(2A) Foundation models for anomaly detection of ionospheric phenomena and correlation with seismo-induced events (CUP -)
Funding institution: Fondazione Bruno Kessler - FBK
Doctoral site: Fondazione Bruno Kessler - FBK
Contact: Andrea Di Luca [adiluca@fbk.eu]
Funds: Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
The Limadou project gathers some Italian institutions participating in the China Seismo Electromagnetic Satellite (CSES) mission. CSES consists of a constellation of satellites, designed to pursue the deepest campaign of observation of the ionosphere. One of the most important scientific goals of the mission is to look for correlations between transient phenomena in the ionosphere and seismic events. The successful candidate will develop and apply state-of-the-art machine learning techniques to enhance the detection of ionospheric anomalies and their potential correlations with seismic activities. In particular, the research will focus on employing foundation models that can interpret complex patterns in space and time observations. Candidates with a strong background in data science, machine learning, and space physics are encouraged to apply. This position offers the opportunity to work with leading experts and institutions, including collaborations with INFN-TIFPA and Fondazione Bruno Kessler.
Intellectual Property Notice for PhD candidates under the UniTrento-FBK Agreement
Please read the following information carefully before submitting your application.
Intellectual Property of Research Results. The intellectual property rights of research results generated by PhD students under scholarships within the UniTrento-FBK Agreement shall belong to FBK.
Transfer of Intellectual Property Rights. FBK will establish agreements with PhD students regarding the transfer of intellectual property rights related to their research results.
Collaboration with UniTrento. If UniTrento academic staff contribute to research results obtained through PhD scholarships funded by FBK, the determination of IP shares will be defined through separate written agreements based on each party’s contribution. PhD students are required to collaborate with UniTrento in all necessary activities related to the joint management of IP.
(2B) Development of space weather tools using the CSES1/2 Constellation (CUP -)
Funding institution: Istituto Nazionale di Geofisica e Vulcanologia - INGV
Doctoral site: Istituto Nazionale di Geofisica e Vulcanologia – INGV, Roma section
Contact: Marco Cristoforetti [mcristofo@fbk.eu]
Funds: Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
Space weather forecasting using data from the CSES1/2 constellation. The Sino-Italian constellation, comprising the CSES1 and CSES2 satellites – which have been operating in pair since 2025 and as individual satellites since 2018 – provides a large amount of high-precision data on: the magnetic field (static and low-frequency), electric field (static and low-frequency), trapped particles and plasma to develop forecast models and enhance Space Weather services. In particular, the data from CSES2 are collected across the entire polar orbit, reaching high latitudes which are particularly sensitive to disturbances of heliospheric origin. These are unique data of their kind which will contribute both to space weather forecasting and to the warning systems developed within the context of the INGV’s Centre for Space-based Earth Observations (COS).
(2C) Characterisation of Solar Energetic Events through the Analysis of Multiband Time Series and Images from Ground-based and Space Observations (CUP C53C23001330005)
Funding institution: Istituto Nazionale di Astrofisica - INAF
Doctoral site: Istituto Nazionale di Astrofisica - INAF, Osservatorio Astronomico di Trieste
Contact: Valentina Alberti [valentina.alberti@inaf.it]
Funds: Project Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
This project focuses on the development of advanced techniques for analysing time series data to extract meaningful physical information about energetic solar events. By leveraging temporal variability, these methods enable the identification of underlying processes, characteristic timescales, and dynamics of the solar atmosphere. Complementing this approach, multiband imaging provides crucial spatial context, allowing for the localisation and morphological interpretation of the observed phenomena. The combined use of time series analysis and imaging thus offers a more comprehensive understanding of solar activity, enhancing our ability to interpret complex events through both their temporal evolution and spatial structure.
(2D) Study of lithospheric deformations using imaging and non-imaging satellite data (CUP I53D24000060005)
Funding institution: University of Siena
Doctoral site: University of Siena
Contact: Riccardo Salvini [riccardo.salvini@unisi.it]
Funds: Project Funds / Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
Given the rapid technological evolution of space missions for Earth observation and the ongoing climate changes, the research project proposes the use of satellite data, combined with field checks and available geophysical databases, for the study of geological processes from the space. In particular, the study of seismic and volcanic activities, as well as gravitational events, will be carried out through satellite techniques using optical passive images (RGB, multispectral and hyperspectral, mono and stereoscopic), active scenes (i.e., SAR) and emitters of opportunity. Furthermore, non-imaging data will be used to analyze the relationships between lithospheric deformations and the rapid variation of ionospheric and magnetospheric parameters.
