Articles | Volume 19, issue 8
https://doi.org/10.5194/bg-19-2095-2022
https://doi.org/10.5194/bg-19-2095-2022
Technical note
 | 
19 Apr 2022
Technical note |  | 19 Apr 2022

Technical note: Incorporating expert domain knowledge into causal structure discovery workflows

Jarmo Mäkelä, Laila Melkas, Ivan Mammarella, Tuomo Nieminen, Suyog Chandramouli, Rafael Savvides, and Kai Puolamäki

Related authors

Exploring temporal and spatial variation of nitrous oxide flux using several years of peatland forest automatic chamber data
Helena Rautakoski, Mika Korkiakoski, Jarmo Mäkelä, Markku Koskinen, Kari Minkkinen, Mika Aurela, Paavo Ojanen, and Annalea Lohila
Biogeosciences, 21, 1867–1886, https://doi.org/10.5194/bg-21-1867-2024,https://doi.org/10.5194/bg-21-1867-2024, 2024
Short summary
Air temperature and precipitation constraining the modelled wetland methane emissions in a boreal region in Northern Europe
Tuula Aalto, Aki Tsuruta, Jarmo Mäkelä, Jurek Mueller, Maria Tenkanen, Eleanor Burke, Sarah Chadburn, Yao Gao, Vilma Mannisenaho, Thomas Kleinen, Hanna Lee, Antti Leppänen, Tiina Markkanen, Stefano Materia, Paul Miller, Daniele Peano, Olli Peltola, Benjamin Poulter, Maarit Raivonen, Marielle Saunois, David Wårlind, and Sönke Zaehle
EGUsphere, https://doi.org/10.5194/egusphere-2023-2873,https://doi.org/10.5194/egusphere-2023-2873, 2024
Short summary
Implementation and initial calibration of carbon-13 soil organic matter decomposition in the Yasso model
Jarmo Mäkelä, Laura Arppe, Hannu Fritze, Jussi Heinonsalo, Kristiina Karhu, Jari Liski, Markku Oinonen, Petra Straková, and Toni Viskari
Biogeosciences, 19, 4305–4313, https://doi.org/10.5194/bg-19-4305-2022,https://doi.org/10.5194/bg-19-4305-2022, 2022
Short summary
Improving Yasso15 soil carbon model estimates with ensemble adjustment Kalman filter state data assimilation
Toni Viskari, Maisa Laine, Liisa Kulmala, Jarmo Mäkelä, Istem Fer, and Jari Liski
Geosci. Model Dev., 13, 5959–5971, https://doi.org/10.5194/gmd-13-5959-2020,https://doi.org/10.5194/gmd-13-5959-2020, 2020
Short summary
Sensitivity of 21st century simulated ecosystem indicators to model parameters, prescribed climate drivers, RCP scenarios and forest management actions for two Finnish boreal forest sites
Jarmo Mäkelä, Francesco Minunno, Tuula Aalto, Annikki Mäkelä, Tiina Markkanen, and Mikko Peltoniemi
Biogeosciences, 17, 2681–2700, https://doi.org/10.5194/bg-17-2681-2020,https://doi.org/10.5194/bg-17-2681-2020, 2020
Short summary

Related subject area

Biogeochemistry: Air - Land Exchange
Evaluating adsorption isotherm models for determining the partitioning of ammonium between soil and soil pore water in environmental soil samples
Matthew G. Davis, Kevin Yan, and Jennifer G. Murphy
Biogeosciences, 21, 5381–5392, https://doi.org/10.5194/bg-21-5381-2024,https://doi.org/10.5194/bg-21-5381-2024, 2024
Short summary
Similar freezing spectra of particles in plant canopies and in the air at a high-altitude site
Annika Einbock and Franz Conen
Biogeosciences, 21, 5219–5231, https://doi.org/10.5194/bg-21-5219-2024,https://doi.org/10.5194/bg-21-5219-2024, 2024
Short summary
Anticorrelation of net uptake of atmospheric CO2 by the world ocean and terrestrial biosphere in current carbon cycle models
Stephen E. Schwartz
Biogeosciences, 21, 5045–5057, https://doi.org/10.5194/bg-21-5045-2024,https://doi.org/10.5194/bg-21-5045-2024, 2024
Short summary
Impact of meteorological conditions on the biogenic volatile organic compound (BVOC) emission rate from eastern Mediterranean vegetation under drought
Qian Li, Gil Lerner, Einat Bar, Efraim Lewinsohn, and Eran Tas
Biogeosciences, 21, 4133–4147, https://doi.org/10.5194/bg-21-4133-2024,https://doi.org/10.5194/bg-21-4133-2024, 2024
Short summary
Monitoring cropland daily carbon dioxide exchange at field scales with Sentinel-2 satellite imagery
Pia Gottschalk, Aram Kalhori, Zhan Li, Christian Wille, and Torsten Sachs
Biogeosciences, 21, 3593–3616, https://doi.org/10.5194/bg-21-3593-2024,https://doi.org/10.5194/bg-21-3593-2024, 2024
Short summary

Cited articles

Akaike, H.: A new look at the statistical model identification, IEEE T. Automat. Contr., 19, 716–723, https://doi.org/10.1109/TAC.1974.1100705, 1974. a
Bergmeir, C. and Benítez, J. M.: On the use of cross-validation for time series predictor evaluation, Information Sciences, 191, 192–213, https://doi.org/10.1016/j.ins.2011.12.028, 2012. a
Chickering, D. M.: Optimal Structure Identification with Greedy Search, J. Mach. Learn. Res., 3, 507–554, https://doi.org/10.1162/153244303321897717, 2003. a
Colombo, D. and Maathuis, M. H.: Order-Independent Constraint-Based Causal Structure Learning, J. Mach. Learn. Res., 15, 3741–3782, 2014. a, b
Druzdzel, M. J.: The role of assumptions in causal discovery, in: Workshop on Uncertainty Processing (WUPES-09), University of Pittsburgh, 57–68, http://d-scholarship.pitt.edu/6017/ (last access: 6 April 2022), 2009. a
Download
Short summary
Causal structure discovery algorithms have been making headway into Earth system sciences, and they can be used to increase our understanding on biosphere–atmosphere interactions. In this paper we present a procedure on how to utilize prior knowledge of the domain experts together with these algorithms in order to find more robust causal structure models. We also demonstrate how to avoid pitfalls such as over-fitting and concept drift during this process.
Altmetrics
Final-revised paper
Preprint