This repository contains data and information regarding the paper: Stefano Berrone and Francesco Della Santa, “Performance Analysis of Multi-Task Deep Learning Models for Flux Regression in Discrete Fracture Networks” (to appear on the special issue “Quantitative Fractured Rock Hydrology” of Geosciences, ISSN 2076-3263).
Summary:
Analysis of underground flows in fractured media is relevant in several engineering fields, e.g., in oil and gas extraction, in geothermal energy production, or in the prevention of geological or water-pollution risk, to mention a few.
Many possible approaches exist for modeling fractured media, and among the most used is the Discrete Fracture Network (DFN) model. In this model, fractures in the rock matrix are represented as planar polygons in a three-dimensional domain that intersect each other; through the intersection segments (called “traces”), a flux exchange between fractures occurs while the 3D domain representing the surrounding rock matrix is assumed to be impermeable. On each fracture, the Darcy law is assumed to characterize the flux and head continuity and flux balance are assumed to characterize all traces.
The following links let download pandas DataFrames as pickle files, containing the data of thousands of simulations each. The columns with name starting with letter ‘K’ contain the fracture transmissivities; the columns with name starting with ‘F’ contain the fracture fluxes, computed via DFN flow simulations. For more details concerning the physic of the problem, see the reference paper.
DFN158 (158 fractures).
Data of 10000 simulations with transmissivity st.dev. parameter 0.20: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.25: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.33: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.40: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.50: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.70: link
DFN202 (202 fractures).
Data of 10000 simulations with transmissivity st.dev. parameter 0.33: link
DFN395 (395 fractures).
Data of 10000 simulations with transmissivity st.dev. parameter 0.20: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.33: link
Data of 10000 simulations with transmissivity st.dev. parameter 0.50: link