cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
%3CLINGO-SUB%20id%3D%22lingo-sub-809966%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3EBuilding%20Advanced%20Predictive%20Models%20-%20Oil%20and%20Gas%20Case%20Study%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-809966%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%0A%3CP%3EThis%20case%20study%20uses%20JMP%20and%20JMP%20Pro%20to%26nbsp%3Bfind%20optimal%20geologic%20and%20completion%20parameters%20in%20upstream%20oil%20and%20gas%20processes%20(identifying%2C%20extracting%20and%20producing%20raw%20materials).%3C%2FP%3E%0A%3CP%3E%26nbsp%3B%3C%2FP%3E%0A%3CP%3E%26nbsp%3B%3C%2FP%3E%0A%3CP%3E%3C%2FP%3E%3CDIV%20class%3D%22lia-vid-container%20video-embed-center%22%3E%3CDIV%20id%3D%22lia-vid-6232415486001w480h270r60%22%20class%3D%22lia-video-brightcove-player-container%22%3E%3CVIDEO-JS%20data-video-id%3D%226232415486001%22%20data-account%3D%226058004218001%22%20data-player%3D%22default%22%20data-embed%3D%22default%22%20class%3D%22vjs-fluid%22%20controls%3D%22%22%20data-application-id%3D%22%22%20style%3D%22width%3A%20100%25%3B%20height%3A%20100%25%3B%22%3E%3C%2FVIDEO-JS%3E%3C%2FDIV%3E%3CSCRIPT%20src%3D%22https%3A%2F%2Fplayers.brightcove.net%2F6058004218001%2Fdefault_default%2Findex.min.js%22%3E%3C%2FSCRIPT%3E%3CA%20class%3D%22video-embed-link%22%20href%3D%22https%3A%2F%2Fcommunity.jmp.com%2Ft5%2Fvideo%2Fgallerypage%2Fvideo-id%2F6232415486001%22%20target%3D%22_blank%22%3E(view%20in%20My%20Videos)%3C%2FA%3E%3C%2FDIV%3E%3CP%3E%3C%2FP%3E%0A%3CP%3E%26nbsp%3B%3C%2FP%3E%0A%3CP%3ESee%20how%20to%3A%3C%2FP%3E%0A%3CUL%3E%0A%3CLI%3EUnderstand%20the%20goal%20of%20the%20models%20-%20to%20determine%20point%20of%20diminishing%20return%20for%20using%20additional%2C%20expensive%20solid%20material%20(proppant)%20in%20the%20process%3C%2FLI%3E%0A%3CLI%3EUnderstand%20the%26nbsp%3B%20response%20of%20interest%20-%20gross%20amount%20of%20oil%20and%20gas%20produced%20from%20a%20particular%20well%20over%20one%20year.%3C%2FLI%3E%0A%3CLI%3EUnderstand%20the%20study%20factors%0A%3CUL%3E%0A%3CLI%3EControlled%20factors%20(20%20completion%20parameters%2C%20amount%20of%20proppant%2C%20well%20perforation%20depth%2C%20%23%20of%20completion%20stages%2C%20lateral%20well%20length)%3C%2FLI%3E%0A%3CLI%3EPseudo-controlled%20factors%20(location%20parameters%2C%20county%2C%20latitude%2C%20longitude)%3C%2FLI%3E%0A%3CLI%3EUncontrolled%20factors%20(23%20geologic%20parameters%2C%20facies%2C%20reservoir%20thickness%2C%20porosity%20%26amp%3B%20permeability%2C%20(TOC)%20total%20organic%20carbon)%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3C%2FLI%3E%0A%3CLI%3EPrepare%20data%20for%20analysis%0A%3CUL%3E%0A%3CLI%3E%3CSPAN%3EHandle%20missing%20values%20using%20imputation%3C%2FSPAN%3E%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3C%2FLI%3E%0A%3CLI%3EUse%20Predictor%20Screening%20to%20identify%20significant%20predictors%20out%20of%20all%20factors%0A%3CUL%3E%0A%3CLI%3ERank%20all%20predictors%20using%20Bootstrap%20Forest%26nbsp%3B%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3C%2FLI%3E%0A%3CLI%3EBuild%20model%20using%20Fit%20Model%20to%20rapidly%20develop%20simple%20to%20complex%20linear%20models%20using%20various%20fitting%20techniques%2C%20model%20parameters%2C%20and%20additional%20settings%20including%20random%20effects%0A%3CUL%3E%0A%3CLI%3EConstruct%20Standard%20Least%20Squares%20model%20(JMP)%3C%2FLI%3E%0A%3CLI%3EConstruct%20Stepwise%20Regression%20model%20(JMP)%3C%2FLI%3E%0A%3CLI%3EConstruct%20Logistic%20Regression%20model%20(JMP)%3C%2FLI%3E%0A%3CLI%3EUse%20Generalized%20Regression%20(Pro)to%20create%20text%2C%20validation%20and%20training%20sets%20and%20then%20model%20correlated%20and%20high-dimensional%20data%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3C%2FLI%3E%0A%3CLI%3EUse%20JMP%20Pro%20to%20fit%20an%20ensemble%20model%20by%20averaging%20many%20decision%20trees%0A%3CUL%3E%0A%3CLI%3ESee%20how%20each%20split%20considers%20a%20random%20subset%20of%20the%20predictors%3C%2FLI%3E%0A%3CLI%3EUse%20Prediction%20Profiler%20to%20identify%20point%20of%20diminishing%20returns%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3C%2FLI%3E%0A%3C%2FUL%3E%0A%3CP%3E%3CSPAN%20class%3D%22lia-inline-image-display-wrapper%20lia-image-align-inline%22%20image-alt%3D%22specifying.JPG%22%20style%3D%22width%3A%20567px%3B%22%3E%3CSPAN%20class%3D%22lia-inline-image-display-wrapper%22%20image-alt%3D%22specifying.JPG%22%20style%3D%22width%3A%20567px%3B%22%3E%3Cspan%20class%3D%22lia-inline-image-display-wrapper%22%20image-alt%3D%22specifying.JPG%22%20style%3D%22width%3A%20567px%3B%22%3E%3Cimg%20src%3D%22https%3A%2F%2Fcommunity.jmp.com%2Ft5%2Fimage%2Fserverpage%2Fimage-id%2F30933i08122B6F16B5CDA5%2Fimage-size%2Flarge%3Fv%3Dv2%26amp%3Bpx%3D999%22%20role%3D%22button%22%20title%3D%22specifying.JPG%22%20alt%3D%22specifying.JPG%22%20%2F%3E%3C%2Fspan%3E%3C%2FSPAN%3E%3C%2FSPAN%3E%3C%2FP%3E%0A%3C%2FLINGO-BODY%3E%3CLINGO-LABS%20id%3D%22lingo-labs-809966%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%3CLINGO-LABEL%3EAdvanced%20Statistical%20Modeling%3C%2FLINGO-LABEL%3E%3C%2FLINGO-LABS%3E
Choose Language Hide Translation Bar

