BISTOM - Bayesian Inference with Stochastic Models
At a glance
- Project leader : Dr. Carlo Albert, Dr. Simone Ulzega
- Deputy of project leader : Prof. Dr. Sven Hirsch
- Project status : completed
- Funding partner : Federal government
- Project partner : Eidgenössische Anstalt für Wasserversorgung, Abwasserreinigung und Gewässerschutz eawag, Swiss Data Science Center SDSC
- Contact person : Simone Ulzega
Description
In essentially all applied sciences, data-driven modeling
heavily relies on a sound calibration of model parameters to
measured data for making probabilistic predictions. Bayesian
statistics is a consistent framework for parameter inference where
knowledge about model parameters is expressed through probability
distributions and updated using measured data. However, Bayesian
inference with non-trivial stochastic models can become
computationally extremely expensive and it is therefore hardly ever
applied. In recent years, sophisticated and scalable algorithms
have emerged, which have the potential of making Bayesian inference
for complex stochastic models feasible, even for very large data
sets. We investigate the power of both Approximate Bayesian
Computation (ABC) and Hamiltonian Monte Carlo (HMC) algorithms
through a case study in SOLAR PHYSICS.
Time-series of cosmogenic radionuclides in wood and polar ice cores
are a proxy for solar magnetic activity on multi-millennial
time-scales and exhibit a number of interesting and mostly
not-yet-understood features such as stable cycles, Grand Minima and
intermittency. Solar physicists have put a lot of effort into the
development of stochastic solar dynamo models, which need to be
calibrated to the observations. Parameter inference for stochastic
dynamo models on long time-series of radionuclides is an open and
highly topical question in solar physics. Achieving more reliable
predictions of solar activity has important implications in
environmental and life sciences.
Publications
-
Ulzega, Simone; Albert, Carlo,
2022.
In:
EGU General Assembly 2022, Vienna, Austria, 23-27 May 2022.
Available from: https://doi.org/10.5194/egusphere-egu22-8729
-
Albert, Carlo; Ulzega, Simone; Ozdemir, Firat; Perez-Cruz, Fernando; Mira, Antonietta,
2022.
Learning summary statistics for Bayesian inference with autoencoders.
SciPost Physics Core.
5(3), pp. 043.
Available from: https://doi.org/10.21468/SciPostPhysCore.5.3.043
-
Albert, Carlo; Ferriz-Mas, Antonio; Gaia, Filippo; Ulzega, Simone,
2021.
Can stochastic resonance explain recurrence of Grand Minima?.
The Astrophysical Journal Letters.
916(2), pp. L9.
Available from: https://doi.org/10.3847/2041-8213/ac0fd6
-
Albert, Carlo; Gaia, Filippo; Ulzega, Simone,
2020.
Can stochastic resonance explain the amplification of planetary tidal forcing?.
In:
EGU General Assembly 2020, Online, 4-8 May 2020.
Available from: https://presentations.copernicus.org/EGU2020/EGU2020-15185_presentation.pdf
-
Albert, Carlo; Ulzega, Simone,
2020.
Stochastic resonance could explain recurrence of Grand Minima.
In:
EGU General Assembly 2020, online, 4-8 May 2020.
Available from: https://doi.org/10.5194/egusphere-egu2020-15185
-
Ulzega, Simone; Albert, Carlo,
2019.
Bayesian inference for solar dynamo models [poster].
In:
1st Swiss “Workshop on Machine Learning for Environmental and Geosciences” (MLEG2019), Dübendorf, 16-17 January 2019.
-
Ulzega, Simone; Albert, Carlo,
2019.
Bayesian inference methods for the calibration of stochastic dynamo models.
In:
4th Solar Dynamo Thinkshop, Rome, Italy, 25 - 26 November 2019.
-
Ulzega, Simone; Albert, Carlo,
2019.
Bayesian parameter inference with stochastic solar dynamo models [poster].
In:
Platform for Advanced Scientific Computing (PASC19), Zurich, 12-14 June 2019.
ZHAW Zürcher Hochschule für Angewandte Wissenschaften.
Available from: https://doi.org/10.21256/zhaw-3225
-
Albert, Carlo; Ulzega, Simone,
2019.
Can stochastic resonance explain the amplification of planetary tidal forcing?.
In:
4th Solar Dynamo Thinkshop, Rome, Italy, 25 - 26 November 2019.
-
Ulzega, Simone; Albert, Carlo,
2018.
Bayesian parameter inference with stochastic solar dynamo models.
In:
NDES 2018, 26th Nonlinear Dynamics of Electronic Systems Conference, Acireale, Italy, June, 11-13 2018.
-
2018.
Calibrating stochastic models for understanding solar activity.
Transfer.
2018(1), pp. 8.
Available from: https://doi.org/10.21256/zhaw-3851