hyperspectral data and to calculate different vegetation indices and red-edge parameters. The best-performing vegetation indices and red-edge parameters were selected by Pearson correlation analysis and multiple stepwise regression (MSR). SPAD values were estimated using a combination of vegetation indices, vegetation indices and red-edge parameters as model factors, two types of machine learning (ML), a support vector machine (SVM), and a backward propagation neural network (BPNN), and partial least squares regression (PLSR) for four growth stages of winter wheat, and validated using independent samples. The results show that for the same data source, the best vegetation indices or red-edge parameters for estimating SPAD values differed at different growth stages and that combining vegetation indices with red-edge parameters gave better estimates than using only vegetation indices as an input factor for estimating SPAD values. There is no significant difference between PLSR, SVM, and BPNN methods in estimating SPAD values, with better stability of the estimated models using machine learning methods. Different growth stages have a large impact on winter wheat SPAD values estimates, with the accuracy of the four growth stage models increasing in the following order: booting < heading < filling < flowering. This study shows that using a combination of vegetation indices and red-edge parameters can improve SPAD values estimates compared to using vegetation indices alone. In the future, the choice of appropriate factors and methods will need to be considered when constructing models to estimate crop SPAD values.

Accurately measuring leaf chlorophyll content (LCC) is crucial for monitoring maize growth. This study aims to rapidly and non-destructively estimate the maize LCC during four critical growth stages and investigate the ability of phenological parameters (PPs) to estimate the LCC. First, four spectra were obtained by spectral denoising followed by spectral transformation. Next, sensitive bands (R_λ), spectral indices (SIs), and PPs were extracted from all four spectra at each growth stage. Then, univariate models were constructed to determine their potential for independent LCC estimation. The multivariate regression models for the LCC (LCC-MR) were built based on SIs, SIs + R_λ, and SIs + R_λ + PPs after feature variable selection. The results indicate that our machine-learning-based LCC-MR models demonstrated high overall accuracy. Notably, 83.33% and 58.33% of these models showed improved accuracy when the R_λ and PPs were successively introduced to the SIs. Additionally, the model accuracies of the milk-ripe and tasseling stages outperformed those of the flare–opening and jointing stages under identical conditions. The optimal model was created using XGBoost, incorporating the SI, R_λ, and PP variables at the R3 stage. These findings will provide guidance and support for maize growth monitoring and management.

The estimation of anthocyanin (Anth) content is very important for observing the physiological state of plants under environmental stress. The objective of this study was to estimate the Anth of maize leaves at different growth stages based on remote sensing methods. In this study, the hyperspectral reflectance and the corresponding Anth of maize leaves were measured at the critical growth stages of nodulation, tasseling, lactation, and finishing of maize. First-order differential spectra (FD) were derived from the original spectra (OS). First, the spectral parameters highly correlated with Anth were selected. A total of two sensitive bands (R_λ), five classical vegetation indices (VI_S), and six optimized vegetation indices (VI_C) were selected from the original and first-order spectra. Then, univariate regression models for Anth estimation (Anth-UR models) and multivariate regression models for estimating anthocyanins (Anth-MR models) were constructed based on these parameters at different growth stages of maize. It was shown that the first-order spectral conversion could effectively improve the correlation between R_λ, VI_C, and Anth, and VI_C are usually more sensitive to Anth than VI_S. In addition, the overall performance of Anth-MR models was better than that of Anth-UR models. Among them, Anth-MR models with the combination of three types of spectral parameters (FD(R_λ) + OS_VI_C + FD_VI_C/VI_S) as inputs had the best overall performance. Moreover, different growth stages had an impact on the Anth estimation models, with tasseling and lactation stages showing better results. The best-performing Anth-MR models for these two growth stages were as follows. For the tasseling stage, the best model was the FD(R_λ) + OS_VI_C + VI_S-based SVM model, with an R² of 0.868, RMSE of 0.007, and RPD of 2.19. For the lactation stage, the best-performing model was the FD(R_λ) + OS_VI_C + FD_VI_C-based RF model, with an R² of 0.797, RMSE of 0.007, and RPD of 2.24. These results will provide a scientific basis for better monitoring of Anth using remote sensing hyperspectral techniques.