|
|
|
|
|
|
0 Replies and 306 Views
Applications of AI and Machine Learning for Seismic Reservoir Characterization 306 0
Started by Patrick Ng
As with any emerging technologies (e.g., AVO versus Azimuths, full-waveform depth imaging, time-lapsed monitoring of fractures), there comes an inflection point where adoption and application will take off fast and furious, leading to step change in business practice. Today machine learning is fast emerging as a powerful tool to uncover new insights and AI may pave the way to actionable wisdom. To separate facts on the 'ground' (geoscience core principles) from hype, here is a webinar worth ...
|
|
|
|
0 |
306 |
03 Aug 2018 10:21 AM |
|
2 Replies and 597 Views
Forging the link between AI and First Principle 597 2
Started by Patrick Ng
'Safe AI', i.e., learning with machine beats machine learning alone Recent headline news, 1) “Uber halts self-driving tests after death in Arizona” and 2) “Florida bridge collapse” are unfortunately one accident too many. First, our thoughts shall go to the families of the victims. Next is call for action on continuous learning within the context of AI and machine learning. Both events prompt us to take a closer look at how we learn from data. Over the coming months, please feel free to ...
|
|
|
|
2 |
597 |
|
|
1 Replies and 327 Views
AAPG Hackathon Sign Up Today 327 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 |
327 |
|
|
0 Replies and 340 Views
Geoscience Building Blocks 340 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 |
340 |
12 Jun 2018 01:08 PM |
|
|
0 |
351 |
17 May 2018 12:57 PM |
|