DATALAKES

Heterogeneous data platform for operational modelling and forecasting of Swiss lakes

Started
February 1, 2019
Status
Completed
Share this project

Abstract

The objective of this project is to advance the forecasting capabilities of the data-driven hydrological and ecological lake modeling algorithms using methodologies inspired by data science and accelerated by high performance computing.

We aim to develop a parallel framework interfacing high resolution 3D numerical solvers for the underlying lake dynamics with modern numerical Markov Chain Monte Carlo sampling methods for Bayesian inference, with particular interest in investigating particle filtering and multi-level variance reduction methodologies. The resulting framework aims at accurate data assimilation and uncertainty quantification in both model parameters and the associated forecasts.

DATALAKES project is a collaboration with the Swiss Data Science Center (SDSC), EPF Lausanne and ETH Zurich, aiming at a sensor-to-frontend data platform providing and analyzing the dynamics of lake ecosystems at high spatial and temporal resolutions. Current version of the existing framework can be found at meteolakes.ch.

People

Collaborators

SDSC Team:
Eric Bouillet
Firat Ozdemir
Fotis Georgatos
Emma Jablonski
Fernando Perez-Cruz

PI | Partners:

Eawag, Scientific Computing Group:

  • Dr. Jonas Sukys
  • Dr. Artur Safin
  • James Runnalls

More info

Eawag, Aquatic Physics:

  • Dr. Damien Bouffard

More info

EPFL, Aquatic Systems Laboratory:

  • Prof. Dr. Alfred Johny Wüest

More info

description

Problem

  • Increasing pressure on lakes needs scientific support
  • 3D numerical simulations of lakes require input data – uncertainty quantification in parameters & forecast
  • New L’EXPLORE platform in Lake Geneva – increasing availability of high resolution data

Solution

  • Sensor-to-frontend open data platform
  • Physics-driven hydrodynamic models
  • Data-driven modeling of input data processes
  • Parallel Bayesian inference – MCMC with ABC or PF
  • Multi-level speedup – hierarchical numerical models
  • Powered by Renku, the SDSC-developed platform for transparency and reproducibility in science
  • A neural network with uncertainty quantification properties in order to more accurately aggregate data from satellite imagery into the Bayesian inference

Impact

  • Real time monitoring & future forecast of lakes
  • Platform for large-scale interdisciplinary collaborations
  • Research in hydrological / ecological lake modeling
  • Scientifically grounded water resources management

Gallery

Annexe

Bibliography

Publications

Tagasovska, N.; Ozdemir, F.; Brando, A.; Ruiz, F.; Dy, J.; van de Meent, J. "Retrospective Uncertainties for Deep Models using Vine Copulas" Proceedings of The 26th International Conference on Artificial Intelligence and Statistics 206 7528–7539 2023 View publication
Safin, A.; Bouffard, D.; Ozdemir, F.; Ramon, C. L.; Runnalls, J.; Georgatos, F.; Minaudo, C.; Šukys, J. "A Bayesian data assimilation framework for lake 3D hydrodynamic models with a physics-preserving particle filtering method using SPUX-MITgcm v1" Geoscientific Model Development 15 20 7715-7730 2022 View publication
Safin, A.; Bouffard, D.; Runnalls, J.; Georgatos, F.; Bouillet, E.; Ozdemir, F.; Perez Cruz, F.; Šukys, J. "Data assimilation in lake Geneva using the SPUX framework" EGU General Assembly Conference Abstracts 19564 2020 View publication

Related Pages

More projects

ALBUM

In Progress
Automated Large-scale Brain Ultrastructure Mapping
Academia

AICADES

In Progress
AI-supported cancer data extraction for population health monitoring and research
Academia

IICU National Data Stream

In Progress
Personalized, data-driven prediction and assessment of infection-related outcomes in Swiss intensive care units (ICUs)
Academia
Public sector

SMARTT

In Progress
Smart sampling for small-angle x-ray scattering Tensor Tomography
Academia

More projects

No results found.
There are no results with this criteria. Try changing your search.
No result

News

Latest news

Quand l’IA soutient l’économie du canton de Vaud, la santé et l’environnement
October 27, 2026

Quand l’IA soutient l’économie du canton de Vaud, la santé et l’environnement

Quand l’IA soutient l’économie du canton de Vaud, la santé et l’environnement

Cinq projets soutenus par le canton de Vaud et réalisés avec le Swiss Data Science Center (SDSC) livrent leurs résultats après un an de
Elevating International Geneva's Impact with AI
October 21, 2026

Elevating International Geneva's Impact with AI

Elevating International Geneva's Impact with AI

Two AI projects have been selected for funding through the 2026 Geneva AI Initiative, run by the EPFL AI Center with the SDSC.
12 Zurich SMEs join next AI Innovation Program
October 15, 2026

12 Zurich SMEs join next AI Innovation Program

12 Zurich SMEs join next AI Innovation Program

Strong results encourage further AI exploration to simplify operations and boost the competitiveness of SMEs in the Canton of Zurich.

Contact us

Would you like to explore how we can work together?

Our team of data scientists and professionals looks forward to engaging in impactful, results-driven collaborations with you.