|
Description of Individual Course UnitsCourse Unit Code | Course Unit Title | Type of Course Unit | Year of Study | Semester | Number of ECTS Credits | TAE-24-100 | | Elective | 1 | 2 | 6 |
| Level of Course Unit | Second Cycle | Objectives of the Course | The aim of the "Machine Learning and Explainable AI Applications in Agricultural Economics" course is to equip participants with a comprehensive understanding of cutting-edge machine learning techniques and explainable artificial intelligence (XAI) applications specifically tailored for the agricultural domain. Through a blend of theoretical knowledge and hands-on practical exercises, this course aims to empower participants to harness the potential of advanced AI technologies to address challenges and optimize processes in agriculture. | Name of Lecturer(s) | Öğr. Gör. Dr. Hakan DUMAN | Learning Outcomes | 1 | Understanding of Machine Learning Concepts:
Outcome: Develop a comprehensive understanding of fundamental machine learning concepts, algorithms, and techniques.
Proficiency: Participants will be proficient in explaining and applying core machine learning principles. | 2 | Agricultural Data Processing Proficiency:
Outcome: Acquire skills in collecting, preprocessing, and managing diverse agricultural datasets, including remote sensing and climate data.
Proficiency: Participants will be proficient in handling and processing various types of agricultural data for machine learning applications. | 3 | Model Development and Optimization Competence:
Outcome: Develop the ability to build, train, and optimize machine learning models tailored for agricultural applications.
Proficiency: Participants will be proficient in selecting, developing, and fine-tuning machine learning models for specific agricultural tasks. | 4 | Explainable AI Techniques Mastery:
Outcome: Master techniques in explainable artificial intelligence (XAI) to enhance the interpretability of machine learning models in agriculture.
Proficiency: Participants will be proficient in implementing and communicating the results of XAI methods applied to agricultural data. | 5 | Practical Application Skills:
Outcome: Apply theoretical knowledge through hands-on practical exercises and real-world case studies in the agricultural context.
Proficiency: Participants will be proficient in applying machine learning techniques to solve practical problems in agriculture. | 6 | Ethical Considerations Awareness:
Outcome: Develop awareness of ethical considerations related to AI in agriculture, including privacy, bias, and societal impacts.
Proficiency: Participants will be proficient in identifying and addressing ethical challenges in the application of machine learning in agriculture. | 7 | Integration with Precision Agriculture:
Outcome: Understand how to integrate machine learning and AI technologies with precision agriculture practices.
Proficiency: Participants will be proficient in leveraging AI to enhance precision agriculture, optimizing resource utilization and decision-making. | 8 | Communication and Collaboration Skills:
Outcome: Foster effective communication and collaboration skills for interdisciplinary teamwork in agricultural AI projects.
Proficiency: Participants will be proficient in conveying technical concepts to non-technical stakeholders and collaborating with experts from diverse fields. | 9 | Project Implementation Competence:
Outcome: Successfully implement machine learning solutions in agricultural projects, demonstrating the ability to address specific challenges.
Proficiency: Participants will be proficient in independently planning, executing, and evaluating machine learning projects in the agricultural domain. | 10 | Continuous Learning Orientation:
Outcome: Develop a mindset for continuous learning in the rapidly evolving field of machine learning and AI applications in agriculture.
Proficiency: Participants will be proficient in staying updated on emerging technologies and adapting their skills to industry advancements. |
| Mode of Delivery | Daytime Class | Prerequisites and co-requisities | | Recommended Optional Programme Components | | Course Contents | Understanding of Machine Learning Concepts:
Outcome: Develop a comprehensive understanding of fundamental machine learning concepts, algorithms, and techniques.
Proficiency: Participants will be proficient in explaining and applying core machine learning principles.
Agricultural Data Processing Proficiency:
Outcome: Acquire skills in collecting, preprocessing, and managing diverse agricultural datasets, including remote sensing and climate data.
Proficiency: Participants will be proficient in handling and processing various types of agricultural data for machine learning applications.
Model Development and Optimization Competence:
Outcome: Develop the ability to build, train, and optimize machine learning models tailored for agricultural applications.
