|
|
|
|
|
|
1 Replies and 345 Views
AAPG Hackathon Sign Up Today 345 1
Started by Patrick Ng
'Where oil is first found, in the final analysis, is in the minds of men' (pioneering petroleum geologist Wallace Pratt, 1952). Fast forward today, Susan Nash (AAPG) put forward the following, 'The reservoir is a puzzle, a mystery, a detective story, a series of meaningful patterns to be uncovered and revealed. And, vast riches have come to those who have gotten it right.' So when algorithm meets data and open mindset, something interesting happens Hackathon. Be s...
|
|
|
|
1 |
345 |
|
|
0 Replies and 370 Views
Geoscience Building Blocks 370 0
Started by Patrick Ng
It is useful to frame ML in terms of what we know, explore what we don’t know that we don’t know so we may create breakthrough. Getting started, lets take a look at feature engineering (alias attributes). Use case 1) Amplitude versus offset (AVO) – for simplicity, think classic two-term model. Reflection amplitude at each time sample is a weighted sum of P (intercept) and G (slope or gradient) multiplied by square of the sine of reflection angle. Features - P and G. Use case...
|
|
|
|
0 |
370 |
12 Jun 2018 01:08 PM |
|
|
0 |
373 |
17 May 2018 12:57 PM |
|
2 Replies and 403 Views
AI Geoscience Workshop coming this July 2018 403 2
Started by Patrick Ng
Heads up - mark your calendar for last week in July (tentative 7/26/2018 and subject to change). Venue - Houston Texas. Location TBD. What is it AAPG Deep Learning TIG teaming with Ikon Science and Google to conduct workshop using a variety of G&G data and running actual machine learning experiments. (If schedule permits, will include TensorFlow.) Premise - 'Learning with Machine beats machine learning alone' AI Geoscience Workshop. Watch this space for updates. Pat...
|
|
|
|
2 |
403 |
|
|
0 Replies and 403 Views
Deep Learning without deep pocket 403 0
Started by Patrick Ng
In response to inquiries on where to begin, consider the following: 1. Book - “The Master Algorithm” available in paperback $15 online (or check your local library). 2. Video - Machine Learning course on Coursera, http://ml-class.org (recall $49 if registered). 3. Python knowledge - take a look at https://www.learnpython.org/ The above is all about getting hands on. Mimic making hand contours and checking well ties. Get a feel for what the gotchas are early on, before investing in mo...
|
|
|
|
0 |
403 |
19 Apr 2018 02:14 PM |