skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements

Journal Article · · Journal of Hydrology
 [1];  [1];  [1];  [1]
  1. University of Texas, Austin, TX (United States)
+ Show Author Affiliations

Carbon capture and storage (CCS) has been extensively investigated as a potential engineering measure to reduce anthropogenic carbon emission to the atmosphere. Real-time monitoring of the safety and integrity of carbon storage reservoirs is a critical aspect of any commercial-scale CCS deployment. Pressure-based sensing is cost effective, suitable for real-time monitoring, and scalable to large monitoring networks. However, questions remain on how to best harness intelligent information from the high-frequency pressure monitoring sensors to support real-time decisions. Here this work presents a deep-learning-based framework for analyzing and detecting anomalies in pressure data streams by using a convolutional long short-term memory (ConvLSTM) neural network model, which allows for the fusion of both static and dynamic reservoir data. In ConvLSTM, the convolutional neural network (CNN) is used for spatial pattern mining and the LSTM is used for temporal pattern recognition. The performance of the ConvLSTM model for real-time anomaly detection is demonstrated using a set of pressure monitoring data collected from Cranfield, Mississippi, an active enhanced-oil-recovery field. The anomaly detection model is trained using bottom-hole pressure data acquired from the base experiment (without leak event) and then tested on pressure data collected during a series of controlled CO2 release experiments (with artificially created leak events). Results show that the ConvLSTM neural network model successfully detected anomalies in the pressure time series obtained from the controlled release experiments. Inclusion of static information into the model further improves the robustness of ConvLSTM.

Research Organization:
Univ. of Texas, Austin, TX (United States)
Sponsoring Organization:
USDOE Office of Fossil Energy (FE)
Grant/Contract Number:
FE0026515
OSTI ID:
1614299
Alternate ID(s):
OSTI ID: 1547541
Journal Information:
Journal of Hydrology, Vol. 573, Issue C; ISSN 0022-1694
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 36 works
Citation information provided by
Web of Science

References (46)

Detection of CO 2 leakage from a simulated sub-seabed storage site using three different types of p CO 2 sensors journal July 2015
Sequestration of CO2 in geological media: criteria and approach for site selection in response to climate change journal June 2000
Causes and financial consequences of geologic CO2 storage reservoir leakage and interference with other subsurface resources journal January 2014
Recurrent Neural Networks for Multivariate Time Series with Missing Values journal April 2018
Geologic CO2 sequestration monitoring design: A machine learning and uncertainty quantification based approach journal September 2018
Wellbore integrity and corrosion of carbon steel in CO2 geologic storage environments: A literature review journal June 2013
Modeling and simulation of carbon sequestration at Cranfield incorporating new physical models journal October 2013
Improving monitoring protocols for CO2 geological storage with technical advances in CO2 attribution monitoring journal October 2015
An assessment of near surface CO2 leakage detection techniques under Australian conditions journal January 2014
Carbon Capture and Storage: How Green Can Black Be? journal September 2009
Long Short-Term Memory journal November 1997
Static and dynamic reservoir modeling for geological CO2 sequestration at Cranfield, Mississippi, U.S.A. journal October 2013
Monitoring a large-volume injection at Cranfield, Mississippi—Project design and recommendations journal October 2013
The state of the art in monitoring and verification—Ten years on journal September 2015
A learning-based data-driven forecast approach for predicting future reservoir performance journal August 2018
3D Convolutional Neural Networks for Human Action Recognition journal January 2013
Early detection of brine and CO2 leakage through abandoned wells using pressure and surface-deformation monitoring data: Concept and demonstration journal December 2013
Rapid detection and characterization of surface CO2 leakage through the real-time measurement of δ13δ13 C signatures in CO2 flux from the ground journal September 2010
Probabilistic Analysis of Fracture Reactivation Associated with Deep Underground CO2 Injection journal October 2012
Global Carbon Budget 2015 journal January 2015
An improved strategy to detect CO 2 leakage for verification of geologic carbon sequestration: IMPROVED STRATEGY TO DETECT CO 2 journal October 2005
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF conference January 2016
Utilization of multiobjective optimization for pulse testing dataset from a CO2-EOR/sequestration field journal November 2018
Analytical solutions for leakage rates through abandoned wells: ANALYTICAL SOLUTIONS FOR LEAKAGE RATES journal April 2004
Direct forecasting of subsurface flow response from non-linear dynamic data by linear least-squares in canonical functional principal component space journal March 2015
Mastering the game of Go with deep neural networks and tree search journal January 2016
Mastering the game of Go without human knowledge journal October 2017
Simulating the Cranfield geological carbon sequestration project with high-resolution static models and an accurate equation of state journal November 2016
Inversion of pressure anomaly data for detecting leakage at geologic carbon sequestration sites journal August 2012
Assessing leakage detectability at geologic CO2 sequestration sites using the probabilistic collocation method journal June 2013
A harmonic pulse testing method for leakage detection in deep subsurface storage formations: HARMONIC PULSE TESTING FOR LEAKAGE DETECTION journal June 2015
Using pulse testing for leakage detection in carbon storage reservoirs: A field demonstration journal March 2016
A laboratory validation study of the time-lapse oscillatory pumping test for leakage detection in geological repositories journal May 2017
Metamodeling-based approach for risk assessment and cost estimation: Application to geological carbon sequestration planning journal April 2018
Building complex event processing capability for intelligent environmental monitoring journal June 2019
Geologic carbon storage is unlikely to trigger large earthquakes and reactivate faults through which CO 2 could leak journal April 2015
Development of a Hybrid Process and System Model for the Assessment of Wellbore Leakage at a Geologic CO 2 Sequestration Site journal October 2008
An Analytical Model for Assessing Stability of Pre-Existing Faults in Caprock Caused by Fluid Injection and Extraction in a Reservoir journal February 2016
Evaluation of the Potential for Gas and CO2 Leakage Along Wellbores journal March 2009
Geochemical sensitivity to CO 2 leakage: detection in potable aquifers at carbon sequestration sites : Modeling and Analysis: Geochemical sensitivity to CO journal January 2014
Toward an adaptive monitoring design for leakage risk – Closing the loop of monitoring and modeling journal September 2018
Analytical model of leakage through fault to overlying formations: ANALYTICAL MODEL OF FAULT LEAKAGE journal November 2012
Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction journal November 2016
Geostatistical 3D geological model construction to estimate the capacity of commercial scale injection and storage of CO2 in Jacksonburg-Stringtown oil field, West Virginia, USA journal January 2019
Dew point pressure prediction based on mixed-kernels-function support vector machine in gas-condensate reservoir journal November 2018
Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM journal January 2017

Similar Records

Integrate Light-Weight Deep Learning Tools with Internet of Things
Technical Report · Mon Sep 30 00:00:00 EDT 2019 · OSTI ID:1614299
A data-driven CO2 leakage detection using seismic data and spatial–temporal densely connected convolutional neural networks
Journal Article · Sat Aug 24 00:00:00 EDT 2019 · International Journal of Greenhouse Gas Control · OSTI ID:1614299
+4 more
Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning
Conference · Wed Jan 01 00:00:00 EST 2020 · OSTI ID:1614299

Related Subjects

58 GEOSCIENCES
42 ENGINEERING
13 HYDRO ENERGY
anomaly detection
convolutional long short-term memory neural network
deep learning
pressure tests