Monitoring model for predicting maize grain moisture at the filling stage using NIRS and a small sample size

Abstract

The change in the maize moisture content during different growth stages is an important indicator to evaluate the growth status of maize. In particular, the moisture content during the grain-filling stage reflects the grain quality and maturity and it can also be used as an important indicator for breeding and seed selection. At present, the drying method is usually used to calculate the moisture content and the dehydration rate at the grain-filling stage, however, it requires large sample size and long test time. In order to monitor the change in the moisture content at the maize grain-filling stage using small sample set, the Bootstrap re-sampling strategy-sample set partitioning based on joint x-y distances-partial least squares (Bootstrap-SPXY-PLS) moisture content monitoring model and near-infrared spectroscopy for small sample sizes of 10, 20, and 50 were used. To improve the prediction accuracy of the model, the optimal number of factors of the model was determined and the comprehensive evaluation thresholds RVP (coefficient of determination (R 2), the root mean square error of cross-validation (RMSECV) and the root mean square error of prediction (RMSEP)) was proposed for sub-model screening. The model exhibited a good performance for predicting the moisture content of the maize grain at the filling stage for small sample set. For the sample sizes of 20 and 50, the R 2 values were greater than 0.99. The average deviations of the predicted and reference values of the model were 0.1078%, 0.057%, and 0.0918%, respectively. Therefore, the model was effective for monitoring the moisture content at the grain-filling stage for a small sample size. The method is also suitable for the quantitative analysis of different concentrations using near-infrared spectroscopy and small sample size.

Genotype and Environment Influence on the Rate of Grain Moisture Loss in Corn During Ripening Period

“…До наступления физиологической спелости он обусловлен аккумуляцией органического вещества в эндосперме и зависит главным образом от температуры воздуха. После физиологической спелости влага теряется вследствие физического испарения, скорость которого находится в сильной обратной зависимости от относительной влажности воздуха и количества осадков (31,37,38). В результате сложного взаимодействия между генотипом и средой наблюдается неустойчивая динамика потери влаги.…”

A novel virtual sample generation method to improve the quality of data and the accuracy of data-driven models

“…However, there are still many fields, which cannot obtain a large amount of data due to factors, such as high experiment cost and long test cycle. Therefore, it is difficult to apply advanced deep learning algorithm to solve problems [1], such as voice print recognition [2] in multimedia field, disease diagnosis [3] [4] and water analysis [5] in biological and medical field, product sales prediction [6] in the economic field and life prediction of fuel cells [7] in the industrial and military fields. In the process of using machine learning to deal with the above problems, there are problems such as small data volume and data imbalance, etc.…”

A high-throughput phenotyping assay for precisely determining stalk crushing strength in large-scale sugarcane germplasm

“…The near infrared spectroscopy (NIRS) is a very efficient method that has been widely used for high-throughput determine various chemical and biochemical structures of agricultural crop ( Washburn et al., 2013 ). For instances, NIRS has been used for high-throughput predicting fiber and nutrient content of dryland cereal cultivars ( Brenna and Berardo, 2004 ; Stubbs et al., 2010 ), phenotyping of moisture and amylose content in maize ( Wang et al., 2019 ; Dong et al., 2021 ), evaluating the composition of carbohydrates in soybean ( Leite et al., 2020 ; Singh et al., 2021 ), detecting biomass of plant root mixtures ( Roumet et al., 2006 ), analyzing available P contents in soils to aid fertilization ( Patzold et al., 2020 ), as well as determining the internal quality and physiological maturity in the fruit ( Cunha et al., 2016 ; de Carvalho et al., 2019 ; Minas et al., 2021 ). In our previous studies, the NIRS has been successfully applied for stalk quality determination ( Wang et al., 2021 ), cell wall features and lignocellulose digestibility characterization in sugarcane ( Li et al., 2021 ; Adnan et al., 2022 ).…”