Research that
reaches practice.

Apter grows out of applied research on climate risk, emergencies and AI, and we carry what it finds into our courses and into how we test AI agents.

What we research

Three lines of work.

Decisions under uncertainty

How coastal and emergency managers decide when the hazard, the data and the future are all uncertain, including deep reinforcement learning for emergency response.

Compound and multi-hazard risk

How hazards combine, such as a storm surge on top of a river flood, and how to assess risks that arrive together.

Evaluating AI agents for professional work

How to judge whether an agent’s output is good enough for a given kind of work. It is the method behind the line we set for each task.

Publications

Selected papers.

Research by Marcello Sano with university and research partners. Affiliations as published.

Full list on Google Scholar

  1. 2026

    GNN-Based Deep Reinforcement Learning for Coastal Emergency Response under Extreme Water Levels

    Sano, M., Casagrande, S., Ferrario, D., Vascon, S., Torresan, S., and Critto, A.

    Tackling Climate Change with Machine Learning workshop, NeurIPS 2026, Sydney, Australia, 11 December 2026Peer-reviewed workshop paper, accepted

  2. 2026

    A deep reinforcement learning framework for coastal multi-hazard emergency response

    Sano, M., Ferrario, D. M., Torresan, S., and Critto, A.

    International Journal of Disaster Risk Reduction, 145, 106439

    doi:10.1016/j.ijdrr.2026.106439

  3. 2026

    Harnessing data-driven methods for climate multi-hazard and multi-risk assessment

    Ferrario, D. M., Sanò, M., Maraschini, M., Critto, A., & Torresan, S.

    Natural Hazards and Earth System Sciences, 26(6), 2975-3024

  4. 2025

    Prioritise risks and improve adaptation strategies in the Veneto coast through the application of a custom AI tool

    Dal Barco, M. K., Casartelli, V., Sanò, M., Vascon, S., Torresan, S., and Critto, A.

    International Journal of Disaster Risk Reduction, 130, 105818

  5. 2024

    Sensitivity analysis for a participatory approach to enhance the climate resilience of Venice, Italy

    Sambo, B., Sano, M., Sperotto, A., Zanetti, M., Torresan, S., Lambert, J. H., and Critto, A.

    Risk Analysis, 44 (7), 1573-1585

  6. 2023

    Status of global coastal adaptation

    Magnan, A. K., Bell, R., Duvat, V. K. E., Ford, J. D., Garschagen, M., Haasnoot, M., Lacambra, C., Losada, I. J., Mach, K. J., Noblet, M., Parthasarathy, D., Sano, M., Vincent, K., Anisimov, A., Hanson, S., Malmström, A., Nicholls, R. J., and Winter, G.

    Nature Climate Change, 13, 1213–1221

    doi:10.1038/s41558-023-01834-x

  7. 2015

    Coastal vulnerability and progress in climate change adaptation: an Australian case study

    Sanò M., Gainza J., Baum S., Low Choy D., Serrao-Neumann, S., Tomlinson R.

    Regional Studies in Marine Science Volume 2, November 2015, Pages 113–123

  8. 2013

    Bayesian belief modeling of climate change impacts for informing regional adaptation options

    Richards R., Sanò, M., Roiko, A., Carter, R.W., Bussey, M., Matthews, J., Smith, T.F.

    Environmental Modelling & Software Volume 44, June 2013, Pages 113–121

Method notes

In preparation

How we set a line for a new kind of task

How we choose the criteria, the line and the sign-off for work we have not assessed before.

Where it goes