SAP HANA Idea Incubator – Predictive Analytic based on Oil & Gas [Natural Resources]- Upstream (Exploration)
https://ideas.sap.com/SAPHANAIdeaIncubator/predictive-analytic-based-on-oil–gas-na
Making use of different parameters or information from satellite imaging for all existing oil extraction sites, it may be possible to derive or generate complex algorithm to understand commonalities among different Oil extraction sites.
Based on this algorithm or pattern, it should be able to predict different possible oil extraction sites across earth by analyzing similar parameters (or information from satellite imaging for these sites).
These algorithm should provide probability to find oil across different areas.
These algorithm can be applied to find extraction sites (ores) for other precious & useful minerals as well based on similar or slightly different data.
Dear Subject Matter Experts,
Please provide your comments if you agree with this idea or you have better idea.
Thanks
Hello Arun Purohit !
So your idea is about finding new extraction sites based on the location of the existing , right ?
The question that came up in my mind is why do you think is SAP HANA necessary for that ?
Best Regards,
Christoforos Verras
hi Christoforos,
i thought R with HANA is required because we may have to process large amount of varied data i.e.
a.There will be large comparison data set from all existing extraction sites
b. There will be of satellite imaging data for sites we want predictions.
What is your opinion?
Regards,
Arun Purohit
hi Arun ,
What i can not understand is how would a statistical analysis give you a prediction - considering the overal cost of a new extraction site.
What if the prediction fails ?
Do you think an Oil firm gamble on such a high - priced (on money / time / HR) procedure ?
This is my only hesitation !
Thank you,
Christoforos Verras
Hi Chritoforos,
I think in Oil & Gas Industry (Upstream), they already do this kind of analysis (including exploration of new areas) before going ahead setting up everything there.
What I am thinking is, using R with HANA with complex algorithm will increase the accuracy of the analysis they might be doing already at some level.
Regarding cost- based on prediction they won't have to setup everything at once right, they can do bare minimum tests to confirm the site found. This I am sure they must be practicing already 🙂 .
Thanks,
Alright then ! 🙂
Hi Christoforos,
I am also not expert in oil & gas but your question was good and important 🙂 .
Check out following link, I found on google just now-
http://www.predictiveanalyticstoday.com/predictive-analytics-oil-gas/
Wowww ... good idea Arun.
But, I think que first, we have to geocode the data and then run the algorithm in some base with HANA, for seeking the geocoded data requires a lot of server memory.
So, I believe that creating a solution IS Oil & Gas to Hana is perfect.
Regards,
Everson
Thanks for your inputs Everson.
Hi Arun,
The below link throws some light in this domain :
http://www.rolta.com/wp-content/uploads//pdfs/resources/Achieving-Operational-Excellence-in-Upstream-Oil-Gas-Industry-SAP-Whitepaper-with-Rolta.pdf
Thanks/Nandini
Thanks Nandini for sharing the Whitepaper.