Preprints
https://doi.org/10.5194/gmd-2022-166
https://doi.org/10.5194/gmd-2022-166
Submitted as: model description paper
08 Aug 2022
Submitted as: model description paper | 08 Aug 2022
Status: this preprint is currently under review for the journal GMD.

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

John Mern1 and Jef Caers2 John Mern and Jef Caers
  • 1Kobold Metals, USA
  • 2Stanford University, Department of Geological Sciences, USA

Abstract. 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 is expected to best improve predictions/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, possibly a large sequence of data acquisition campaigns need 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.

John Mern and Jef Caers

Status: open (until 13 Oct 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

John Mern and Jef Caers

John Mern and Jef Caers

Viewed

Total article views: 325 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
274 47 4 325 2 1
  • HTML: 274
  • PDF: 47
  • XML: 4
  • Total: 325
  • BibTeX: 2
  • EndNote: 1
Views and downloads (calculated since 08 Aug 2022)
Cumulative views and downloads (calculated since 08 Aug 2022)

Viewed (geographical distribution)

Total article views: 257 (including HTML, PDF, and XML) Thereof 257 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Sep 2022
Download
Short summary
In this work, we formulate sequential geoscientific data acquisition problem as problem that is similar to playing chess against nature, except the pieces are not fully observed. Solutions to these problems are given in AI, and rarely used in geoscientific data planning. We illustrate our approach to a simple 2D problem of mineral exploration.