| Affiliations: | STEM Research Leadership |
| Project Leader: | Karun Kaniyamattam, Ph.D.
karun.kaniyamattam@ag.tamu.edu Animal Science |
|
Meeting Times:
|
TBA |
|
Team Size:
|
6
|
| Open Spots: | 0 |
|
Special Opportunities:
|
This project offers students valuable hands-on interdisciplinary research experiences. Participants will gain advanced skills in agent-based modeling (ABM), and data analysis, utilizing essential tools such as NetLogo and Python. Students will also engage with cutting-edge agricultural technologies, including machine learning, enhancing their technical proficiency. By contributing to sustainability research, students will tackle real-world challenges, improving their critical thinking and problem-solving abilities. They will enhance their presentation and communication skills through stakeholder engagement and have opportunities for publication or conference presentations. The project fosters teamwork skills, allowing students to explore potential career paths in academia, industry, or policy-making related to sustainable agriculture.
|
|
Team Needs:
|
This opportunity is available to undergraduates studying Data Science, Information Systems, Animal Science, Veterinary Science, and related fields. Ideal mentees should be enthusiastic and interested in livestock systems, machine learning, agent-based modeling, artificial intelligence (AI), and Python programming. |
|
Description:
|
This study aims to assess the environmental impacts of various swine production practices while evaluating different economic strategies through a comprehensive hybrid intelligent model that integrates machine learning (ML) and agent-based modeling (ABM). Building upon previously developed ABMs that simulate the nutrient requirements of growing-finishing pigs, this research incorporates environmental metrics such as greenhouse gas emissions, nutrient excretion, and resource utilization. The model will simulate complex interactions among pig agents, environmental factors, and economic variables, allowing for diverse farming practices and management strategies. By analyzing various scenarios, including conventional and sustainable farming approaches, we will evaluate the resultant effects on production efficiency and environmental outcomes. ML contributes to optimization by predicting outcomes and recommending best practices based on various farming scenarios, evaluating impacts on sustainability metrics such as nutrient efficiency and greenhouse gas emissions. Key findings will reveal critical trade-offs between economic viability and environmental performance, highlighting the importance of sustainable practices in reducing ecological footprints while maintaining profitability. The results will provide actionable insights for producers and policymakers, suggesting pathways to enhance sustainability in the pork sector. Ultimately, this research contributes to the development of informed strategies that align agricultural productivity with environmental stewardship, supporting the long-term sustainability of swine production systems. |