Contact: ana.marza@unil.ch
Office 3239, Géopolis Building
Ana Marza is a PhD student with a background in Earth Sciences and a passion for automation. Her current research (in partnership with Bern University of Applied Sciences) uses machine learning to investigate the sources of subseasonal predictability. By sifting through large volumes of data, machine learning can, for example, discern how the state of the polar vortex today affects forecast skill one month from now. Understanding when and why subseasonal forecasts fail is important for planning ahead in sectors like renewable energy.
Publications:
Mârza, A.-C., Domeisen, D. I. V., Ramella-Pralungo, L., and Meyer, A.: Unraveling the sources of subseasonal predictability with machine learning. EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-4253, https://doi.org/10.5194/egusphere-egu25-4253, 2025.
Towards the construction of regional marine radiocarbon calibration curves: an unsupervised machine learning approach.
Marza, A.-C., Menviel, L., and Skinner, L. C., Geochronology Discuss. [preprint] doi.org/10.5194/gchron-2023-26, in review, 2023.
Urban wildflower meadow planting for biodiversity, climate and society: An evaluation at King’s College, Cambridge.
Marshall, C. A. M., Wilkinson, M. T., Hadfield, P. M., Rogers, S. M., Shanklin, J. D., Eversham, B. C., Healey, R., Kranse, O. P., Preston, C. D., Coghill, S. J., McGonigle, K. L., Moggridge, G. D., Pilbeam, P. G., Marza, A. C., Szigecsan, D., Mitchell, J., Hicks, M. A., Wallis, S. M., Xu, Z., Eves-van den Akker, S. (2023)
Ecological Solutions and Evidence, 4, e12243.
doi.org/10.1002/2688-8319.12243