Course introduction:

The course 《Big Data and Artificial Intelligence for Mineral Exploration》closely follows international academic frontiers such as big data in geosciences and artificial intelligence. It primarily teaches the basic concepts of artificial intelligence, its development history and research content, and the current status and research hotspots of big data in geosciences. It also covers the fundamental principles of deep learning algorithms and computer programming languages. By integrating the study of real-world cases and basic training in practical exercises, the course enables students to grasp essential knowledge of artificial intelligence in fields such as resource exploration and oil and gas field development. Students will develop the capability to conduct mineral resource potential assessments based on deep learning techniques.

Teaching Objectives

This course is designed to meet the national strategic development needs of the next - generation artificial intelligence and resources and energy. It aims to enable students to master the basic theories, academic frontiers, fundamental methods, technologies and applications of artificial intelligence. Students will be able to design solutions for complex engineering problems related to geosciences big data, and design and develop potential evaluation software systems for solid minerals and oil - gas resources, thus laying a good foundation for subsequent professional courses and graduation internships. After completing this course, students will be able to do research work of prediction and potential evaluation in the field of resources and energy in the big - data era.

Course Objective 1: Master the basic concepts and fundamental theories of big data and artificial intelligence.

Course Objective 2: Design artificial-intelligence-based methods for mineral resource potential evaluation.

Course Objective 3: Design artificial-intelligence-based application models for oil and gas field exploration and development.

Teaching Arrangement:

Chapter 1: Geosciences Big Data

1.1 Introduction to Geosciences Big Data

1.2 Research Status of Geoscience Big Data

Lecturer: Prof. Yihui Xiong

Chapter 2: Artificial Intelligence and Mineral Prediction

2.1 Foundation of Artificial Intelligence

2.2 Research Status of Artificial Intelligence in Mineral Prediction

Lecturer: Assoc Prof. Ziye Wang

Chapter 3: Artificial Intelligence and Exploration Geochemistry

3.1 Overview and Progress of Exploration Geochemistry

3.2 Data Processing Methods and Applications in Exploration Geochemistry

Lecturer: Assoc Prof. Yue Liu

Chapter 4: Intelligent Three-Dimensional Geological Representation and Modeling

4.1 Research Progress of Three-Dimensional Geological Modeling

4.2 Applications of Intelligent Three-Dimensional Geological Modeling

Lecturer: Prof. Qiyu Chen

Chapter 5: Artificial Intelligence and Smart Oilfield Development

5.1 Research Frontiers of Smart Oilfield Development

5.2 Applications of Smart Oilfield Development

Lecturer: Prof. Zhi Zhong

Chapter 6: Artificial Intelligence and Smart Oil and Gas Exploration

6.1 Research Frontiers of Smart Oil and Gas Exploration

6.2 Applications of Smart Oil and Gas Exploration

Lecturer: Assoc Prof. Hao Wu

Chapter 7: Geosciences Knowledge Base and Intelligent Applications

7.1 Geoscience Knowledge Representation

7.2 Intelligent Applications of Geoscience Knowledge Base

Lecturer: Assoc Prof. Chengbin Wang

Chapter 8: Flipped Classroom

8.1 Course Design Presentations

Practical work: Mineral Resource Potential Evaluation Based on Deep Learning

Practice1: Software Installation and Environment Configuration

Practice 2: Deep Learning Model Building

Practice 3: Parameter Optimization and Sample Preparation

Practice 4: Mineral Resource Potential Evaluation Based on Convolutional Neural Networks

References:

1. Viktor Mayer-Schönberger and Kenneth Cukier: Big Data: A Revolution That Will Transform How We Live, Work, and Think, Zhejiang People's Publishing House. 

2. Renguang Zuo, Yihui Xiong, and Ziye Wang, 2022: Mineral Prospectivity Mapping Based on Deep Learning: Principles and Practice, Science Press.

3. Renguang Zuo, Ziye Wang, and Yihui Xiong, 2023: Practical Guide for Intelligent Mineral Prospectivity Mapping, China University of Geosciences Press.