(2E) Study on the use of new observation technologies from space for spatially explicit estimation of forest variables (CUP F63C25000370005)
Funding institution: Agenzia Spaziale Italiana - ASI
Doctoral site: University of Florence
Contact: Gherardo Chirici [gherardo.chirici@unifi.it]
Funds: Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
Technological advancement in the field of observation from space now makes available more and more data sources with increasing spatial resolution, temporal frequency, and spectral and radiometric detail, whether passive (multi or hyperspectral) or active (radar) technologies. On the other hand, the source of data for deriving official estimates of descriptive variables of forest ecosystems (extent, biomass, pollutant removal, biodiversity) and their dynamics over time are based on traditional forms of ground surveys based on formal statistical sampling plans. The theme of the doctoral project is the development of modern systems for spatially explicit estimation of these forest variables by integrating ground surveys with multi-sensor remote sensing imagery, such as that acquired by the IRIDE satellite system, with machine learning and artificial intelligence algorithms. These methods may in the future provide an innovative new approach for developing new forest monitoring systems, including in the context of climate change scenarios.
(2F) Solar Storm Tracking Models for the Moon and Mars (METEOLEM) (CUP F63C26000380001)
Funding institution: Italian Space Agency - ASI
Doctoral site: University of Calabria - UNICAL
Contact: Sergio Servidio [sergio.servidio@fis.unical.it]
Funds: Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
The PhD project "Solar Storm Tracking Models for the Moon and Mars" (METEOLEM) aims to develop a predictive system for solar energetic particle (SEP) risk assessment in view of human exploration of the Moon and Mars. The project addresses this issue through a multiscale and interdisciplinary approach that integrates solar physics, heliospheric plasma physics, and turbulence theory. Using the PLUTO MHD code, a coronal mass ejection (CME) will be simulated to characterize magnetic reconnection processes responsible for particle acceleration, defining the source region, spectral distribution, and initial anisotropy. These data then serve as input for the EUHFORIA code, where magnetic field line tracking techniques determine the connectivity between the CME source region and the Moon and Mars, identifying the potentially most exposed areas. The critical breakthrough involves incorporating a sub-grid magnetic turbulence model into field line tracking, using Monte Carlo techniques to simulate random walk and pitch-angle scattering. Realistic turbulence spectra and diffusion coefficients yield probabilistic particle flux distributions on lunar and Martian surfaces, accounting for both large-scale connectivity and micro-turbulence diffusion. The final output comprises risk maps for extreme CME events, quantifying the probability of >10 MeV proton radiation lethal to astronauts and damaging to extraterrestrial infrastructure. The project links CME simulations with turbulence models for SEP forecasting, producing operational risk maps directly usable by ASI and ESA for mission planning and crew safety, and will benefit from research periods at KU Leuven and other research centers.
Positions reserved for candidates of Kenyan nationality
(2KA) Generative AI for Space Weather Nowcasting (CUP F63C26000230005)
Funding institution: Italian Space Agency - ASI
Doctoral site: Fondazione Bruno Kessler - FBK
Contact: Marco Cristoforetti [mcristofo@fbk.eu]
Funds: Institutional Funds
Mobility abroad: compulsory, minimum 6 months
Periods in companies/research centres/public administrations: optional
Solar activity can severely disrupt GNSS positioning, aviation communications, and power grids by perturbing the Earth's ionosphere. Forecasting these disturbances at short lead times is an open and practically relevant problem: physics-based models are hard to adopt for responding during rapidly evolving geomagnetic storms, and simple data extrapolation breaks down exactly when it matters most.
Approaches based on AI, developed for precipitation nowcasting, have strong potential for adaptation, e.g., to ionospheric Total Electron Content maps, available as globally gridded products updated every 15 minutes. The core challenge is that ionospheric dynamics are driven by external solar forcing with no meteorological analog, requiring the model to integrate multimodal inputs to anticipate the onset and spatial evolution of ionospheric storms.
The successful candidate will work at the intersection of deep learning and space physics, in close collaboration with FBK researchers.