Domain meets Deep Neural Networks: Hybrid Physics-based Hackathon for Geoscientists and Engineers

Summary

Halliburton and AAPG are collaborating to bring to AAPG community a Hybrid Physics-based deep neural network (DNN) Hackathon.

The objective of this hackathon, designed for domain geoscientists and engineers, is to hack the provided Python® code and develop DNN models for time series predictions of reservoir behavior.

Date: Thursday, July 19, 2018 from 7:00 AM to 5:30 PM (CDT)

Location: Marathon Energy Conference Center - Houston, TX

Register Now

Halliburton and AAPG are collaborating to bring to AAPG community a Hybrid Physics-based deep neural network (DNN) Hackathon.

The objective of this hackathon, designed for domain geoscientists and engineers, is to hack the provided Python® code and develop DNN models for time series predictions of reservoir behavior.

Date: Thursday, July 19, 2018 from 7:00 AM to 5:30 PM (CDT)

Location: Marathon Energy Conference Center - Houston, TX

This is a past event. Registration is closed

After we sell out, please sign up on the waiting list -- we will open more seats.

Hybrid Physics/DNN Integration

The use of deep learning models in oil and gas is on the rise.

Deep learning models while showing a lot of promise have limitations when applied to oil and gas problems.

Specifically these limitations deal with being able to incorporate geoscientists’ understanding of subsurface physics into deep learning models.

Subsurface physics can be incorporated in one of many ways a subset being:

Augmentation of training datasets for deep learning models using data generated by physics driven simulators, including physics-based models as a component in an ensemble of data driven deep learning models

Formally incorporating domain physics within the deep neural network structure

Scope and Prerequisites

Domain meets DNN hackathon is designed for practitioners, data scientists, developers, decision-makers and includes hands-on Python coding experiments. OpenEarth™ Community (OEC) , a cloud-based environment will be provided. For this hackathon, participants will focus on

  • Augmenting provisioned training dataset using a relevant physics based model
  • Modifying and applying supplied algorithm to their own model

Required Bootcamp Webinar July 16. All participants must participate in the pre-event familiarization boot-camp webinar. The bootcamp will orient participants with Python-coding and OEC environment. You will receive log-in information and time.

Agenda
7.00am Doors open
7:45am Welcome and Introduction, Susan Nash, Director of Innovation, Science, and Technology, AAPG / Patrick Ng, AAPG Deep Learning TIG / Rekha Patel, Halliburton
8:15am Hackathon Overview – Steve Ward, Chief Advisor
8:30am Hackathon Begins – Srinath Madasu, Technical Advisor
9:30am Coding for the Scope 1 Starts
12 Noon Lunch
1:00pm Coding for Scope 2 Starts
3:30pm Presentations/Judging
5:00pm Awards & Networking
Thank you to our sponsors
Hackathon Host
Hackathon Host
Coffee Break Sponsor
Coffee Break Sponsor
Patron Sponsor
Patron Sponsor
Patron Sponsor
Patron Sponsor
 Domain meets Deep Neural Networks: Hybrid Physics-based Hackathon for Geoscientists and Engineers
56660
 
56592
 
56581
 
56462
 
56460
 
56427
 
56434
 
56437
 
56435
 
56390
 
56661
 
56389
 
56388
 
56450
 
56356
 
56355
 
56499
 
56193
 
56108
 
56106
 
56098
 
55547
 
55296
 
55302
 
55299
 
55297
 
55306
 
55292
 
55437
 
55007
 
55006
 
55004
 
54321
 
54215
 
54218
 
54217
 
54214
 
54211
 
54210
 
54209
 
54208
 
54207
 
54204
 
54203
 
54199
 
54198
 
54197
 
54196
 
54195
 
54227
 
54225
 
54228
54226
 
54224
 
54654
 
54213
 
54655
 
54212
 
54194
 
54193
 
54192
 
54191
 
54190
 
54189
 
54188
 
54187
 
54186
54530
 
54529
 
54528
 
54527
 
53996
 
53995
 
54086
 
54336
 
54042
 
54035
 
54059
 
54026
 
54053
54029
 
54038
 
54041
54022
54243
 
54065
54386
54062
 
54063
 
54069
 
54006
 
54003
 
55008
 
54925
 
54030
 
54024
 
54015
 
54064
54044
 
54028
54016
 
54047
 
54048
 
54061
54034
54007
54009
 
54057
 
54031
 
54056
54010
 
54004
 
54055
 
54045
 
54033
 
54385
 
54023
54036
 
54051
 
54050
 
54020
54068
 
54052
 
54018
54002
 
54013
54058
 
54589
54049
 
54032
 
54017
 
54037
 
54067
 
54027
 
54043
 
54011
 
54039
 
55134
 
54574
54060
 
54384
 
54005
 
54025
 
54019
 
54012
 
54040
 
54021
 
54054
 
54046
53938
 
53762
 
53760
 
53603
 
53602
 
53237
 
54688
 
53061
 
53014
 
53007
 
53005
 
52709
 
52650
 
52649
 
52638
 
52301
 
52150
 
52568
 
52567
 
51957
 
51612
 
50629
 
50805
 
50465
 
49724
 
49566
 
50220
 
49589
 
49588
 
49587
 
49988
 
49528
 
49527
 
49523
 
49579
 
49195
 
49161
 
49103
 
49012
 
49008
 
46575
 
46089
 
45534
 
39997
 
39058
 
39057
 
37297
 
24627
 

See Also: GeoLegends Video

GeoLegends: Dietrich Welte (Part 1) GeoLegends Video GeoLegends: Dietrich Welte (Part 1) Desktop /Portals/0/PackFlashItemImages/WebReady/GeoLegends_Welte-Dietrich_Part1.jpg?width=100&h=100&mode=crop&anchor=middlecenter&quality=75amp;encoder=freeimage&progressive=true 37183
GeoLegends: R.G. "Jerry" Albertus and Stephen Kneller (Part 2) GeoLegends Video GeoLegends: R.G. "Jerry" Albertus and Stephen Kneller (Part 2) Desktop /Portals/0/PackFlashItemImages/WebReady/GeoLegends_Albertus-Kneller_Part2.jpg?width=100&h=100&mode=crop&anchor=middlecenter&quality=75amp;encoder=freeimage&progressive=true 42915
GeoLegends: Robert M. Sneider (presented by Larry Meckel) GeoLegends Video GeoLegends: Robert M. Sneider (presented by Larry Meckel) Desktop /Portals/0/PackFlashItemImages/WebReady/GeoLegends_Sneider-Bob-Meckel.jpg?width=100&h=100&mode=crop&anchor=middlecenter&quality=75amp;encoder=freeimage&progressive=true 42883
GeoLegends: Michael Forrest (Part 1) GeoLegends Video GeoLegends: Michael Forrest (Part 1) Desktop /Portals/0/PackFlashItemImages/WebReady/GeoLegends_Forrest-Michael_Part1.jpg?width=100&h=100&mode=crop&anchor=middlecenter&quality=75amp;encoder=freeimage&progressive=true 43101
GeoLegends: Pete Matuszczak GeoLegends Video GeoLegends: Pete Matuszczak Desktop /Portals/0/PackFlashItemImages/WebReady/GeoLegends_Wattenberg-Story.jpg?width=100&h=100&mode=crop&anchor=middlecenter&quality=75amp;encoder=freeimage&progressive=true 43133

Other Videos