Building Advanced Predictive Models - Oil and Gas Case Study

Published on ‎11-07-2024 03:29 PM by Community Manager Community Manager | Updated on ‎11-07-2024 05:39 PM

This case study uses JMP and JMP Pro to find optimal geologic and completion parameters in upstream oil and gas processes (identifying, extracting and producing raw materials).

 

 

 

See how to:

  • Understand the goal of the models - to determine point of diminishing return for using additional, expensive solid material (proppant) in the process
  • Understand the  response of interest - gross amount of oil and gas produced from a particular well over one year.
  • Understand the study factors
    • Controlled factors (20 completion parameters, amount of proppant, well perforation depth, # of completion stages, lateral well length)
    • Pseudo-controlled factors (location parameters, county, latitude, longitude)
    • Uncontrolled factors (23 geologic parameters, facies, reservoir thickness, porosity & permeability, (TOC) total organic carbon)
  • Prepare data for analysis
    • Handle missing values using imputation
  • Use Predictor Screening to identify significant predictors out of all factors
    • Rank all predictors using Bootstrap Forest 
  • Build model using Fit Model to rapidly develop simple to complex linear models using various fitting techniques, model parameters, and additional settings including random effects
    • Construct Standard Least Squares model (JMP)
    • Construct Stepwise Regression model (JMP)
    • Construct Logistic Regression model (JMP)
    • Use Generalized Regression (Pro)to create text, validation and training sets and then model correlated and high-dimensional data
  • Use JMP Pro to fit an ensemble model by averaging many decision trees
    • See how each split considers a random subset of the predictors
    • Use Prediction Profiler to identify point of diminishing returns

specifying.JPG



Start:
Tue, Sep 22, 2020 02:00 PM EDT
End:
Tue, Sep 22, 2020 03:00 PM EDT
Labels (1)
Attachments
0 Kudos
0 Comments