Brackenridge, RachelDemyanov, VasilyVashutin , OlegNigmatullin , Ruslan2022-02-082022-02-082022-01-31Brackenridge, R, Demyanov, V, Vashutin , O & Nigmatullin , R 2022, 'Improving Subsurface Characterisation with ‘Big Data’ Mining and Machine Learning', Energies, vol. 15, no. 3, 1070. https://doi.org/10.3390/en150310701996-1073ORCID: /0000-0002-0572-314X/work/107908622https://hdl.handle.net/2164/18045Funding: This research was supported by Wood Mackenzie through funding of a Postdoctoral Research Associate position at Heriot Watt University, and through access to data from two basins. Acknowledgments: This work was supported by Wood Mackenzie through funding research collab- oration with Heriot-Watt University. All the data were anonymised and supplied by Wood Mackenzie and authors are thankful for the opportunity to publish the outcomes of this research. Authors also thank Mikhail Kanevski of University of Lausanne for the peer exchange on feature selection and the opportunities opened during his course on Machine Learning hands-on applications. Authors acknowledge the use of Orange Data Mining [27] and ML Office for SOM application [30]. We thank Susan Agar, who reviewed the paper most comprehensively and helped improve it along with two anonymous reviewers.2312582980engSDG 7 - Affordable and Clean Energy2040 Energy Tranistionreservoirsubsurface characterisationbig dataunsupervised learningsupervised learningmultivariant analysismachine learninghydrocarbon explorationQE GeologyQEJournal article10.3390/en15031070http://www.scopus.com/inward/record.url?scp=85124023265&partnerID=8YFLogxK153