Antonios is an environmental data scientist interested in exploring data science tools like statistical and Bayesian analysis, machine/deep learning, and explainable AI to solve challenges in environmental applications. Among others, these challenges include improving predictive skill of hydroclimate and extreme events, understanding climate teleconnections and predictability, advancing climate attribution and causal discovery, etc.
Prior to joining UVA, he worked as a research scientist at Colorado State University, where he pioneered the investigation of the fidelity of explainable AI tools for applications in the geosciences. Some of his papers have garnered international attention and have been highlighted by publishers. Examples include "A new interhemispheric teleconnection increases predictability of winter precipitation in southwestern US," published in Nature Communications; "Zonally contrasting shifts of the tropical rain belt in response to climate change," published in Nature Climate Change; and "Underestimated MJO variability in CMIP6 models,"published in Geophysical Research Letters. Antonios serves as an Associate Editor for the AMS journal "Artificial Intelligence for the Earth Systems."
Antonios holds a Ph.D. in Civil and Environmental Engineering from University of California, Irvine, and a M.Sc. in the same major from University of Patras, Greece.
Ph.D., Civil and Environmental Engineering, University of California, Irvine
M.Sc., Water Resources and Environmental Engineering, University of Patras
Diploma, Civil Engineering, University of Patras
Mamalakis, A., E.A. Barnes and I. Ebert-Uphoff, (2023) Carefully choose the baseline: Lessons learned from applying XAI attribution methods for regression tasks in geoscience, Artificial Intelligence for the Earth Systems, 2(1), https://doi.org/10.1175/AIES-D-22-0058.1.
Mamalakis, A., E.A. Barnes and I. Ebert-Uphoff, (2022) Investigation of the fidelity of explainable artificial intelligence methods in applications of convolutional neural networks in geoscience, Artificial Intelligence for the Earth Systems, 1(4), https://doi.org/10.1175/AIES-D-22-0012.1.
Mamalakis, A., I. Ebert-Uphoff and E.A. Barnes, (2022) Neural network attribution methods for problems in Geoscience: A novel synthetic benchmark dataset, Environmental Data Science, DOI: 10.1017/eds.2022.7.
Mamalakis, A., A. AghaKouchak, J.T. Randerson and E. Foufoula-Georgiou, (2022) Hotspots of Predictability: Identifying regions of high precipitation predictability at seasonal timescales from limited time series observations, Water Resources Research, 58(5), e2021WR031302.
Mamalakis, A., J.T. Randerson, J.-Y. Yu, M.S. Pritchard, G. Magnusdottir, P. Smyth, P.A. Levine, S. Yu and E. Foufoula-Georgiou (2021) Zonally contrasting shifts of the tropical rain belt in response to climate change, Nature Climate Change, 11, 143-151. https://doi.org/10.1038/s41558-020-00963-x
Le,V.V.P., C. Guilloteau, C.,A. Mamalakis and E. Foufoula-Georgiou (2021) Underestimated MJO variability in CMIP6 models, Geophysical Research Letters, 48, e2020GL092244, https://doi.org/10.1029/2020GL092244 (Top downloaded article, 2021)
Mamalakis, A. and E. Foufoula-Georgiou (2018) A multivariate probabilistic framework for tracking the intertropical convergence zone: Analysis of recent climatology and past changes, Geophysical Research Letters, doi:10.1029/2018GL079865
Mamalakis, A., J.-Y. Yu, J.T. Randerson, A. AghaKouchak, and E. Foufoula-Georgiou (2018) A new interhemispheric teleconnection increases predictability of winter precipitation in southwestern US, Nature Communications, doi: 10.1038/s41467-018-04722-7 (50 most read articles)
Mamalakis A., A. Langousis, R. Deidda and M. Marrocu (2017) A parametric approach for simultaneous bias correction and high-resolution downscaling of climate model rainfall, Water Resour. Res., doi: 10.1002/2016WR019578 (included in Editors’ highlights).
Get the latest news
Subscribe to receive updates from the School of Data Science.