Geological Knowledge Discovery using Machine Augmented Intelligence

With the increasing use of artificial intelligence and machine learning in our daily lives such as for information search, online shopping, and virtual assistant AIs, the geoscience domain has also been active in the uptake of machine learning and AI to assist in interpreting geology from data.

This talk presents innovative machine-assisted technologies that improve the efficiency and the robustness of geological interpretation of different types of geodata used in the resource industry.

A number of applications of machine learning were developed in collaboration with the mining industry for the analysis and integration of multi-modal drill hole data. These applications integrate the algorithms and workflows to assist human decisions. The approach is to provide end users the control of the algorithmic process as much as possible; and to enable a seamless integration of algorithms in the interpreter’s workflow using interactive visualisation.

This talk also presents ongoing AI research that extracts geological insights from documents using machine reading of text. It applies advanced text mining methods and constructs a graph-based knowledge base called a knowledge graph to store and access geological information. Case studies on different mineral deposits demonstrate the effectiveness of the methods for rapidly and robustly transforming text data into structured information that faithfully represents the contents of the source reports.