MATLAB is selected as the primary platform for computer vision and machine learning because it provides an integrated and relatively accessible environment for students with different levels of programming experience. Its built-in functions, interactive applications, visualization capabilities, and specialized toolboxes allow students to experiment with image-processing and machine-learning methods for easy adoption to various other disciplines. The learning outcomes are given below:
### Learning Outcomes

Upon successful completion of this course, students will be able to:

- Explain fundamental concepts of computer vision, artificial intelligence (AI), and data analytics and their applications in agriculture and natural resources.
- Use MATLAB to import, visualize, process, and analyze digital images for research applications.
- Apply fundamental image-processing techniques in MATLAB, including image enhancement, color-space analysis, thresholding, morphological operations, segmentation, and feature extraction.
- Analyze images acquired using different sensing modalities, including RGB, hyperspectral, fluorescence, and infrared imaging.
- Apply traditional and neural-network-based image segmentation techniques to extract meaningful information from agricultural and biological images.
- Use computer vision techniques to quantify plant traits and understand their applications in image-based plant phenotyping, precision agriculture, and plant breeding and selection.
- Understand the fundamentals of 3D reconstruction from multi-view images and its potential applications in digital agriculture.
- Apply introductory supervised and unsupervised machine learning techniques to agricultural and natural-resource datasets.
- Analyze and visualize research data to identify patterns, relationships, and trends that support data-driven decision-making.
- Apply introductory time-series analysis and prediction methods to investigate temporal changes in biological and agricultural systems.
- Gain introductory experience with Python and Google Colab and understand how computational concepts learned in MATLAB can be transferred to other programming environments.
- Explain fundamental concepts of generative AI, Large Language Models (LLMs), prompt engineering, Retrieval-Augmented Generation (RAG), and agentic AI, and identify their potential applications in research.
- Use generative AI tools responsibly for research-related tasks such as summarization, information extraction, data interpretation, and scientific communication.
- Develop a basic customized AI chatbot or AI-assisted application for a selected research need.
- Use data visualization and statistical analysis tools to explore, interpret, and communicate research findings.
- Apply computer vision, AI, and data analytics techniques to a mini-project addressing a research problem in agriculture or natural resources.
- Communicate computational methods and research findings effectively through scientific writing, visualization, and presentation.

This beginner-friendly activity is designed for students from diverse academic disciplines and backgrounds who are interested in applying computer vision, artificial intelligence (AI), and data analytics to research problems in agriculture and natural resources. No prior expertise in computer vision, AI, or advanced programming is required. The activity introduces computational concepts gradually through instructor-led demonstrations, guided exercises, and hands-on applications using real-world agricultural datasets.

The course has been adopted as one of the required advanced courses for the Environmental Science minor program at the University of Nebraska–Lincoln. The course is taught even years during the fall semesters.

The more information about the course can be found in:

https://newsroom.unl.edu/announce/snr/19911/106389?fbclid=IwY2xjawQOpshleHRuA2FlbQIxMQBzcnRjBmFwcF9pZBAyMjIwMzkxNzg4MjAwODkyAAEel1_ErwbAkdbp7OEFjM0xKAVP7a1qYucxAuoImeFx7aD52If6jyOPK4MXtA8_aem_TSGlu_m2dSsBRdL20Clu8w