Posts Tagged ‘maybel2e’

Deep learning and process understanding for data-driven Earth system science | Nature

Tuesday, March 5th, 2019

https://www.nature.com/articles/s41586-019-0912-1
Perspective | Published: 13 February 2019
Deep learning and process understanding for data-driven Earth system science Markus Reichstein, Gustau Camps-Valls, Bjorn Stevens, Martin Jung, Joachim Denzler, Nuno Carvalhais & Prabhat
Nature volume 566, pages195–204 (2019)

QT:[[”
Figure 3 presents a system-modelling view that seeks to integrate machine learning into a system model. As an alternative perspective, system knowledge can be integrated into a machine learning frame- work. This may include design of the network architecture36,79, physical constraints in the cost function for optimization58, or expansion of the training dataset for undersampled domains (that is, physically based data augmentation)80.

Surrogate modelling or emulation
See Fig. 3 (circle 5). Emulation of the full (or specific parts of) a physical model can be useful for computational efficiency and tractability rea- sons. Machine learning emulators, once trained, can achieve simulations orders of magnitude faster than the original physical model without sacrificing much accuracy. This allows for fast sensitivity analysis, model parameter calibration, and derivation of confidence intervals for the estimates.

(2) Replacing a ‘physical’ sub-model with a machine learning model
See Fig. 3 (circle 2). If formulations of a submodel are of semi-empirical nature, where the functional form has little theoretical basis (for example, biological processes), this submodel can be replaced by a machine learning model if a sufficient number of observations are available. This leads to a hybrid model, which combines the strengths of physical modelling (theoretical foundations, interpretable compartments) and machine learning (data-adaptiveness).

Integration with physical modelling
Historically, physical modelling and machine learning have often been treated as two different fields with very different scientific paradigms (theory-driven versus data-driven). Yet, in fact these approaches are complementary, with physical approaches in principle being directly interpretable and offering the potential of extrapolation beyond observed conditions, whereas data-driven approaches are highly flexible in adapting to data and are amenable to finding unexpected patterns (surprises).

A success story in the geosciences is weather
prediction, which has greatly improved through the integration of better theory, increased computational power, and established observational systems, which allow for the assimilation of large amounts of data into the modelling system2
. Nevertheless, we can accurately predict the evolution
of the weather on a timescale of days, not months.
“]]

# REFs that I liked
ref 80

ref 57
Karpatne, A. et al. Theory-guided data science: a new paradigm for scientific discovery from data. IEEE Trans. Knowl. Data Eng. 29, 2318–2331 (2017).

# some key BULLETS

• Complementarity of physical & ML approaches
–“Physical approaches in principle being directly interpretable and offering the potential of extrapolation beyond observed conditions, whereas data-driven approaches are highly flexible in adapting to data”

• Hybrid #1: Physical knowledge can be integrated into ML framework –Network architecture
–Physical constraints in the cost function
–Expansion of the training dataset for undersampled domains (ie physically based data augmentation)

• Hybrid #2: ML into physical – eg Emulation of specific parts of a physical for computational efficiency

Artificial intelligence alone won’t solve the complexity of Earth sciences

Tuesday, March 5th, 2019

https://www.nature.com/articles/d41586-019-00556-5

More New Yorkers Opting for Life in the Bike Lane – The New York Times

Thursday, August 3rd, 2017

More NYers Opting for…the Bike Lane – 450k trips/day v. 170k in ’05
https://www.NYTimes.com/2017/07/30/nyregion/new-yorkers-bike-lanes-commuting.html But there’s #bikelash from walkers & drivers

How Not to End Cancer in Our Lifetimes – WSJ

Friday, April 8th, 2016

How Not to End Cancer in Our Lifetimes
http://www.wsj.com/articles/how-not-to-end-cancer-in-our-lifetimes-1459811684“It’s extraordinarily hard to re-identify tissue” anonymously biobanked. True?

The Economist explains: Why fashion week is passé | The Economist

Thursday, March 10th, 2016

Why #fashion week is passé
http://www.economist.com/blogs/economist-explains/2016/03/economist-explains-5?fsrc=scn/tw/te/bl/ed/whyfashionweekispass Technology is making the timing of big shows irrelevant

We Need a New Green Revolution

Saturday, January 9th, 2016

We Need a New Green Revolution http://www.nytimes.com/2016/01/04/opinion/we-need-a-new-green-revolution.html Advocates US agri-science funding to grow yields. Sensible given #obesity epidemic?

QT:{{"
“Today, farm production has stopped growing in the United States, and agriculture research is no longer a priority; it constitutes only 2 percent of federal research and development spending. And, according to the Department of Agriculture, total agricultural production has slowed significantly since the turn of the century. We need another ambitious surge in agricultural science.”
"}}

What Will Replace Google Reader? : The New Yorker

Friday, July 5th, 2013

NYer: What Will Replace #Google Reader? #Digg? Potluck? We could do better… via @shinshinuk http://bit.ly/15jpdIx

http://www.newyorker.com/online/blogs/elements/2013/06/what-will-replace-google-reader.html