PhD Student · Università del Salento

Emanuele Donno

Working on Quantum Machine Learning

Computer Engineer exploring how quantum computing and machine learning can help us understand — and forecast — a changing climate.

Portrait of Emanuele Donno Quantum ML Climate AI
4

Publications & preprints

18

Months of climate-AI research at CMCC

7

Selected projects, from HPC to full-stack

9

Certifications & awards

About me

Nice to meet you 👋

I'm a licensed Computer Engineer and a PhD student in Engineering of Complex Systems at the University of Salento, where I research Quantum Computing and Quantum Machine Learning approaches for climate science.

Before the PhD I spent about 18 months as a Post-Degree Researcher at the Euro-Mediterranean Centre on Climate Change (CMCC), building end-to-end ML/DL pipelines on multidimensional climate datasets and contributing to ML4Fires, the wildfire-forecasting module of the EU interTwin Digital Twin project, trained at scale on HPC.

My path started in Physics, moved on to Information and Computer Engineering and, along the way, picked up a full-stack toolbox: Python, Java/Spring Boot, Angular/Ionic, Docker and MPI. Born and raised in Lecce, I love meeting new people, and away from the keyboard you'll find me playing chess or lost in a good book.

  • Based inLecce, Italy
  • CurrentlyPhD, Engineering of Complex Systems
  • LicensedOrder of Engineers of Lecce, since 2024
  • LanguagesItalian (native) · English (B2, IELTS 6.0)
  • Off-screenChess, reading, good company
Journey

Experience & education

From physics lectures to supercomputers and qubits.

2024 — PresentEducation

PhD in Engineering of Complex Systems

Università del Salento — Lecce, Italy

Research project: Quantum Computing and Quantum Machine Learning approaches for Climate Change applications, including quantum data assimilation.

06/2023 — 11/2024Experience

Post-Degree Researcher

CMCC Foundation — Advanced Scientific Computing (ADIC) Division, Lecce
  • Worked on ML4Fires, the wildfire-forecasting module of the EU interTwin project (GA 101058386), part of the Environmental Digital Twin Engine for global wildfire propagation and projection.
  • Built end-to-end ML/DL pipelines (data preparation, feature engineering, training, evaluation) for CNN, U-Net and U-Net++ on the SeasFire Cube v3 datacube (NetCDF/Xarray) and CMIP6 SSP projections.
  • Helped migrate the training stack from TensorFlow to PyTorch, running multi-node, multi-GPU distributed training and containerized inference on HPC.
  • Adopted MLflow for experiment tracking and reproducibility.
  • PyTorch
  • HPC
  • Digital Twins
  • MLflow
  • NetCDF
2019 — 2023Education

M.Sc. in Computer Engineering 105/110

Università del Salento — Lecce, Italy

Thesis: Global downscaling of remotely sensed soil-moisture retrievals using Machine Learning. Courses in High Performance Computing, Computer Vision and Parallel Algorithms sparked my passion for Machine Learning; Robotics, IoT and Network Technologies showed me how far it can reach.

2016 — 2019Education

B.Sc. in Information Engineering 97/110

Università del Salento — Lecce, Italy

Thesis: Design and development of a back-end subsystem for an event-management service (Spring Boot REST).

2013 — 2016Education

Physics

Dept. of Mathematics and Physics “Ennio De Giorgi”, Lecce

Where I grew some of the soft skills that define me most: teamwork and communication.

2008 — 2013Education

Scientific High School

Liceo Scientifico “Cosimo De Giorgi”, Lecce
Research

Publications & preprints

Where classical and quantum computing meet climate science.

Quantum Machine Learning Quantum Data Assimilation Digital Twins Wildfire Forecasting HPC & Distributed Training
2026
First authorPreprint · Under review

From Classical to Quantum-Mechanical Data Assimilation: A Comparison between DATO and QMDA

E. Donno, G. Conti, P. Oddo, S. Gualdi, L. Mainetti, G. Aloisio
Submitted to Future Generation Computer Systems (FGCS), Special Collection on Advances in Quantum Computing: Methods, Algorithms, and Systems, Vol. III
arXiv
2026
Journal article

interTwin: Advancing Scientific Digital Twins through AI, Federated Computing and Data

Co-author
Future Generation Computer Systems (FGCS) — The International Journal of eScience
DOI
2025
EGU General Assembly

Facilitating the development of Machine Learning-based Digital Twin applications for extreme weather events

D. Elia, E. Donno, M. Bunino, M. Fronza, D. Donno, G. Padovani, S. Fiore, A. Manzi
EGU General Assembly 2025
DOI
2024
EGU General Assembly

A Data Space environment for Big Data and ML-based Climate applications in the European Open Science Cloud

D. Elia, F. Antonio, S. Fiore, E. Donno, G. Accarino, P. Nassisi, G. Aloisio
EGU General Assembly 2024
DOI
Projects

Selected work

From global-scale climate models to full-stack platforms and parallel algorithms.