Proficiency: Participants will be proficient in selecting, developing, and fine-tuning machine learning models for specific agricultural tasks.
Explainable AI Techniques Mastery:
Outcome: Master techniques in explainable artificial intelligence (XAI) to enhance the interpretability of machine learning models in agriculture.
Proficiency: Participants will be proficient in implementing and communicating the results of XAI methods applied to agricultural data.
Practical Application Skills:
Outcome: Apply theoretical knowledge through hands-on practical exercises and real-world case studies in the agricultural context.
Proficiency: Participants will be proficient in applying machine learning techniques to solve practical problems in agriculture.
Ethical Considerations Awareness:
Outcome: Develop awareness of ethical considerations related to AI in agriculture, including privacy, bias, and societal impacts.
Proficiency: Participants will be proficient in identifying and addressing ethical challenges in the application of machine learning in agriculture.
Integration with Precision Agriculture:
Outcome: Understand how to integrate machine learning and AI technologies with precision agriculture practices.
Proficiency: Participants will be proficient in leveraging AI to enhance precision agriculture, optimizing resource utilization and decision-making.
Communication and Collaboration Skills:
Outcome: Foster effective communication and collaboration skills for interdisciplinary teamwork in agricultural AI projects.
Proficiency: Participants will be proficient in conveying technical concepts to non-technical stakeholders and collaborating with experts from diverse fields.
Project Implementation Competence:
Outcome: Successfully implement machine learning solutions in agricultural projects, demonstrating the ability to address specific challenges.
Proficiency: Participants will be proficient in independently planning, executing, and evaluating machine learning projects in the agricultural domain.
Continuous Learning Orientation:
Outcome: Develop a mindset for continuous learning in the rapidly evolving field of machine learning and AI applications in agriculture.
Proficiency: Participants will be proficient in staying updated on emerging technologies and adapting their skills to industry advancements. | Weekly Detailed Course Contents | |
1 | Overview of the course structure, objectives, and expectations.
Introduction to machine learning fundamentals and its relevance to agriculture.
Discussion on the historical context and evolution of machine learning. | | | 2 | In-depth exploration of supervised and unsupervised learning concepts.
Practical examples of machine learning applications in diverse industries.
Assignment: Research and present a case study on a machine learning application in agriculture | | | 3 | Understanding the basics of agriculture, farming practices, and challenges.
Introduction to precision agriculture and its impact on sustainable farming. | | | 4 | Essential data science concepts, data collection, and preprocessing.
Overview of statistical concepts relevant to machine learning. | Group activity: Analyze and clean a sample agricultural dataset. | | 5 | Basics of programming languages, with a focus on Python.
Introduction to data manipulation and analysis libraries (e.g., Pandas, NumPy). | Hands-on session: Python programming exercises related to agriculture. | | 6 | Overview of machine learning tools and platforms used in agriculture.
Practical workshop: Setting up and using machine learning environments. | Assignment: Implement a basic machine learning model using a provided dataset. | | 7 | | Practical session: Hands-on implementation of deep learning algorithms for agricultural tasks. | | 8 | Integration of remote sensing data and IoT devices in agriculture.
Use of sensor data for machine learning applications. | Case studies: Analysing successful examples of remote sensing and IoT integration in agriculture. | | 9 | Field trip or virtual tour to a farm implementing advanced sensing technologies. | Group discussion: Reflection on the practical applications observed during the trip. | | 10 | Explainable AI (XAI) techniques and their importance in agriculture.
Ethical considerations in AI applications, with a focus on agriculture. | Practical session: Implementing interpretable machine learning models. | | 11 | Explainable AI (XAI) techniques and their importance in agriculture.
Ethical considerations in AI applications, with a focus on agriculture. | Practical session: Implementing interpretable machine learning models. | | 12 | | Student presentations: Share findings from individual or group projects.
Project submission.
Discussion on the ethical challenges and responsibilities in deploying AI in agriculture. | | 13 | | In-depth analysis of industry case studies in agricultural AI.
Group project review: Presentation and peer feedback on the machine learning solutions proposed. | | 14 | Course summary, review, and reflections.
