Prediction of Eggplant Leaf Fv/Fm Based on Vis-NIR Spectroscopy

Chlorophyll fluorescence parameter F-v/F-m is an important indicator to investigate the effects of stress on plant photosynthesis. Previous studies showed a high linear correlation between vegetation index and F-v/F-m, However, fitting F-v/F-m, and vegetation index directly showed insufficient an accuracy. In order to achieve accurate prediction of this parameter, this research took eggplant as the research object, and proposed a F-v/F-m, prediction method based on Vis-NIR Spectroscopy. The experiment obtained visible-near infrared spectrum data and F-v/F-m, of eggplant leaves in different growth states, Monte Carlo Sampling (MCS) method was used to remove obvious abnormal samples. Three spectral preprocessing methods and 5 characteristic wavelength selection algorithms were adopted for spectral data processing. Partial least squares regression (PLSR) models were built to evaluate these methods. Based on the optimal characteristic wavelength combinations, F-v/F-m, prediction models were established by four machine learning algorithms: back propagation (BP) neural network, radial basis function (RBF) neural network, extreme learning machine (ELM), and regression support vector machine (SVR). The effects of the algorithms on the accuracy of the F-v/F-m, prediction model were analyzed. Therefore, the optimal combination of the above methods, for F-v/F-m, prediction was confirmed. The results were as follows: the spectral reflectance of eggplant leaves decreased significantly with the increase of F-v/F-m, indicating the feasibility of retrieving F-v/F-m, by spectral information. Based on 293 sets of experimental samples, two sets of characteristic wavelengths with optimal modeling effect were extracted, which were pre-processed by multivariate scattering correction (MSC) and standard normal variable transformation (SNV) respectively, and screened by the combination use of competitive adaptive reweighted sampling method and successive projections algorithm(CARS -b SPA). Among them, the test set determination coefficient (R-2) of MSC-CARS-SPA-PLSR and SNV-CARS-SPA-PLSR was 0.8961 and 0.8812 respectively. The root means square error was 0.0118 and 0.0126. Both showed higher accuracy than the PLSR model of the full spectrum data. Meanwhile, both methods selected 12 characteristic wavelengths, which only accounted for 0.88% of the full spectrum (1358). This indicated a small number of wavelengths conducive to model accuracy were selected. Among the machine learning models established by optimal wavelengths, SNV-CARS-SPA-SVR obtained the highest prediction accuracy, with a determination coefficient of 0.9117 and root mean square error of 0.0108 the test set. Thus, the SNVCARS-SPA-SVR modeling method used in this research improved the accuracy of the model and effectively reduced the complexity of the model, providing an implementation method for accurate prediction of F-v/F-m, based on the visible-near infrared spectrum. This method can be further applied in rapid and non-destructive detection of crop growth status and early warning of agricultural conditions.