Carbajal's Youtube channel

Carbajal's Youtube channel

A Youtube channel with unofficial video recordings of Juan Pablo Carbajal’s talks.

Check it out and subscribe!

Patrick Troxler's master thesis

Patrick Troxler's master thesis

Congratulations to Patrick Troxler for passing his master thesis defense!

Patrick used Kalman Filters to provide online inflow prediction to Water Treatment Plant in Oberengadin (under construction). He managed to go from 0 to something that is actually working, we are sure the results will improve in a few iterations. Well done!

Follow the link in the title to explore the repositories with the code of his work.

Special Issue

Special Issue "Machine Learning Applied to Hydraulic and Hydrological Modelling"

Submit to our special issue!

The computational power available nowadays allow us to tackle simulation challenges in hydraulic and hydrological modelling at different scales that were impossible a few decades ago. However, even in the current situation, the time needed for these simulations is inadequate for many scientific and engineering applications, such as decision support systems, flood warning systems, design or optimization of hydraulic structures, calibration of model parameters, uncertainty quantification, real-time model-based control, etc.

To address these issues, the development of fast surrogate models to increase the simulation speed seems to be promising strategy: it does not require a huge investment in new hardware and software, and the same tools can be used to solve very different problems. The field of Machine Learning offers a huge library of methods to build surrogate models, many of which have been successfully used in hydraulic and hydrological modelling.

In this Special Issue we would like to invite research works which incorporate Machine Learning techniques in hydraulic and hydrological modelling, such as (but not restricted to):

  • Artificial Science, in which a relation between input and output is learned using only data, also known as data-driven methods.

  • Scientific Numerical Modelling, such as simplified numerical models, model calibration (system identification) or optimization, renormalized models, up (down)scaled models, coarse models, etc.

  • Emulation, where a fast emulator is developed based on training data derived by a slow simulator

Dr. Vasilis Bellos

Dr. Juan Pablo Carbajal

Guest Editors

Machine Learning in Hydroresearch

Is emulation just an application of machine learning to an specific problem?

relation between machine learning, emulation, and mechanistic modeling
Credit: Juan Pablo Carbajal under CCBY 4.0 via Emumore's Wiki.

The most frequent answer is probably: yes! However, there is more to emulation than just model-free statistical learning methods.

Continue Reading ...
EmuMore at the 5th IAHR Europe Congress

EmuMore at the 5th IAHR Europe Congress

EmuMore was present in the 5th IAHR Europe congress: New Challenges in Hydraulic Research and Engineering. We organized a special session on Machine Learning.

Follow the link to browse the proceedings of the session.

Sebastiano Rusca's master thesis

Sebastiano Rusca's master thesis

Congratulations to Sebastiano Rusca for passing his master thesis defense!

Sebastiano worked on the exploration of Gasussian Processes based emulation for flood prediction. Among other interesting stuff, he explored the use of a classifier to decide what emulator to use (in his case the decision was only whether to use the emulator or not).

Follow the link in the title and check the Downloads page to get a copy of his thesis.

EmuMore at AGU 2017

EmuMore at AGU 2017

Dr. Vasilis Bellos presented our results on emulation of 2D shallow water equations used for the simulation of the Tous dam break. The publication is coming soon, with data and scripts!

Computational effort and emulation error

There is nothing better to force a new perspective on the work we do than the questions from other people. In this post we revisit the idea of emulation inspired by some surgical questions formulated by Kris Villez, aiming at understanding the relation between an emulator and the simulator it is based on.

These are the questions we will discuss:

  1. Can my emulator make exact predictions of my simulator output for any input?

  2. If my emulator makes exact predictions, will it be faster than my simulator?

  3. How small should my emulation error be?

Emulation error vs computational effort
Credit: CCBY4.0 based on Kris Villez' original diagram
Continue Reading ...
Wiki renders math

Wiki renders math

If you have peeked into our wiki you might have noticed that MathJax was not rendering, sorry for that! This was due to a bug in the BitBucket platform that now is fixed: kudos for the Atlassian team!

Now you should get rendered math even if you do not have a BitBucket account, give it a try.

Biokinetic Models

New process technologies that enable the shift from conventional biological wastewater treatment processes to resource recovery systems are matched by an increasing demand for predictive capabilities. Mathematical models are excellent tools to meet this demand, but they runtime still hinders parameter indetification and real-time control.

Continue Reading ...
Emulation Talk at ZHAW Winterthur, Switzerland

Emulation Talk at ZHAW Winterthur, Switzerland

We will presenting some of our work at the 2nd European COST Conference on Mathematics for Industry in Switzerland, Artificial Intelligence in Industry and Finance.

Rotated Principal Components. Interpretability in the Eye of the Beholder

In the sciences, it is increasingly more common to deal with high-dimensional datasets. In some fields like meteorology this was always the case. Many tools have been released to perform “dimensionality reduction”, which enables us to interpret and handle these huge datasets more easily. One of the most popular methods is Principal Components Analysis (PCA) (we have talked about its many guises), but it has been criticized. Here we make a short and partial review of “Rotation of principal components” by M. B. Richman, a highly cited article from the 80’s popular in earth sciences …

PCA of a multivariate Gaussian distribution
Credit: CCBY4.0 Nicoguaro at Wikimedia commons
Continue Reading ...
Model Order Reduction and Emulation

So you have your nifty numerical simulator that captures all the details of the complex device you want to model, everything! You got your digital twin, and for a while everything is OK.

Beyond reality

There comes the day in which you want to use your simulator in ways that go beyond the constraints imposed by the physical world … well, that is the reason why we build simulators, isn’t it?

Continue Reading ...
Groundwater Recharge Rate

After a fruitful meeting with Christian Möck from the Department of Water Resources & Drinking Water at Eawag, we agreed to collaborate on building an emulator for a physics based simulator of Groundwater recharge rates.

Surface water cycle
Credit: M. W. Toews under CCBY 4.0 via Wikimedia Commons.
Continue Reading ...
Polyonymous Algorithms

One core idea of emulation is to represent the ensemble of outputs of a complicated simulator in a reduced basis. The battle-horse algorithm to do this is the famous PCA, a.k.a POD, a.k.a SVD, a.k.a EOF, a.k.a. EBD, a.k.a. KLD, a.k.a. …

Continue Reading ...
Repository goes Public!

Repository goes Public!

From now on everybody is able to read and fork the content in our repostiory. Be warned: it is in pre-alpha so mind your steps!

Wiki goes Public!

Wiki goes Public!

From now on everybody is able to read the content in our wiki. Be warned: the wiki content is crazy.

The kickoff meeting on 19th April 2017 set the project into motion! The official starting date is 1st of May, but we are nevertheless already setting up the activities.

Continue Reading ...

subscribe via RSS