Spectral Preprocessing Combined with Deep Transfer Learning to Evaluate Chlorophyll Content in Cotton Leaves

Abstract

Rapid determination of chlorophyll content is significant for evaluating cotton’s nutritional and physiological status. Hyperspectral technology equipped with multivariate analysis methods has been widely used for chlorophyll content detection. However, the model developed on one batch or variety cannot produce the same effect for another due to variations, such as samples and measurement conditions. Considering that it is costly to establish models for each batch or variety, the feasibility of using spectral preprocessing combined with deep transfer learning for model transfer was explored. Seven different spectral preprocessing methods were discussed, and a self-designed convolutional neural network (CNN) was developed to build models and conduct transfer tasks by fine-tuning. The approach combined first-derivative (FD) and standard normal variate transformation (SNV) was chosen as the best pretreatment. For the dataset of the target domain, fine-tuned CNN based on spectra processed by FD + SNV outperformed conventional partial least squares (PLS) and squares-support vector machine regression (SVR). Although the performance of fine-tuned CNN with a smaller dataset was slightly lower, it was still better than conventional models and achieved satisfactory results. Ensemble preprocessing combined with deep transfer learning could be an effective approach to estimate the chlorophyll content between different cotton varieties, offering a new possibility for evaluating the nutritional status of cotton in the field.

Optimized Transfer Learning for Chlorophyll Content Estimations across Datasets of Different Species Using Sun-Induced Chlorophyll Fluorescence and Reflectance

“…The chlorophyll-to-carotenoid ratio provides insights into leaf functionality because C ab varies dynamically throughout the plant growth cycle, while the carotenoid content remains relatively stable before advanced stage of senescence [37,38]. On the other hand, the reflectance-based model yielded results consistent with previous studies, such as Xiao [19] who established transfer models between different cotton cultivars with R 2 ranging from 0.58 to 0.73. For the models based on reflectance spectra, those employing rice dataset #3 as the training set showed the worst average R 2 and RMSE.…”

“…Spectral preprocessing techniques are common methods used to achieve calibration transfer and represent the first step in spectral analysis processing [18]. Xiao [19] found that the transfer model improved after processing with first derivative (FD) and standard normal variate transformation (SNV) compared to traditional partial least squares regression (PLSR) or support vector regression (SVR) models. Additionally, incorporating a portion of new data into the training dataset can improve the transfer learning performance.…”

Prediction and visualization map for physicochemical indices of kiwifruits by hyperspectral imaging

“…Due to the influence of the particle size and surface scattering of the samples ( 21 , 22 ), some noise is included in the acquired original spectra. To improve the prediction accuracy and stability of the detection model, this study used standard normal variation (SNV) to eliminate the noise in the original spectra ( 16 ).…”

Quantifying Contributions of Different Factors to Canopy Photosynthesis in 2 Maize Varieties: Development of a Novel 3D Canopy Modeling Pipeline

“…Some steps in this pipeline still exhibited low throughput, such as measuring leaf chlorophyll content and leaf photosynthetic light response curves. Multispectral or hyperspectral imaging has been employed to predict leaf chlorophyll content [ 69 ] and photosynthetic parameters [ 70 ]; however, challenges exist due to leaf angle and the distance between the light source and the leaves [ 71 ]. The light response curve can be estimated from leaf chlorophyll fluorescence parameters, including quantum yield of PSII (Φ PSII ) and electronic transport rate under varying light intensities [ 72 ].…”