Prediction of milling yield in wheat with the use of spectral, colour, shape, and morphological features

Assadzadeh, Sahand; Walker, Cassandra K.; McDonald, Linda S.; Panozzo, Joe

doi:10.1016/j.biosystemseng.2021.12.005

Cited by 15 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three key quality traits milling yield (Assadzadeh et al, 2022; Dowell et al, 2006), dough water absorption (Dowell et al, 2006), and maximum resistance (Békés et al, 2001) are considered important in breeding programs. These traits were the focus of this study and were compared over three breeding generations to determine the reliability of the selection strategy using NIRS to predict values in the first generation; small‐scale testing on the second generation (Figure 1) improved outcomes in the third generation when lines were assessed using large‐scale tests (Figure 1).…”

Section: Resultsmentioning

confidence: 99%

Near‐infrared spectroscopy enables quality selection in wheat breeding

Walker,

Panozzo

2023

Cereal Chem

Self Cite

View full text Add to dashboard Cite

Background and objectivesThe use of Near Infrared spectroscopy (NIRS) and small‐scale testing to evaluate wheat germplasm is a cost‐effective strategy to reduce thousands of wheat lines to hundreds and then to tens of lines. Identifying high quality germplasm among thousands of lines is dependent on the accuracy of the tests which are employed, and how well these data correlate with the large‐scale test which are used confirm the end‐use quality prior to commercial release of a new wheat variety. In this study NIR‐based testing was investigated to determine the effectiveness of this high‐throughput, non‐destructive technology.FindingsTo demonstrate the effectiveness of NIRS and small‐scale testing as a selection strategy, interpretive population statistics evaluating three consecutive generations (F4, F5, F6) from a wheat breeding program were compared. The F4 (early‐stage) generation (2019) were predicted for milling yield with a proportion of 13.9 % of lines above 74% (w/w) milling yield. From those lines that progressed to F5 (mid‐generation in 2020), the portion increased to 26.2 % of lines above 74% (w/w) milling yield. Selected lines from F5 were progressed to F6 (advanced generation in 2021) where 62.4 % of lines were above 74% (w/w) milling yield.ConclusionsEach time the set progressed through the selection strategy the portion of lines above 74% (w/w) milling yield increased.Significance and noveltyThis study demonstrates the value and efficiency of high‐throughput selection strategies using non‐destructive NIRS at the F4 (early‐stage generation) stage and small‐scale testing at F5 of a wheat breeding program.This article is protected by copyright. All rights reserved.

show abstract

Section: Resultsmentioning

confidence: 99%

Near‐infrared spectroscopy enables quality selection in wheat breeding

Walker,

Panozzo

2023

Cereal Chem

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite the advances in deep learning models in terms of performance (Goodfellow et al ., 2016) and their use in the field of wheat processing (Sabanci et al ., 2020; Assadzadeh et al ., 2022), models such as artificial neural network (ANN) are still difficult to interpret and require large amounts of data to be trained and to achieve good performance.…”

Section: Methodsmentioning

confidence: 99%

A decision support tool for the first stage of the tempering process of organic wheat grains in a mill

Parrenin

Danjou

Agard

et al. 2023

Int J of Food Sci Tech

View full text Add to dashboard Cite

SummaryWheat tempering conditions grains before a milling process begins. Process adjustments must be made to reach a desired level of flour quality and yield, depending on multiple factors. This article aims to develop a decision support tool to help operators adjust the first‐stage tempering parameters. It is based on a regression model that predicts an increase in organic wheat moisture content according to the properties of the wheat (initial wheat moisture content, wheat protein content and wheat temperature), process parameters (targeted wheat moisture content, wheat flow rate, water flow rate, wheat quantity and resting time) and tempering conditions (water quantity, average day temperature and average day humidity). The increase in wheat moisture achieved during the first tempering stage varies between 0% and 5%. Five regression models were compared: OLS, LASSO, RIDGE, ElasticNet and XGBoost. The models have been developed and tested from a case study at an organic wheat mill. The results indicate that the LASSO model outperformed others, with an average prediction error of 0.428%. The model showed the importance of humidity and temperature factors during the tempering process. The flow of water and wheat were the most influential parameters for an increase in wheat moisture content.

show abstract

“…Grain quality when received by grain receival agents is graded using two approaches: firstly, subjective procedures undertaken by trained operators (grain inspectors) assessing visual traits, including stained, cracked, defective grain and contaminants; and secondly objectively using standardised instrumentation, such as sieves to determine grain size and near infrared spectroscopy (NIR) to determine composition, such as protein and moisture concentration. Key traits used in valuing and trading grain include the percentage of small grain (screenings), foreign material (unable to be processed, milled or malted), contaminates, sprouted, stained or discoloured grain, broken, damaged or distorted grain, presence of insects or mould, test weight, or composition including moisture concentration, protein concentration, low levels of aflatoxins and a high Hagberg falling number test [8][9][10][11]. Many of these traits are measured as a % per weight of samples subsampled from the grain load.…”

Section: Of 24mentioning

confidence: 99%