A new history matching sensitivity analysis framework with random forests and Plackett-Burman design

• Main Authors: Aulia, A., Jeong, D., Mohd Saaid, I., Shuker, M.T., El-Khatib, N.A.
• Format: Article
• Published: Society of Petroleum Engineers 2017
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041079102&partnerID=40&md5=202496cadc69bf8359ba3fc0db6f4322; http://eprints.utp.edu.my/20297/
• Institution: Universiti Teknologi Petronas

To improve the current industry standard one-parameter-at-a-time sensitivity analysis method, we propose a new sensitivity analysis framework that utilizes Plackett-Burman design and Random Forests (a wellknown data mining method). The new framework significantly reduces the number of required simul...