AIandML: Difference between revisions

From CSDMS
No edit summary
 
(16 intermediate revisions by 3 users not shown)
Line 3: Line 3:
== '''With Artificial Intelligence & Machine Learning - What Lies Ahead for Earth Surface Modeling ?''' ==
== '''With Artificial Intelligence & Machine Learning - What Lies Ahead for Earth Surface Modeling ?''' ==


A Forum, 1030-1230pm, 24th May 2018, SEEC Room ###
A Forum, 1030-1230pm, Thursday 24th May 2018, SEEC Room C120 (main auditorium)
 
Convened by Chris JENKINS (INSTAAR, Boulder CO) and Jeff OBELCZ (NRL, Stennis, MS)
Convened by Chris JENKINS (INSTAAR, Boulder CO) and Jeff OBELCZ (NRL, Stennis, MS)


Line 9: Line 10:
=== '''Questions for the Forum''' ===
=== '''Questions for the Forum''' ===
* What can AI and ML currently do that might benefit Earth Surface Dynamics Modeling ?
* What can AI and ML currently do that might benefit Earth Surface Dynamics Modeling ?
* What is the relationship between Process Modelling and AI/ML ?
* What is the relationship between Process Modelling and AI&ML ?
* How should CSDMS Community Respond to the Appearance of AI/ML
* How should CSDMS Community Respond to the Appearance of AI&ML
* What Earth Surface Dynamics Modeling-related tasks are not suited for AI/ML? Why?
* What Earth Surface Dynamics Modeling-related tasks are not suited for AI&ML? Why?
 
=== '''Agenda and Survey Docs''' ===
 
Please see the Agenda at [https://drive.google.com/open?id=1zqRAEm7G3twkjXWOVTETMbNDvlQAD4oB HERE]
 
Please complete and return the simple [https://docs.google.com/forms/d/1xl7v5Z8MFd5M4pmcA2eqQb9zlc-O838Ipvy0G8MjCx0/edit Pre-Clinic Survey] (3 questions, ~1 minute)
 
=== '''Other groupings''' ===
NSF May 2018. [https://www.nsf.gov/news/news_summ.jsp?cntn_id=245418&WT.mc_id=USNSF_51&WT.mc_ev=click Statement on Artificial Intelligence for American Industry.] NSF director outlines vision for AI that benefits the economy and U.S. workers.
 
IS-GEO, May 2018. [https://is-geo.org/ The IS-GEO Research Coordination Network aims to support an emerging community of researchers in intelligent systems (IS) and geosciences (GEO).] A NSF Research Coordination Network.


=== '''Background Reading''' ===
=== '''Background Reading''' ===
* Participants can share URL's here to papers that discuss the workings of AI/ML and applications in fields such as ours. Some papers are also relevant to questions for the forum (above).
* Participants can share URL's here to papers that discuss the workings of AI&ML and applications in fields such as ours. Some papers are also relevant to questions for the forum (above).
 
A number of copies will be made available at the forum.


Jones, N. 2018. [https://www.nature.com/news/how-machine-learning-could-help-to-improve-climate-forecasts-1.22503 How machine learning could help to improve climate forecasts]. Nature 548, 379–380 (24 August 2017) doi:10.1038/548379a .
Jones, N. 2018. [https://www.nature.com/news/how-machine-learning-could-help-to-improve-climate-forecasts-1.22503 How machine learning could help to improve climate forecasts]. Nature 548, 379–380 (24 August 2017) doi:10.1038/548379a .
Line 21: Line 35:


Abbot, J. & Marohasy,J. 2013. [https://www.witpress.com/elibrary/wit-transactions-on-ecology-and-the-environment/172/24639 The Application Of Artificial Intelligence For Monthly Rainfall Forecasting In The Brisbane Catchment, Queensland, Australia.] WIT Transactions on Ecology and the Environment, 172, 125 - 135. DOI:10.2495/RBM130111
Abbot, J. & Marohasy,J. 2013. [https://www.witpress.com/elibrary/wit-transactions-on-ecology-and-the-environment/172/24639 The Application Of Artificial Intelligence For Monthly Rainfall Forecasting In The Brisbane Catchment, Queensland, Australia.] WIT Transactions on Ecology and the Environment, 172, 125 - 135. DOI:10.2495/RBM130111
Karpatne, A., et al., 2017. [https://arxiv.org/pdf/1711.04708.pdf Machine Learning for the Geosciences: Challenges and Opportunities.] Workshop on Mining Big Data in Climate and Environment (MBDCE 2017), 17th SIAM International Conference on Data Mining (SDM 2017).
Burghard, C. 2017. [http://www.nvidia.com/object/idc-deep-learning-in-healthcare.html From Bench to Bedside: Deep Learning’s Journey in Healthcare. ] (Registration required)
Datascience 2018. [https://www.datascience.com/resources Resources.] Culver City CA (Commercially oriented source of up-to-date briefings, useful even down to technical levels.)
Joppa, L.N. 2017. [https://www.nature.com/articles/d41586-017-08675-7 The case for technology investments in the environment. Create an artificial-intelligence platform for the planet, urges Lucas N. Joppa.] Nature 552, 325-328 (2017), doi:10.1038/d41586-017-08675-7.
Marone, C. 2018. [https://www.nature.com/articles/s41561-018-0117-5?WT.ec_id=NGEO-201805&spMailingID=56516686&spUserID=MTg1NDc3MTE2MzY3S0&spJobID=1384567859&spReportId=MTM4NDU2Nzg1OQS2 Training machines in Earthly ways]. Nature Geoscience 11, 301-302 (2018), doi: 10.1038/s41561-018-0117-5 .
Rahimi, A. 2018 [http://www.argmin.net/2017/12/05/kitchen-sinks/ Reflections on Random Kitchen Sinks] 'arg minblog' May 2018.
and commentary:
Hutson, M. 2018. [http://www.sciencemag.org/news/2018/05/ai-researchers-allege-machine-learning-alchemy AI researchers allege that machine learning is alchemy] Science May 2018.
Thessen, A.E. 2016. [https://oneecosystem.pensoft.net/articles.php?id=8621 Adoption of Machine Learning Techniques in Ecology and Earth Science.] One Ecosystem 1: e8621. DOI10.3897/oneeco.1.e8621.
Lehman et al. 2018. [https://arxiv.org/abs/1803.03453 The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities]. arXiv:1803.03453. (aka Complex models produce unexpected results)
[http://www.sciencemag.org/news/2018/02/missing-data-hinder-replication-artificial-intelligence-studies Machine learning replicability crisis]


