
Spacial Data Analytics and Machine Learning
Title: Interpretation of geoscience data using spatial data analytics and machine learning

Presenter Bio : Dr. Glen Nwaila
Dr. Glen Nwaila is a Director and Adjunct Professor at the Wits Mining Institute (WMI), University of the Witwatersrand. Glen has over 13 years of practical experience in mining and exploration geology, teaching, consulting and R&D. Glen’s current work focuses on increasing the integration of multivariate geoscience data with machine learning for uncertainty reduction and optimal decision-making.
About this event
This one-day workshop introduces the geoscience students and practising professionals to the machine-aided interpretation of geological data using spatial data analytics and machine learning.
You will learn to develop data-driven machine workflows for lithofacies prediction and automated 3D block modelling using drill core/well logs, sourcing of satellite remote sensing data and extracting useful information for automated mineralisation anomaly detection, and principal component analysis for dimension reduction. As you build prediction and classification models, you will learn how to train algorithms using training data so you can predict the outcome for future datasets.
What will I learn
- Effectively prepare data for Data Analytics and Machine Learning applications in order to ensure that conclusions drawn are trustworthy and reliable
- Gain insights from data using a lean workflow that incorporates outlier detection, data debiasing and imputation, feature engineering, and spatiotemporal modelling
- Understand the assumptions and limits of data precision, scale and coverage
- Create classification, prediction and spatial uncertainty models
By the end of the workshop, you will have a firm understanding of:
- Classification of lithofacies from drill core data
- Automated anomaly detection
- Dimension reduction and visualisation of gridded data
Working Environment
Python Integrated Development Environment (IDE) and Code Editors such as Jupyter Notebook, Spyder, Visual Studio, Visual Studio Code, PyCharm
The course will be delivered by Prof. Glen Nwaila from the University of the Witwatersrand (LinkedIn: Glen Nwaila), hosted by the South African Geophysical Association

