A Machine Learning Method for the Risk Prediction of Casing Damage and Its Application in Waterflooding

Jiqun Zhang, Li Wu (), Deli Jia (), Liming Wang, Junhua Chang, Xianing Li, Lining Cui and Bingbo Shi
Additional contact information
Jiqun Zhang: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Li Wu: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Deli Jia: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Liming Wang: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Junhua Chang: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Xianing Li: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Lining Cui: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China
Bingbo Shi: Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China

Sustainability, 2022, vol. 14, issue 22, 1-21

Abstract: During the development of oilfields, casings in long-term service tend to be damaged to different degrees, leading to poor development of the oilfields, ineffective water circulation, and wasted water resources. In this paper, we propose a data-based method for predicting casing failure risk at both well and well-layer granularity and illustrate the application of the method to GX Block in an eastern oilfield of China. We first quantify the main control factors of casing damage by adopting the F -test and mutual information, such as that of the completion days, oil rate, and wall thickness. We then select the top 30 factors to construct the probability prediction model separately using seven algorithms, namely the decision tree, random forest, AdaBoost, gradient boosting decision tree, XGBoost, LightGBM, and backpropagation neural network algorithms. In terms of five evaluation indicators, namely the accuracy, precision, recall, F1-score, and area under the curve, we find that the LightGBM algorithm yields the best results at both granularities. The accuracy of the prediction model based on the preferred algorithm reaches 87.29% and 92.45% at well and well-layer granularity, respectively.

Keywords: water flooding; water resources; casing damage; influencing factor; machine learning; intelligent prediction model (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/22/14733/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/22/14733/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:22:p:14733-:d:967007

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().