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

A Sensor-Aware Decoupled Learning Framework for Robust Multi-Scale Time-Series Forecasting in Oil Production Systems.

Guojian Cheng1,2, Wenhan Zhang1, Zhonghui Jin3

  • 1School of Computer Science, Xi'an Shiyou University, Xi'an 710065, China.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

Related Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

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

Sort by
Same author

High-Temperature Ash Melting and Fluidity Behavior upon the Cocombustion of Sewage Sludge and Coal.

ACS omega·2024
Same author

Numerical simulation of a mechanical flocculation process with multi-chambers in series.

Water science and technology : a journal of the International Association on Water Pollution Research·2023
Same author

Production of Polyhydroxyalkanoates in Unsterilized Hyper-Saline Medium by Halophiles Using Waste Silkworm Excrement as Carbon Source.

Molecules (Basel, Switzerland)·2021
Same author

An efficient scRNA-seq dropout imputation method using graph attention network.

BMC bioinformatics·2021
Same author

Differences in Brain Functional Networks of Executive Function Between Cantonese-Mandarin Bilinguals and Mandarin Monolinguals.

Frontiers in human neuroscience·2021
Same author

Three new species of <i>Liparis s.l.</i> (Orchidaceae: Malaxideae) from Southwest China based on morphological characters and phylogenetic evidence.

Plant diversity·2021
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces the Temporal Augmented Residual Network (TAR-Net) for accurate oil well production forecasting. TAR-Net effectively models complex sensor data by decoupling temporal dependencies and local fluctuations, improving prediction accuracy.

Area of Science:

  • Petroleum Engineering
  • Data Science
  • Artificial Intelligence

Background:

  • Oil well production forecasting is crucial but limited by models that struggle to balance long-term temporal patterns and short-term sensor data.
  • Coupled modeling approaches often lead to trade-offs, reducing robustness against complex, non-stationary sensor dynamics and increasing noise interference.

Purpose of the Study:

  • To propose a novel hybrid framework, the Temporal Augmented Residual Network (TAR-Net), to address the limitations of current oil well production forecasting models.
  • To decouple the learning of temporal dependencies and the representation of nonlinear features for improved model performance and robustness.

Main Methods:

  • A decoupled paradigm separating global temporal modeling and local fluctuation compensation.
Keywords:
LightGBMdeep learningoil production monitoringresidual learningsensor-based forecastingtemporal convolutional network

Related Experiment Videos

  • Utilizing a multi-scale dilated Temporal Convolutional Network (TCN) for long-range temporal pattern extraction.
  • Employing a LightGBM-based residual module for targeted error correction and adaptive multi-fidelity Bayesian optimization for enhanced adaptability.

    • Main Results:

    • TAR-Net demonstrated superior performance on real Volve oilfield sensor data, achieving an R² of 0.9832 and a Mean Absolute Percentage Error (MAPE) of 7.8%.
    • Outperformed 13 benchmark models, confirming its effectiveness in complex industrial production scenarios.
    • Residual and trajectory analyses confirmed the model's ability to balance global trend consistency with local fluctuation sensitivity.

    Conclusions:

    • TAR-Net offers a robust, sensor-aware solution for complex multi-scale temporal modeling in industrial production systems.
    • The decoupled approach successfully enhances forecasting accuracy and model robustness in dynamic environments.
    • This framework provides a significant advancement for accurate oil well production prediction.