Systematic Machine leARning Training for PORous mEdia characterizationS (SMART PORES)

• Project/Area Number: 21K13999
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 17030:Human geosciences-related
• Research Institution: Tokyo Institute of Technology
• Principal Investigator: パトモノアジ アニンディティヨ 東京工業大学, 工学院, JSPS特別研究員 (20899265)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Project Status: Granted (Fiscal Year 2021)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2023: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2021: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
• Keywords: Porous media / Machine Learning / Permeability

Outline of Research at the Start

Nations around the globe had agreed to cut CO2 emission, but our society will still rely on hydrocarbon energy in the next decades. Coupling efficient petroleum production and CCS will provide a suitable alternative. Advancement in micro-tomography marks the rise of digital rock physics (DRP). In this decade, the implementations of machine learning (ML) to various industries have opened unprecedented possibilities. Here, I propose the implementation of ML with the combination between void structure images and statistics of pore-throat network by using deep learning (DL).