Future trends in machine learning and AI applications in agriculture. | | |
| Recommended or Required Reading | Course Basic Contexts:
Machine Learning Fundamentals:
Book: "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" - Aurélien Géron
Content: Focuses on core machine learning concepts and algorithms.
Agricultural Background:
Book: "Precision Agriculture Technology for Crop Farming" - Qin Zhang
Content: Provides an overview of fundamental principles in agriculture, modern farming technologies, and the significance of precision agriculture.
Data Science Basics:
Book: "Python for Data Analysis" - Wes McKinney
Content: Develops foundational skills in data collection, preprocessing, and analysis using Python.
Programming Fundamentals:
Book: "Python Crash Course" - Eric Matthes
Content: Teaches basic concepts of the Python programming language, especially foundational skills required for machine learning.
Ethical Considerations:
Book: "Ethics of Artificial Intelligence and Robotics" - Vincent C. Müller
Content: Explores ethical considerations in artificial intelligence and machine learning.
Course Auxiliary Contexts:
Advanced Machine Learning Techniques:
Book: "Deep Learning" - Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Content: A reference source focusing on deep learning and advanced machine learning techniques.
Remote Sensing and IoT Integration:
Book: "Remote Sensing and GIS for Ecologists" - Paul A. Racey and Andrew N. Green
Content: Focuses on the integration of remote sensing data and Internet of Things (IoT) devices in agriculture.
Cloud Computing for Agriculture:
Book: "Cloud Computing for Agriculture" - Edited by Hemanth Kumar Yamjala
Content: Explores the use of cloud computing platforms for handling large agricultural datasets.
Geospatial Analysis:
Book: "GIS and Remote Sensing Techniques in Land- and Water-management" - Edited by Martin Y. Appiah et al.
Content: A resource on how geographic information systems (GIS) and remote sensing techniques can be applied in agricultural management.
Industry Case Studies:
Book: "Data Science for Business" - Foster Provost and Tom Fawcett
Content: Analyzes industry case studies, focusing on data science applications in the business world.
Regulatory Frameworks:
Book: "Artificial Intelligence: A Guide for Thinking Humans" - Melanie Mitchell
Content: Addresses regulatory frameworks and ethical issues in artificial intelligence and machine learning.
Interdisciplinary Collaboration:
Book: "Collaborative Intelligence: Thinking with People Who Think Differently" - Dawna Markova and Angie McArthur
Content: Emphasizes the importance of interdisciplinary collaboration.
Communication and Reporting:
Book: "Data Points: Visualization That Means Something" - Nathan Yau
Content: Focuses on effective communication and visualization in data science.
Continuous Learning Resources:
Source: Online platforms (Coursera, edX, Udacity) and article archives.
Content: Various resources for participants to stay updated and continue learning beyond the course.
Hands-on Projects:
Source: Real datasets and application examples from platforms like Kaggle and GitHub.
Content: Resources containing real-world projects for participants to practice and apply learned concepts. | Planned Learning Activities and Teaching Methods | | Assessment Methods and Criteria | |
Report Preparation | 3 | 75 | Report Presentation | 1 | 25 | SUM | 100 | |
Report Preparation | 1 | 100 | SUM | 100 | Term (or Year) Learning Activities | 40 | End Of Term (or Year) Learning Activities | 60 | SUM | 100 |
| Language of Instruction | Turkish | Work Placement(s) | |
| Workload Calculation | |
Report Preparation | 4 | 25 | 100 | Report Presentation | 1 | 1 | 1 | Criticising Paper | 3 | 10 | 30 | Self Study | 14 | 3 | 42 | |
Contribution of Learning Outcomes to Programme Outcomes | LO1 | LO2 | LO3 | LO4 | LO5 | LO6 | LO7 | LO8 | LO9 | LO10 |
| * Contribution Level : 1 Very low 2 Low 3 Medium 4 High 5 Very High |
|
|
Iğdır University, Iğdır / TURKEY • Tel (pbx): +90 476
226 13 14 • e-mail: info@igdir.edu.tr
|
|
|