The Intelligent Prospector v1.0: geoscientific model development and prediction by sequential data acquisition planning with application to mineral exploration

Geoscientific models are based on geoscientific data; hence, building better models, in the sense of attaining better predictions, often means acquiring additional data. In decision theory, questions of what additional data are expected to best improve predictions and decisions is within the realm of value of information and Bayesian optimal survey design. However, these approaches often evaluate the optimality of one additional data acquisition campaign at a time. In many real settings, certainly in those related to the exploration of Earth resources, a large sequence of data acquisition campaigns possibly needs to be planned. Geoscientific data acquisition can be expensive and time-consuming, requiring effective measurement campaign planning to optimally allocate resources. Each measurement in a data acquisition sequence has the potential to inform where best to take the following measurements; however, directly optimizing a closed-loop measurement sequence requires solving an intractable combinatoric search problem. In this work, we formulate the sequential geoscientific data acquisition problem as a partially observable Markov decision process (POMDP). We then present methodologies to solve the sequential problem using Monte Carlo planning methods. We demonstrate the effectiveness of the proposed approach on a simple 2D synthetic exploration problem. Tests show that the proposed sequential approach is significantly more effective at reducing uncertainty than conventional methods. Although our approach is discussed in the context of mineral resource exploration, it likely has bearing on other types of geoscientific model questions.

Automated summary

Geoscientific models rely on geoscientific data, so improving models often requires acquiring additional data. The value of information and Bayesian optimal survey design can guide the acquisition of additional data, but they usually focus on evaluating one campaign at a time. In real settings, especially in Earth resource exploration, planning a large sequence of data acquisition campaigns is necessary. This study formulates the problem as a partially observable Markov decision process and presents methodologies to solve it using Monte Carlo planning methods, demonstrating its effectiveness in reducing uncertainty.