PIML

KO | EN

gitlite — search

#hacktoberfest #typescript #golang #machine-learning #deep-learning #docker #macos #nodejs #windows #awesome #kubernetes #vue #security #ios

(★ 10)

My pytorch based implementation of the paper 'Limitations of Physics Informed Machine Learning for Nonlinear Two-Phase Transport in Porous Media'

PIML 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

This repository contains parts of the code implemented for my project:
# Improving reservoir forecasting with lesser data

In this work, I studied how knowledge of reservoir physics can help improve data-based models for reservoir prediction. This concept can be generalized to other data-science and Machine Learning areas where we have access to analytical equations that can provide strong prior to the model. My research extends the work of [1]. But this repository only contains the my simple Pytorch based implementation of [1], which uses the PINN developed in [PINN](https://github.com/nanditadoloi/PINN).

### Solution to the Buckley Leverett Fluid Flow model with Convex Flux function at time t=0.75
![image](https://raw.githubusercontent.com/nanditadoloi/PIML/main/solution.png "SolutionImage")

Dependencies: `pytorch` and `numpy` packages.

[1] Fuks, Olga, and Hamdi A. Tchelepi. "Limitations of physics informed machine learning for nonlinear two-phase transport in porous media." Journal of Machine Learning for Modeling and Computing 1.1 (2020).

PIML

PIML 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

PIML

PIML 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README