Now open for application
Closed for application
CU41.CU-Alpha.04

Multi - risk methods for assessing climate resilience and impacts on socio - ecological systems

  • Reference person
    Andrea
    Critto
    critto@unive.it
  • Host University/Institute
    Università Ca’ Foscari di Venezia
  • Internship
    N
  • Research Keywords
    Multi-hazard risk
    Machine Learning and Explainable AI
    Climate Resilience
  • Reference ERCs
    SH7_6 Environmental and climate change, societal impact and policy
    PE4_18 Environment chemistry
    PE6_11 Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)
  • Reference SDGs
    GOAL 11: Sustainable Cities and Communities
    GOAL 13: Climate Action
    GOAL 15: Life on Land
  • Studente
  • Supervisor
  • Co-Supervisor

Description

Climate change is intensifying the frequency and severity ofnatural hazards such as heatwaves, droughts, floods, sea level rise, leading toincreasingly complex multi-hazard scenarios. The growing interconnectivity ofsocio-economic and environmental systems is further amplifying risks, withcascading effects that may lead into high-impact crises. At the same time, theincreased availability of big data (e.g., Earth Observations, social media,climate projections, environmental monitoring) and advancements in artificialintelligence (AI) are transforming risk assessment, enabling deeper insightsinto hazard interactions. However, there are still major challenges inunderstanding multi-risk dynamics, in particular with regards to the analysisof changes in vulnerability due to multi-hazard events and the modelling ofcascading impacts across multiple scales and sectors. Network Science providesa framework for modelling how systemic risks propagate across interconnectedsystems, identifying critical vulnerabilities and allowing for proactiveresilience planning. This research topic aims at investigating systemic riskmodelling, data science and AI, developing transferable multi-riskmethodologies across scales and sectors, to unlock sustainable adaptation andresilience strategies.

Suggested skills:

The ideal candidate should have a strong background inenvironmental sciences and/or statistics, with expertise in climate change riskassessment, data science, machine learning, or network science for analyzinghazard interactions. Experience with geospatial analysis (GIS, remote sensing,Earth Observations data) is highly desirable. Proficiency in Python, R, orMATLAB is essential, along with knowledge of machine learning (Neural networks,Bayesian Networks, …), agent-based models, or Explainable AI (e.g., SHAPvalues). The candidate should possess strong analytical, interdisciplinary, andcommunication skills, with fluency in English.

Research team and environment

We will make available to the PhD fellow the labs, tools andinfrastructures of the CMCC@Ca’Foscari, a strategic partnership betweenCa’Foscari University of Venice and CMCC Foundation. Our multidisciplinaryresearch team includes environmental scientists, climatologists, economists,conducting national and international research on the interaction betweenclimate, environment, economy, society. The fellow will benefit from CMCC’scomputational infrastructure and will be provided with a workstation (equippedwith PC, printer, Wi-Fi access, etc.); access to University Libraries; apersonal e-mail; access to online scientific journals, and access tointernational and EU professional databases.