[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124171-en":3,"doc-seo-124171-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124171,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","PHYSICS-DRIVEN FEATURE CREATION TO IMPROVE MACHINE LEARNING MODELS PERFORMANCE FOR OIL PRODUCTION RATE PREDICTION","A physics-driven feature creation framework improves machine learning for oil production rate prediction by reducing feature dimensions while preserving model quality. The approach derives features from physical phenomena using domain knowledge and analytical relationships, in contrast to conventional dimension reduction via Principal Component Analysis (PCA). The study uses reservoir and well variables including permeability, skin, reservoir pressure, net pay thickness, water cut, and production rate, trains models such as SVM, k-NN, decision tree, random forest, and linear regression with PCA-based feature selection, and compares tuned and validated results under k-fold cross-validation. Results show higher R² (average gain of about 20% with physics-driven features versus PCA) and reduced sensitivity to data splits, with random forest and linear regression performing best.","PHYSICS-DRIVEN FEATURE CREATION TO IMPROVE MACHINE LEARNING MODELS PERFORMANCE FOR OIL PRODUCTION RATE  \nPREDICTION  \nEghbal Motaei 1   \nSeyed Mehdi Tabatabai 1   \nTarek Ganat 2   \nAhmad Khanifar 1  \nSulaiman Dzaiy 3  \nTimur Chis 3   \n1 Petroleum Engineering Department, Petronas Carigali SDN BHD, Malaysia  \n2 Sultan Qaboos University, Oman  \n3 Petroleum-Gas University of Ploiesti, Romania  \nemail (corresponding author): [mehdi.tabatabai@gmail.com](mehdi.tabatabai@gmail.com)  \n[DOI: 10.51865/JPGT.2024.02.22](DOI: 10.51865/JPGT.2024.02.22)  \nABSTRACT  \nThis paper aims to develop a machine learning-based model for oil production rate prediction. The significance of feature dimension reduction is addressed by applying well-established approaches like Principal Component Analysis (PCA) and the proposed physics-driven feature creation technique. The physics-driven features, derived from experience or analytical modeling, introduce physical relevance and improve model quality. The study focuses on oil production prediction using a dataset that includes reservoir permeability, wellbore skin, reservoir pressure, net pay thickness, water cut, and well-liquid production rate. Several machine learning techniques, such as SVM, k-NN, Decision Tree, Random Forest, and linear regression, were constructed using PCA featureselection. The models were tuned and validated using k-fold cross-validation. The same models were then built using physics-driven features, and their performance metrics were compared. The results show significant improvement when applying the proposed physics-driven feature creation, compared to PCA. Over 10-fold cross-validation, PCA improved the R² performance metric by 10%(from 70% to 77%), while physics-driven features increased it by 20%(from 70% to 90% on average) . The Random Forest and linear regression models outperformed the others, particularly when built based on physics-driven features. Additionally, models based on physics-driven features exhibited less sensitivity to data splits for learning and testing, proving more reliable with better performance metrics compared to those using original features.  \nKeywords: Oil rate prediction, Feature Engineering, Principal Component Analysis, Artificial Intelligence, Machine Learning  \nINTRODUCTION  \nThe digital transformation has introduced numerous Artificial Intelligence (AI) approaches to Decline Curve Analysis (DCA) for oil production rate forecasts. DCA, a well-established method since 1944 [1], has proven more promising than time-consuming numerical or analytical approaches, even with current advancements in computational capacity. The primary advantage of DCA is its time efficiency, allowing for simple application across hundreds of wells [2] . Since the early 2000s, machine learning techniques have been extensively applied to oil production rate estimation [3], aiming for time-reliable predictions using datasets generated from analytical or numerical simulation models [4] . Machine learning has proven to be powerful in numerous geoscience applications [5,6,7], including oil production prediction [8] . Researchers have employed various machine learning techniques for this purpose, such as Support Vector Machine (SVM) [9,10] and Random Forest (RF) [11] . The latter study utilized SVM and RF to predict oil production rates as part of supply chain optimization.  \nIn machine learning approaches, feature selection typically involves choosing variables based on their correlation with target values, ensuring that the model is built using the most impactful data [10] . A well-established technique for feature selection and dimension reduction is Principal Component Analysis (PCA) . This method is commonly used to replace raw data features with new, hybrid features that capture the most significant variations in the dataset [12] . While conventional dimension reduction approaches like Principal Component Analysis (PCA) often risk compromising machine learning model quali","cbCairT3qrfU14eY","https://ap.wps.com/l/cbCairT3qrfU14eY","pdf",1226942,1,16,"English","en",105,"# Abstract\n# Introduction\n## Digital transformation and decline curve analysis (DCA)\n## Machine learning for oil production forecasting\n## Feature selection and PCA-based dimension reduction\n## Physics-driven feature creation concept\n## Example: BMI-based feature replacement\n## Study objective and motivation","[{\"question\":\"What problem does the paper address in oil production forecasting?\",\"answer\":\"The paper addresses how to predict oil production rate using machine learning while improving quality under feature dimension reduction.\"},{\"question\":\"How are physics-driven features different from PCA-based features?\",\"answer\":\"Physics-driven features are created by incorporating physical phenomena and domain-specific dependency relationships, whereas PCA replaces raw features with hybrid components that capture dataset variance.\"},{\"question\":\"Which model families performed best in the experiments?\",\"answer\":\"Random Forest and linear regression showed the strongest performance, especially when trained using physics-driven features.\"}]","PHYSICS-DRIVEN FEATURE CREATION TO IMPROVE MACHINE LEARNING MODELS PERFORMANCE FOR OIL PRODUCTION RATE PREDICTION | PDF",1785820839,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"physics-driven-feature-creation-to-improve-machine-learning-models-performance-for-oil-production-rate-prediction","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/physics-driven-feature-creation-to-improve-machine-learning-models-performance-for-oil-production-rate-prediction/124171/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in oil production forecasting?","Question",{"text":75,"@type":76},"The paper addresses how to predict oil production rate using machine learning while improving quality under feature dimension reduction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are physics-driven features different from PCA-based features?",{"text":80,"@type":76},"Physics-driven features are created by incorporating physical phenomena and domain-specific dependency relationships, whereas PCA replaces raw features with hybrid components that capture dataset variance.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model families performed best in the experiments?",{"text":84,"@type":76},"Random Forest and linear regression showed the strongest performance, especially when trained using physics-driven features.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]