Articles | Volume 12, issue 5
https://doi.org/10.5194/gmd-12-1791-2019
https://doi.org/10.5194/gmd-12-1791-2019
Methods for assessment of models
 | 
06 May 2019
Methods for assessment of models |  | 06 May 2019

Efficient surrogate modeling methods for large-scale Earth system models based on machine-learning techniques

Dan Lu and Daniel Ricciuto

Related authors

A model-independent data assimilation (MIDA) module and its applications in ecology
Xin Huang, Dan Lu, Daniel M. Ricciuto, Paul J. Hanson, Andrew D. Richardson, Xuehe Lu, Ensheng Weng, Sheng Nie, Lifen Jiang, Enqing Hou, Igor F. Steinmacher, and Yiqi Luo
Geosci. Model Dev., 14, 5217–5238, https://doi.org/10.5194/gmd-14-5217-2021,https://doi.org/10.5194/gmd-14-5217-2021, 2021
Short summary
LIVVkit 2.1: automated and extensible ice sheet model validation
Katherine J. Evans, Joseph H. Kennedy, Dan Lu, Mary M. Forrester, Stephen Price, Jeremy Fyke, Andrew R. Bennett, Matthew J. Hoffman, Irina Tezaur, Charles S. Zender, and Miren Vizcaíno
Geosci. Model Dev., 12, 1067–1086, https://doi.org/10.5194/gmd-12-1067-2019,https://doi.org/10.5194/gmd-12-1067-2019, 2019
Short summary
The multi-assumption architecture and testbed (MAAT v1.0): R code for generating ensembles with dynamic model structure and analysis of epistemic uncertainty from multiple sources
Anthony P. Walker, Ming Ye, Dan Lu, Martin G. De Kauwe, Lianhong Gu, Belinda E. Medlyn, Alistair Rogers, and Shawn P. Serbin
Geosci. Model Dev., 11, 3159–3185, https://doi.org/10.5194/gmd-11-3159-2018,https://doi.org/10.5194/gmd-11-3159-2018, 2018
Short summary
Bayesian calibration of terrestrial ecosystem models: a study of advanced Markov chain Monte Carlo methods
Dan Lu, Daniel Ricciuto, Anthony Walker, Cosmin Safta, and William Munger
Biogeosciences, 14, 4295–4314, https://doi.org/10.5194/bg-14-4295-2017,https://doi.org/10.5194/bg-14-4295-2017, 2017
Short summary

Related subject area

Climate and Earth system modeling
Technology to aid the analysis of large-volume multi-institute climate model output at a central analysis facility (PRIMAVERA Data Management Tool V2.10)
Jon Seddon, Ag Stephens, Matthew S. Mizielinski, Pier Luigi Vidale, and Malcolm J. Roberts
Geosci. Model Dev., 16, 6689–6700, https://doi.org/10.5194/gmd-16-6689-2023,https://doi.org/10.5194/gmd-16-6689-2023, 2023
Short summary
A diffusion-based kernel density estimator (diffKDE, version 1) with optimal bandwidth approximation for the analysis of data in geoscience and ecological research
Maria-Theresia Pelz, Markus Schartau, Christopher J. Somes, Vanessa Lampe, and Thomas Slawig
Geosci. Model Dev., 16, 6609–6634, https://doi.org/10.5194/gmd-16-6609-2023,https://doi.org/10.5194/gmd-16-6609-2023, 2023
Short summary
Monte Carlo drift correction – quantifying the drift uncertainty of global climate models
Benjamin S. Grandey, Zhi Yang Koh, Dhrubajyoti Samanta, Benjamin P. Horton, Justin Dauwels, and Lock Yue Chew
Geosci. Model Dev., 16, 6593–6608, https://doi.org/10.5194/gmd-16-6593-2023,https://doi.org/10.5194/gmd-16-6593-2023, 2023
Short summary
Improvements in the Canadian Earth System Model (CanESM) through systematic model analysis: CanESM5.0 and CanESM5.1
Michael Sigmond, James Anstey, Vivek Arora, Ruth Digby, Nathan Gillett, Viatcheslav Kharin, William Merryfield, Catherine Reader, John Scinocca, Neil Swart, John Virgin, Carsten Abraham, Jason Cole, Nicolas Lambert, Woo-Sung Lee, Yongxiao Liang, Elizaveta Malinina, Landon Rieger, Knut von Salzen, Christian Seiler, Clint Seinen, Andrew Shao, Reinel Sospedra-Alfonso, Libo Wang, and Duo Yang
Geosci. Model Dev., 16, 6553–6591, https://doi.org/10.5194/gmd-16-6553-2023,https://doi.org/10.5194/gmd-16-6553-2023, 2023
Short summary
Earth System Model Aerosol–Cloud Diagnostics (ESMAC Diags) package, version 2: assessing aerosols, clouds, and aerosol–cloud interactions via field campaign and long-term observations
Shuaiqi Tang, Adam C. Varble, Jerome D. Fast, Kai Zhang, Peng Wu, Xiquan Dong, Fan Mei, Mikhail Pekour, Joseph C. Hardin, and Po-Lun Ma
Geosci. Model Dev., 16, 6355–6376, https://doi.org/10.5194/gmd-16-6355-2023,https://doi.org/10.5194/gmd-16-6355-2023, 2023
Short summary

Cited articles

Agarap, A. F. M.: Deep learning using Rectified Linear Units (ReLU), https://arxiv.org/pdf/1803.08375 (last access: 7 February 2019), 2018. 
Archambeau, C., Valle, M., Assenza, A., and Verleysen, M.: Assessment of probability density estimation methods: Parzen window and finite Gaussian mixtures, IEEE, ISCAS 2006, 21–24 May 2006, Island of Kos, Greece, https://doi.org/10.1109/ISCAS.2006.1693317, 2006. 
Bardenet, R. and Kegl, B.: Surrogating the surrogate: accelerating Gaussian-process-based global optimization with a mixture cross-entropy algorithm, in: International Conference on Machine Learning, 21–24 June 2010, Haifa, Israel, 55–62, 2010. 
Basu, A., De, S., Mukherjee, A., and Ullah, E.: Convergence guarantees for rmsprop and adam in nonconvex optimization and their comparison to nesterov acceleration on autoencoders, arXiv preprint arXiv:1807.06766, available at: https://arxiv.org/abs/1807.06766 (last access: 10 March 2019), 2018. 
Bergstra, J. and Bengio, Y.: Random search for hyper-parameter optimization, J. Mach. Learn. Res., 13, 281–305, 2012. 
Download
Short summary
This work uses machine-learning techniques to advance the predictive understanding of large-scale Earth systems.