Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Real-Time Prediction Method of Shale Gas Fracturing Construction Pressure Based on MS-1DCNN-TFT Neural Network.

Zhaoyi Liu1,2, Xiangyu Wang1, Lingling Han1

  • 1College of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China.

ACS Omega
|July 3, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Social isolation and loneliness associate with early menopause and mortality in women: a UK Biobank cohort study.

BMC medicine·2026
Same author

Exploring EFL Students' Perceived Changes in Emotional Engagement and Perceptual Skills After Prolonged Use of AI-Based Tools: A Qualitative Study.

Perceptual and motor skills·2026
Same author

Method for Selective REM Sleep Deprivation using The Selective Nose Flicking for Forgetting REM (SNiFFer).

Journal of visualized experiments : JoVE·2026
Same author

Targeting coupling of type H-like vessels and cell fate transition to delay soft tissue aging.

Nature communications·2026
Same author

Monolithic Integration of Crack-Free 2D Bi<sub>2</sub>O<sub>2</sub>Se via Stress Modulation.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

DPhA-EtOBz-TSC targets cystathionine γ-lyase (CSE) to trigger ferroptosis and inhibit colorectal cancer growth in vitro and in vivo.

European journal of pharmacology·2026

This study introduces an advanced AI method for predicting shale gas fracturing pressure in real-time. The novel approach significantly improves prediction accuracy, aiding in cost reduction and efficiency increases.

Area of Science:

  • Petroleum Engineering
  • Artificial Intelligence
  • Data Science

Background:

  • Accurate real-time prediction of shale gas fracturing construction pressure is crucial for operational efficiency and safety.
  • Existing methods often struggle with long-term prediction accuracy and adapting to changing working conditions.

Purpose of the Study:

  • To develop a robust and accurate method for real-time prediction of shale gas fracturing construction pressure.
  • To enhance model adaptability and mitigate performance degradation during long-term predictions.

Main Methods:

  • A hybrid deep learning architecture combining a multiscale one-dimensional convolutional neural network (MS-1DCNN) for feature extraction and a temporal fusion transformer (TFT) for time-series modeling.
  • Implementation of a mild online learning strategy using a FIFO buffer and EMA weight updates for continuous model adaptation.

Related Experiment Videos

Main Results:

  • The static model achieved a Mean Absolute Error (MAE) of 3.21 MPa, outperforming baseline methods.
  • Online learning further reduced the MAE to 1.98 MPa, a 38% improvement, demonstrating effective error drift suppression.

Conclusions:

  • The proposed MS-1DCNN-TFT model with online learning offers a reliable algorithmic solution for intelligent monitoring of shale gas fracturing.
  • This approach holds significant potential for cost reduction and efficiency enhancement in shale gas operations.