|Publication type:||Conference poster|
|Type of review:||Peer review (abstract)|
|Title:||Bayesian inference for solar dynamo models|
|Conference details:||1st Swiss “Workshop on Machine Learning for Environmental and Geosciences” (MLEG2019), Dübendorf, 16-17 January 2019|
|Subject (DDC):||003: Systems |
|Abstract:||Bayesian statistics allows us to express domain knowledge about model parameters as a probability distribution and, by means of Bayes’ theorem, to update this knowledge using measured data. It is thus a perfect example of interpretable data science and a proven tool for making probabilistic predictions. It forces us to conceptualize our knowledge about the system, the measurement process and the dominant sources of uncertainty in the form of a stochastic model for the measured data. Bayesian inference is almost never consistently applied in connection with non- trivial stochastic models, because it is computationally extremely expensive. In recent years, sophisticated and scalable algorithms have emerged, which have the potential of making Bayesian inference for complex stochastic models feasible, even for large data sets. It is the primary goal of this SDSC project to explore the potential of these algorithms and to make them accessible to researchers from various domains. The Bayesian inference algorithms we apply fall into two classes: Approximate Bayesian Computation (ABC) and Hamiltonian Monte Carlo (HMC). While the former class is technically easy to apply but yields only approximate results, the latter requires much more tailoring to a particular problem, but has the potential of yielding exact results. The basic idea behind ABC is to compress data into a few so-called summary statistics and accept or reject model parameters depending on how well associated model outputs (pseudo-data generated via model forward simulation) comply with the (real) data in terms of these statistics . Today, ABC is used in many domains, but little is known as to (i) how the summary statistics should be chosen and (ii) how accurate the inference results are. In this project, we’re using machine learning tools for the generation of summary statistics and compare the inference results to exact results generated with HMC. The basic idea behind HMC is to re-interpret the Bayesian posterior as the partition function of an interacting particle system and use the tools of Statistical Physics to calculate it efficiently . We will show first results from an application in solar physics, where we’re trying to infer parameters of the solar dynamo from time-series of radionuclides (recorded in tree rings and ice cores), which are a proxy for solar activity.|
|Fulltext version:||Published version|
|License (according to publishing contract):||Licence according to publishing contract|
|Departement:||Life Sciences and Facility Management|
|Organisational Unit:||Institute of Computational Life Sciences (ICLS)|
|Published as part of the ZHAW project:||BISTOM - Bayesian Inference with Stochastic Models|
|Appears in collections:||Publikationen Life Sciences und Facility Management|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.