Dynamical counterfactual inference under time-series model for waterflooding oilfield

The performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching. To address these challenges, causal inference is an effective methodology since it can provide a causality for formalizing...

Full description

Saved in:
Bibliographic Details
Main Authors: Guoquan Wen, Chao Min, Qingxia Zhang, Guoyong Liao
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-02-01
Series:Petroleum
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405656124000476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708945682202624
author Guoquan Wen
Chao Min
Qingxia Zhang
Guoyong Liao
author_facet Guoquan Wen
Chao Min
Qingxia Zhang
Guoyong Liao
author_sort Guoquan Wen
collection DOAJ
description The performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching. To address these challenges, causal inference is an effective methodology since it can provide a causality for formalizing causality in history, not statistical dependence. In this paper, to dynamically predict oil production from causality existed in waterflooding oilfield, a dynamical counterfactual inference framework is built to predict oil production. The proposed framework can forecast the oil production under non-observation of engineering factors, i.e., counterfactual, and provide the causal effect of engineering factors impacting on oil production. Meanwhile, combining with the practice exploitation in engineering factor impacting on production, a counterfactual experiment is designed to execute counterfactual prediction. Compared with general machine learning and statistical models, our results not only show better performance in oil production flooding but also guide the specific optimization in improving production, which holds more practical application significance.
format Article
id doaj-art-c4175b90c6e24a338b22b7e49dcfc437
institution DOAJ
issn 2405-6561
language English
publishDate 2025-02-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Petroleum
spelling doaj-art-c4175b90c6e24a338b22b7e49dcfc4372025-08-20T03:15:28ZengKeAi Communications Co., Ltd.Petroleum2405-65612025-02-0111111312410.1016/j.petlm.2024.11.001Dynamical counterfactual inference under time-series model for waterflooding oilfieldGuoquan Wen0Chao Min1Qingxia Zhang2Guoyong Liao3School of Science, Southwest Petroleum University, Chengdu, 610500, China; Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, 610500, ChinaSchool of Science, Southwest Petroleum University, Chengdu, 610500, China; Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, 610500, China; State Key Laboratory of Oil and Gas Reservoir and Exploitation, Chengdu, 610500, China; Corresponding author.School of Science, Southwest Petroleum University, Chengdu, 610500, China; Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, 610500, ChinaSchool of Science, Southwest Petroleum University, Chengdu, 610500, China; Institute for Artificial Intelligence, Southwest Petroleum University, Chengdu, 610500, ChinaThe performances of numerical simulation and machine learning in production forecasting are severely dependent on precise geological modeling and high-quality history matching. To address these challenges, causal inference is an effective methodology since it can provide a causality for formalizing causality in history, not statistical dependence. In this paper, to dynamically predict oil production from causality existed in waterflooding oilfield, a dynamical counterfactual inference framework is built to predict oil production. The proposed framework can forecast the oil production under non-observation of engineering factors, i.e., counterfactual, and provide the causal effect of engineering factors impacting on oil production. Meanwhile, combining with the practice exploitation in engineering factor impacting on production, a counterfactual experiment is designed to execute counterfactual prediction. Compared with general machine learning and statistical models, our results not only show better performance in oil production flooding but also guide the specific optimization in improving production, which holds more practical application significance.http://www.sciencedirect.com/science/article/pii/S2405656124000476Waterflooding oilfieldSingle oil wellCounterfactual inferenceTime-series
spellingShingle Guoquan Wen
Chao Min
Qingxia Zhang
Guoyong Liao
Dynamical counterfactual inference under time-series model for waterflooding oilfield
Petroleum
Waterflooding oilfield
Single oil well
Counterfactual inference
Time-series
title Dynamical counterfactual inference under time-series model for waterflooding oilfield
title_full Dynamical counterfactual inference under time-series model for waterflooding oilfield
title_fullStr Dynamical counterfactual inference under time-series model for waterflooding oilfield
title_full_unstemmed Dynamical counterfactual inference under time-series model for waterflooding oilfield
title_short Dynamical counterfactual inference under time-series model for waterflooding oilfield
title_sort dynamical counterfactual inference under time series model for waterflooding oilfield
topic Waterflooding oilfield
Single oil well
Counterfactual inference
Time-series
url http://www.sciencedirect.com/science/article/pii/S2405656124000476
work_keys_str_mv AT guoquanwen dynamicalcounterfactualinferenceundertimeseriesmodelforwaterfloodingoilfield
AT chaomin dynamicalcounterfactualinferenceundertimeseriesmodelforwaterfloodingoilfield
AT qingxiazhang dynamicalcounterfactualinferenceundertimeseriesmodelforwaterfloodingoilfield
AT guoyongliao dynamicalcounterfactualinferenceundertimeseriesmodelforwaterfloodingoilfield