@article{scholars17409,
            year = {2022},
       publisher = {Springer Science and Business Media Deutschland GmbH},
         journal = {Lecture Notes in Electrical Engineering},
           pages = {597--604},
          volume = {758},
            note = {cited By 0; Conference of 1st International Conference on Artificial Intelligence for Smart Community, AISC 2020 ; Conference Date: 17 December 2020 Through 18 December 2020; Conference Code:286319},
             doi = {10.1007/978-981-16-2183-3{$_5$}{$_7$}},
           title = {Current Overview of Machine Learning Application for Predicting Steam Huff and Puff Injection Production Performance},
        keywords = {Computer aided instruction; Engineering education; Enhanced recovery; Petroleum reservoir engineering; Petroleum reservoirs; Steam, 'current; Enhanced-oil recoveries; Machine learning applications; Machine-learning; Oil and gas; Production performance; Proxy model; Reservoir engineering; Steam huff and puff; Thermal, Machine learning},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142694054&doi=10.1007\%2f978-981-16-2183-3\%5f57&partnerID=40&md5=6e750e2ead17b4d50256b06a9b1458dd},
        abstract = {Thermal Enhanced Oil Recovery (EOR) is one of the main contributors to EOR worldwide production. Steam huff and puff injection, one of its methods, is a technique in which steam is injected in a cyclical manner alternating with oil production. Reservoir simulation is considered as the most reliable solution to evaluate the reservoir performance and designing an optimized production scheme. However, it still remains time-consuming and expensive. Applying machine learning to build a predictive proxy model is a suitable solution to deal with the issue. Presently, there have been a limited number of studies covering the topic of proxy model development to estimate production performance for this injection method. This study provides a review of the machine learning implementations for estimating steam huff and puff injection production performance, starting with an introductory explanation about the method, followed by the currently deployed machine learning models along with the challenges and future prospects. {\^A}{\copyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.},
            issn = {18761100},
          author = {Merdeka, M. G. and Ridha, S. and Negash, B. M. and Ilyas, S. U.},
            isbn = {9789811621826}
}