A new GAN study for fluvial facies modelling got published in Computational Geosciences as an outcome of Chao Sun’s PhD

Geological realism in Fluvial facies modelling with GAN under variable depositional conditions by Chao Sun,  Vasily Demyanov,   Daniel Arnold Computational Geosciences, 10.1007/s10596-023-10190-w This study investigates generative adversarial networks (GANs)’ capacity to model multi-facies distributions of meandering systems. Earlier works showed that GANs outperform geostatistical methods in reproducing complex geometry, like the shapes of fluvial channels. […]


Read the article

A benchmark data set for meandering reservoir facie modelling published online and now available to download.

The GAN River-I data set is designed to provide a stern test for machine learning and geostatistical tools that wish to recreate the complex geometries of realistic facies distributions in subsurface reservoirs. It provides more complex, non-stationary facies distributions than earlier open data sets,  and is generated with FLUMY process-based algorithm. It has been puiblished […]


Read the article

GeoDataScience talks at GeoNetZero CDT annual conference in Edinburgh

Final year PhD students have presented summaries of their theses at the GeoNetZero CDT annual conference: Athos Nathanail – Assisted Geological Interpretation Based on Human-like Creative Computing – Depositional Environment Interpretation from outcrop data Chao Sun – Use of Artificial Intelligence to Generate Complex Fluvial Systems Quentin Corlay – Detection of Geobodies in 3D Seismic using […]


Read the article

CCS sandpit event at TU Delft

Heriot-Watt GeoDataScience group teams with TUDelft in a CCS sandpit – Innovative solutions on subsurface utilization for energy transition, September 11-15, 2022 organised by Denis Voskov (TU Delft) and Vasily Demyanov (HWU) The event provided a unique opportunity for PhD students from the two universities to exchange their research experience in reservoir characterization and modelling. […]


Read the article

Best Remote Presentation Award at IAMG 2022 – Gleb Shishaev

Gleb Shishaev got the Best Remote Presentation Award at the International Association for Mathematical Geoscience Conference IAMG in September for his talk “Uncertainty Quantification of depositional and structural properties with Generative Deep Learning and Graph Convolutions” – a great achievement on his PhD path! Gleb could not get to Nancy to present in person as […]


Read the article

Gleb Shishaev presents an e-poster on AHM with generative DL with graph convolutions at EAGE ECMOR 2022

History Matching And Uncertainty Quantification Of Reservoir Performance With Generative Deep Learning And Graph Convolutions Shishaev G, Demyanov V, Arnold D, Vygon R Generative deep learning is becoming a widely used approach in geological modelling, especially in problems that involve optimization processes under uncertainty like history matching. The basic idea of reservoir modelling and history matching by generative […]


Read the article

GeoDataSciance group to present at IAMG 2022 in Nancy

GeoDataScience and UQ Group PhD students have been selected to give oral presentations at the International Association for Mathematical Geoscience (IAMG) 21st annual conference in Nancy. Honored to be part of a very high profile programme put together by the IAMG 2022 Scientific Committee. Thu Sep 1st Session 16 Reservoir/Petroleum Geostatistics S1601. Fast Detection of […]


Read the article

Bastian Steffens PhD thesis successfully examined and signed off for graduation

Congratulations to Bastian Steffens, who successfully passed a PhD viva examined by Prof Insa Neuweiler (external), Dr Mark Bentley (internal) in April 2022 with the thesis Integrating geological uncertainty and dynamic data into modelling procedures for fractured reservoirs . The final corrections has now been approved and signed off for graduation and the thesis available for download. […]


Read the article

2nd GeoDataScience and UQ group research dissemination on-line open day

9 May 2022: The programme for the day will offer a series of presentations across various aspects of machine learning applications to reservoir uncertainty modelling workflows: seismic interpretation, geological pattern recognition from outcrops, fluvial facies modelling with GANs, dynamic data integration into fracture reservoir modelling and multi-objective optimisation of reservoir production to tackle CO2 emission […]


Read the article