Global Soil-Moisture Downscaling

ML-based downscaling of satellite-derived soil-moisture products on the EASE 2.0 grid, with pipelines for multidimensional Earth-observation datasets.

  • Machine Learning
  • Remote Sensing
  • NetCDF
  • Xarray
  • PyTorch

Social Tech Platform

LinkedIn-style multi-user platform: Angular + Ionic frontend, Spring Boot REST backend, Firebase for push and bulk notifications. End-to-end ownership, from architecture to deployment.

  • Angular
  • Spring Boot
  • Ionic
  • Firebase
  • REST

MAD — My Accessible Data

Multi-user system for secure personal-data management using IOTA's Masked Authenticated Messaging (MAM) over the Tangle; Angular/Ionic frontend, Spring Boot REST backend.

  • Blockchain
  • IOTA
  • IoT
  • Java
  • Angular

Drupal Plugin for Remote Learning

Drupal content-management plugin backed by a Spring Boot service over a materialized-table relational schema, with an Angular web client and stored procedures for data exchange between backends.

  • Drupal
  • Spring Boot
  • MySQL
  • Angular

Parallel Fast Hartley Transform

Parallel design and implementation of the one-dimensional Fast Hartley Transform (FHT) using the MPICH message-passing library.

  • C
  • MPI
  • Parallel Computing

COVID-19 Spread Modeling

Polynomial and multivariate regression plus Kalman filtering applied to COVID-19 spread, modeled with the SIR compartmental model.

  • Python
  • Data Analysis
  • SciPy
  • Scikit-Learn
Skills

Toolbox

The languages, frameworks and tools I reach for.

AI & ML

  • PyTorch
  • TensorFlow
  • Keras
  • Scikit-Learn
  • Computer Vision
  • Distributed training
  • MLflow

Quantum (PhD)

  • Qiskit
  • PennyLane
  • Quantum Circuits
  • Quantum ML
  • Quantum Data Assimilation

Languages

  • Python
  • Java
  • TypeScript
  • C
  • SQL
  • Shell/Bash
  • Matlab
  • LaTeX

LLM & GenAI (personal projects)

  • Ollama
  • Hugging Face
  • RAG
  • Prompt engineering
  • Claude Code
  • ChatGPT
  • Gemini

Backend & Infra

  • Spring Boot
  • REST APIs
  • Docker
  • Git
  • MPI/MPICH
  • HPC
  • Linux/Unix

Data & Storage

  • NumPy
  • Pandas
  • NetCDF
  • Xarray
  • Cartopy
  • MySQL
  • MongoDB
  • SQLite

Frontend

  • Angular
  • Ionic
  • TypeScript
  • HTML5/CSS
  • Bootstrap
  • Firebase

Tools

  • VS Code
  • JetBrains IDEs
  • Jupyter
  • Google Colab
  • Postman
  • CoppeliaSim
  • Draw.io
  • Balsamiq
Certifications & awards

Always learning

Jun 2026

Large Language Models (LLMs) Concepts

DataCamp

Jun 2026

Introduction to FastAPI

DataCamp

Jun 2026

Introduction to Power BI

DataCamp

May 2026

Quantum Machine Learning with Python & Qiskit

IBM SkillsBuild

Sep 2025

JUNIQ-EPIQ Summer School on Quantum Computing

Forschungszentrum Jülich — gate-based algorithms and quantum annealing

Jun 2024

Professional Engineering License

Order of Engineers of Lecce — Sec. A, Sector C

May 2022

ICIAP 2021

21st International Conference on Image Analysis and Processing

Jul 2019

IELTS Academic

Overall 6.0/9.0 — CEFR B2

Mar 2019

Samsung Innovation Camp

Innovation & Technology, Business Strategy, Digital Marketing

Contact

Let's build something,
classical or quantum.

Open to research collaborations, talks and interesting problems in ML, HPC and quantum computing.