Rapid determination of water content in potato tubers based on hyperspectral images and machine learning algorithms

Abstract

This study investigated the hyperspectral reflectance response of time series generated during oven drying to changes in the moisture content of potato tubers. Seventeen preprocessing methods were used to eliminate the influence of spectral noise on the spectral characteristic curve. Algorithms such as CatBoost, LightGBM, and XGBoost are used to obtain the first 40 effective characteristic spectra of hyperspectral images, which reduces the redundancy of data and improves the prediction accuracy. The water content prediction model of potato tubers was established by using the selected characteristic bands. The results showed that the combined model based on Lasso and XGBoost algorithm had the strongest prediction ability. The best model is MF-Lasso-XGBoost, which has R 2 value of 0.8908, Rmse of 0.0610, Mdae of 0.0389, and R 2 cv of 0.8448. This research can provide reference for the detection of potato moisture content and theoretical basis for the development of crop moisture detector.

Study on the detection of apple soluble solids based on fractal theory and hyperspectral imaging technology

“…We choose to use black and white plate correction to reduce the influence to achieve reflectivity calibration of hyperspectral images. We first cover the lens with the lens cover to acquire the dark background image D, then take down the lens, place the whiteboard to make the height of the whiteboard consistent with the height of the apple sample, and acquire the whiteboard hyperspectral image W. The correction algorithm is as follows (Jiang et al, 2022;Zou et al, 2022) (Equation 1):…”

Hyperspectral image-based measurement of total flavonoid content of leaf-use Ginkgo biloba L.

“…Meanwhile, hyperspectral images are highly correlated between adjacent wavebands, which leads to collinearity and redundancy problems. Optimal wavelength selection algorithm needed to be used to solve the former problem, in order to shorten the time of building prediction models, reduce the dimension of spectral data and promote the performance of prediction models (Zou et al, 2022a(Zou et al, , 2022b.…”

Hyperspectral imaging with a band matrix reduction method to detect early drought stress in tomato

“…The regions of interest in the hyperspectral images corrected by black and white is extracted by using ENVI5.3 (Exelis Visual Information Solutions Inc., USA) software. (Wang et al, 2021;Zou et al, 2022b), which can basically eliminate shadow interference compared with using NVDI to extract the sample pixel, and then the data was exported to Excel. The data of the first 20 bands were removed to avoid the damage of noisy data in the spectral boundary region.…”