PhD thesis of Zanjan University in collaboration with Midran Company
Title of thesis: Using artificial intelligence in genetic evaluation of the pregnancy failure trait in industrial Holstein cattle herds in Iran
Supervisory and advisory team: Dr. Mohammad Bagher Zandi – Dr. Morad Pasha Eskandari Nasab – Eng. Mohammad Vakili
PhD student: Masoud Zandiyeh
The dairy cattle breeding industry in Iran is considered one of the important axes of providing animal protein and economic development of the country. In the meantime, the Holstein breed, due to its high efficiency in milk production, has accounted for a major share of the country’s industrial herds.
However, one of the main challenges in dairy herd management is the phenomenon of pregnancy failure, which has a direct impact on the production efficiency and economy of livestock farming units.
Studies show that this phenomenon can affect up to 15-20% of pregnancies and cause significant economic losses to the livestock farming industry annually.
Several factors, including
nutritional management,
environmental conditions,
diseases, and genetic factors,
play a role in this problem.
In recent decades, traditional genetic evaluation methods based on linear models have been used to investigate reproductive traits. However, the complexity of the genetic mechanisms affecting pregnancy failure and the interaction of environmental factors have created limitations in the prediction accuracy of these models.
Today, significant advances in the fields of artificial intelligence and machine learning have provided unprecedented opportunities for analyzing complex and large data. These technologies are able to identify patterns and relationships hidden in data using advanced algorithms and provide more accurate predictions to improve genetic selection processes and livestock health management.
This research seeks to use the capabilities of artificial intelligence and machine learning to analyze complex data related to Holstein dairy cows. The main goal of this research is to develop more accurate predictive models to identify animals with desirable traits, improve herd health management, reduce pregnancy failure rates, and ultimately increase productivity and profitability in the dairy cattle industry.
In this regard, the present study investigates new machine learning methods to analyze data related to factors affecting pregnancy failure, identify effective patterns in genetic selection, and provide solutions for livestock health management. This research not only contributes to the development of knowledge in the field of animal husbandry, but can also be used as a basis for creating intelligent and data-driven systems in the dairy cattle industry.
It is recalled that Sepahan Knowledge-Based Managers and Analysts Company, with more than 3,000 customers in Iran and 8 other countries, supports all theses, research and academic theses with the approach of using animal husbandry data, and in this regard, you can contact the head office of this company.
* Pregnancy failure refers to cases where, after successful insemination, the embryo is unable to survive at various stages of development.
