Interactive Causal Structure Discovery in Earth System Sciences

Laila Melkas, Rafael Savvides, Suyog H. Chandramouli, Jarmo Mäkelä, Tuomo Nieminen, Ivan Mammarella, Kai Puolamäki
Proceedings of The KDD'21 Workshop on Causal Discovery, PMLR 150:3-25, 2021.

Abstract

Causal structure discovery (CSD) models are making inroads into several domains, including Earth system sciences. Their widespread adaptation is however hampered by the fact that the resulting models often do not take into account the domain knowledge of the experts and that it is often necessary to modify the resulting models iteratively. We present a workflow that is required to take this knowledge into account and to apply CSD algorithms in Earth system sciences. At the same time, we describe open research questions that still need to be addressed. We present a way to interactively modify the outputs of the CSD algorithms and argue that the user interaction can be modelled as a greedy finding of the local maximum-a-posteriori solution of the likelihood function, which is composed of the likelihood of the causal model and the prior distribution representing the knowledge of the expert user. We use a real-world data set for examples constructed in collaboration with our co-authors, who are the domain area experts. We show that finding maximally usable causal models in the Earth system sciences or other similar domains is a difficult task which contains many interesting open research questions. We argue that taking the domain knowledge into account has a substantial effect on the final causal models discovered.

Cite this Paper

BibTeX
@InProceedings{pmlr-v150-melkas21a, title = {Interactive Causal Structure Discovery in Earth System Sciences }, author = {Melkas, Laila and Savvides, Rafael and Chandramouli, Suyog H. and M\"{a}kel\"{a}, Jarmo and Nieminen, Tuomo and Mammarella, Ivan and Puolam\"{a}ki, Kai}, booktitle = {Proceedings of The KDD'21 Workshop on Causal Discovery}, pages = {3--25}, year = {2021}, editor = {Le, Thuc Duy and Li, Jiuyong and Cooper, Greg and Triantafyllou, Sofia and Bareinboim, Elias and Liu, Huan and Kiyavash, Negar}, volume = {150}, series = {Proceedings of Machine Learning Research}, month = {15 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v150/melkas21a/melkas21a.pdf}, url = {https://proceedings.mlr.press/v150/melkas21a.html}, abstract = {Causal structure discovery (CSD) models are making inroads into several domains, including Earth system sciences. Their widespread adaptation is however hampered by the fact that the resulting models often do not take into account the domain knowledge of the experts and that it is often necessary to modify the resulting models iteratively. We present a workflow that is required to take this knowledge into account and to apply CSD algorithms in Earth system sciences. At the same time, we describe open research questions that still need to be addressed. We present a way to interactively modify the outputs of the CSD algorithms and argue that the user interaction can be modelled as a greedy finding of the local maximum-a-posteriori solution of the likelihood function, which is composed of the likelihood of the causal model and the prior distribution representing the knowledge of the expert user. We use a real-world data set for examples constructed in collaboration with our co-authors, who are the domain area experts. We show that finding maximally usable causal models in the Earth system sciences or other similar domains is a difficult task which contains many interesting open research questions. We argue that taking the domain knowledge into account has a substantial effect on the final causal models discovered.} }
Endnote
%0 Conference Paper %T Interactive Causal Structure Discovery in Earth System Sciences %A Laila Melkas %A Rafael Savvides %A Suyog H. Chandramouli %A Jarmo Mäkelä %A Tuomo Nieminen %A Ivan Mammarella %A Kai Puolamäki %B Proceedings of The KDD'21 Workshop on Causal Discovery %C Proceedings of Machine Learning Research %D 2021 %E Thuc Duy Le %E Jiuyong Li %E Greg Cooper %E Sofia Triantafyllou %E Elias Bareinboim %E Huan Liu %E Negar Kiyavash %F pmlr-v150-melkas21a %I PMLR %P 3--25 %U https://proceedings.mlr.press/v150/melkas21a.html %V 150 %X Causal structure discovery (CSD) models are making inroads into several domains, including Earth system sciences. Their widespread adaptation is however hampered by the fact that the resulting models often do not take into account the domain knowledge of the experts and that it is often necessary to modify the resulting models iteratively. We present a workflow that is required to take this knowledge into account and to apply CSD algorithms in Earth system sciences. At the same time, we describe open research questions that still need to be addressed. We present a way to interactively modify the outputs of the CSD algorithms and argue that the user interaction can be modelled as a greedy finding of the local maximum-a-posteriori solution of the likelihood function, which is composed of the likelihood of the causal model and the prior distribution representing the knowledge of the expert user. We use a real-world data set for examples constructed in collaboration with our co-authors, who are the domain area experts. We show that finding maximally usable causal models in the Earth system sciences or other similar domains is a difficult task which contains many interesting open research questions. We argue that taking the domain knowledge into account has a substantial effect on the final causal models discovered.
APA
Melkas, L., Savvides, R., Chandramouli, S.H., Mäkelä, J., Nieminen, T., Mammarella, I. & Puolamäki, K.. (2021). Interactive Causal Structure Discovery in Earth System Sciences . Proceedings of The KDD'21 Workshop on Causal Discovery, in Proceedings of Machine Learning Research 150:3-25 Available from https://proceedings.mlr.press/v150/melkas21a.html.

Related Material