Webinar cycle in Hydrogeology and Geochemistry
HYDROGEOLOGY GROUP (Associated Unit CSIC-UPC, Barcelona)
Date: Thursday, 5th May 2022
Starting time: 15:15 pm (Central European Time)
Duration: 1h
Guest Speaker: Linus Walter, PhD student
Title: Introducing Physics Informed Neural Networks in Subsurface Flow
live in: https://meet.google.com/snb-qdkn-eex (free of charge)
Abstract:
Geoenergies such as underground gas storage and energy storage,geothermal energy and geologic carbon storage are key technologies on the way to the foreseeable energy transition. The reservoir characterization in these projects remains challenging since predictive modeling approaches face limitations in identifying the spatial distribution of distinct lithologies and their hydro-mechanical properties from downwell testing procedures. Pumping tests are usually carried out to infer permeability, but offer only few observation points in space and require large extrapolation through inversion. The application of Physics Informed Neural Networks (PINN) offers a promising solution which can seamlessly incorporate field data, while enforcing the accordance with physical laws in the domain of study. We implement this concept via two distinct loss terms for observational data and for a mass balance equation in the loss function of an Artificial Neural Network (ANN).
Preliminary results suggest that our PINN model will be able to forecast the spatiotemporal fluid pressure distribution in a 1D domain. In this way, we give a first impression of the opportunities that PINN applications offer in the field of reservoir modeling.