EGBM: an ensemble gradient boost machine for lost circulation prediction

Juan Wang; Liang Li; Jianjun Ma; Yaobin Xie; Yuan Gao; Yaorong Xie; Xiaoli Zhang; Chengyou Wu

doi:10.1117/12.2627607

11 March 2022 EGBM: an ensemble gradient boost machine for lost circulation prediction

Juan Wang, Liang Li, Jianjun Ma, Yaobin Xie, Yuan Gao, Yaorong Xie, Xiaoli Zhang, Chengyou Wu

Proceedings Volume 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021); 1216002 (2022) https://doi.org/10.1117/12.2627607
Event: International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 2021, Sanya, China

Abstract

Lost circulation is one of the common drilling accidents. Occurrence of such problem will lead to a lot of wastage of resources. This paper proposes research on the application of ensemble gradient boost decision tree (GBDT) to develop a robust model that can be used to predict the occurrence of lost circulation precisely. In the first step, we collect 1048550 wells drilling data from northwest of China. Then two artificial features, distance feature and aggregation feature, are constructed by visualization. Next, we use three GBDT algorithms, XGBoost, LightGBM and Catboost, to build prediction models. Finally, we take the mean and maximum probability, predicted by the above three algorithms, as the ultimate output result. The result of the analysis has revealed that the ensemble model we propose performance are better than a single model. Besides, the model incorporates artificial features can attain a higher predicting accuracy.

Citation Download Citation

Juan Wang, Liang Li, Jianjun Ma, Yaobin Xie, Yuan Gao, Yaorong Xie, Xiaoli Zhang, and Chengyou Wu "EGBM: an ensemble gradient boost machine for lost circulation prediction", Proc. SPIE 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 1216002 (11 March 2022); https://doi.org/10.1117/12.2627607

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Machine learning

Performance modeling

Data mining

Evolutionary algorithms

Integrated modeling

Lithium

Show All Keywords

Keywords/Phrases

Search In:

Publication Years