Can We Use Laser Technology to Develop a Rapid Feed Test?
Titre de Projet
Developing Innovative Laser-Induced breakdown Spectroscopy Technology with Machine Learning Capability for Rapid Analysis of Cereal Grain and Byproduct Composition
Des Cherchers
Nii Patterson [email protected]
Dr. Amina Hussein, University of Alberta Dr. Mohamad Sabsabi, National Research Council Canada Dr. Mike Jelenski, Veterinary Agri-Health Services Ltd Dr. Allan Feurtado, National Research Council Canada Dr. Bianyun Yu, National Research Council Canada
| Le Statut | Code de Project |
|---|---|
| En cours. Résultats attendus en March, 2027 | FDE.13.24 |
Background
Feed testing is essential to ensure cattle quality of cattle feed and help producers develop rations that adequately meet the animals needs. While feed testing is simple to do it requires samples to be sent to the lab for analysis resulting in delays in being able to utilize feed properly. This team has previously had success determining components of pea flour so want to develop a rapid, laser based test for feed analysis that could be used on farm.
Objectives
- Partner with beef industry to acquire pre-analyzed (NIR and wet chemistry) representative cereal grains and by-product samples and conduct preliminary LIBS analysis
- Perform elemental analysis using ICP-MS instrumentation of representative samples to enhance LIBS calibration
- Optimize analytical capability of LIBS by combining LIBS and MIR and chemometrics methods in order to develop a new, rapid, in situ, and advanced method to quantitatively determine nutrients content in the forage feed.
- Build and leverage predictive models using machine learning to improve measurement accuracy of LIBS
What they will do
LIBS is a technique that uses a high-powered laser to create a plasma from a sample, which then emits light at specific wavelengths. By analyzing these wavelengths, LIBS can identify and measure the elements in the sample, making it useful for quick and accurate analysis of solids, liquids, and gases. This research team wants to test if this technology can be used to determine the nutritional breakdown of specific feed sources.
Commercial nutritionists will send in feed samples, along with their feed test results from a lab. The team will then use those samples to build a library of commonly used feedstuffs to calibrate the laser and use machine learning to improve the test.
Implications
This project is the first step to determine if it is possible to develop a handheld feed test tool. If this is successful we would be one step closer to having a tool that could provide rapid, on farm, feed analysis.