=== '''Displays during the Forum''' ===
=== '''Displays during the Forum''' ===
Line 29: Line 63:




<small>''Dateline: CJ 12Feb2018''</small><small>Small text</small>
<small>''Dateline: CJ 17May2018''</small><small>Small text</small>

Latest revision as of 10:46, 26 March 2019

2018 CSDMS Annual Meeting:

With Artificial Intelligence & Machine Learning - What Lies Ahead for Earth Surface Modeling ?

A Forum, 1030-1230pm, Thursday 24th May 2018, SEEC Room C120 (main auditorium)

Convened by Chris JENKINS (INSTAAR, Boulder CO) and Jeff OBELCZ (NRL, Stennis, MS)


Questions for the Forum

  • What can AI and ML currently do that might benefit Earth Surface Dynamics Modeling ?
  • What is the relationship between Process Modelling and AI&ML ?
  • How should CSDMS Community Respond to the Appearance of AI&ML
  • What Earth Surface Dynamics Modeling-related tasks are not suited for AI&ML? Why?

Agenda and Survey Docs

Please see the Agenda at HERE

Please complete and return the simple Pre-Clinic Survey (3 questions, ~1 minute)

Other groupings

NSF May 2018. Statement on Artificial Intelligence for American Industry. NSF director outlines vision for AI that benefits the economy and U.S. workers.

IS-GEO, May 2018. The IS-GEO Research Coordination Network aims to support an emerging community of researchers in intelligent systems (IS) and geosciences (GEO). A NSF Research Coordination Network.

Background Reading

  • Participants can share URL's here to papers that discuss the workings of AI&ML and applications in fields such as ours. Some papers are also relevant to questions for the forum (above).

A number of copies will be made available at the forum.

Jones, N. 2018. How machine learning could help to improve climate forecasts. Nature 548, 379–380 (24 August 2017) doi:10.1038/548379a .

Grover, A. et al. 2015. A Deep Hybrid Model for Weather Forecasting. 2015 ACM, DOI: http://dx.doi.org/10.1145/2783258.2783275.

Abbot, J. & Marohasy,J. 2013. The Application Of Artificial Intelligence For Monthly Rainfall Forecasting In The Brisbane Catchment, Queensland, Australia. WIT Transactions on Ecology and the Environment, 172, 125 - 135. DOI:10.2495/RBM130111

Karpatne, A., et al., 2017. Machine Learning for the Geosciences: Challenges and Opportunities. Workshop on Mining Big Data in Climate and Environment (MBDCE 2017), 17th SIAM International Conference on Data Mining (SDM 2017).

Burghard, C. 2017. From Bench to Bedside: Deep Learning’s Journey in Healthcare. (Registration required)

Datascience 2018. Resources. Culver City CA (Commercially oriented source of up-to-date briefings, useful even down to technical levels.)

Joppa, L.N. 2017. The case for technology investments in the environment. Create an artificial-intelligence platform for the planet, urges Lucas N. Joppa. Nature 552, 325-328 (2017), doi:10.1038/d41586-017-08675-7.

Marone, C. 2018. Training machines in Earthly ways. Nature Geoscience 11, 301-302 (2018), doi: 10.1038/s41561-018-0117-5 .

Rahimi, A. 2018 Reflections on Random Kitchen Sinks 'arg minblog' May 2018. and commentary: Hutson, M. 2018. AI researchers allege that machine learning is alchemy Science May 2018.

Thessen, A.E. 2016. Adoption of Machine Learning Techniques in Ecology and Earth Science. One Ecosystem 1: e8621. DOI10.3897/oneeco.1.e8621.

Lehman et al. 2018. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities. arXiv:1803.03453. (aka Complex models produce unexpected results)

Machine learning replicability crisis

Displays during the Forum

  • Posters, and printed materials for distribution will be available at the event

Online Resources for the Forum

  • This Wiki will serve Abstracts, URL's, Posters, Images supplied by participants before and during the meeting


Dateline: CJ 17May2018Small text