Statistical Learning Techniques to Estimate the Size of Oilfield Flares from Satellite Data
Abstract/Contents
- Abstract
- This work investigates the feasibility of using statistical learning techniques to more accurately estimate the sizes of gas flares in the Bakken region. Satellite estimated flaring values from the VIIRS Nightfire Prerun v1 dataset were compared with reported flaring values from NDIC. VIIRS Nightfire errors were categorized into underestimation of flare sizes (Type II) Â and failure to identify flares altogether (Type I). Three statistical learning techniques (regression, random forest, boosted trees) were applied to reduce Type II error. We see marginal improvements in predictive accuracy using statistical learning techniques vs raw VIIRS Nightfire data.
Description
Type of resource | text |
---|---|
Date created | June 2015 |
Creators/Contributors
Author | Bharadwaj, Sharad |
---|---|
Primary advisor | Brandt, Adam |
Degree granting institution | Stanford University, Department of Energy Resources Engineering |
Subjects
Subject | School of Earth Energy & Environmental Sciences |
---|---|
Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
Preferred citation
- Preferred Citation
- Bharadwaj, Sharad. (2015). Statistical Learning Techniques to Estimate the Size of Oilfield Flares from Satellite Data. Stanford Digital Repository. Available at: https://purl.stanford.edu/jr324qc6145
Collection
Master's Theses, Doerr School of Sustainability
View other items in this collection in SearchWorksContact information
- Contact
- brannerlibrary@stanford.edu
Also listed in
Loading usage metrics...