Head of Simulation and Data Lab (Jülich Supercomputing Centre)
Associate Professor (University of Iceland)

Prof. Gabriele Cavallaro

Let’s connect on LinkedIn

Remote Sensing

High Performance Computing

Machine Learning

Quantum Computing

Affiliations

Head of Simulation and Data Lab "AI and ML for Remote Sensing" Jülich Supercomputing Centre

Associate Professor, Faculty of Electrical and Computer Engineering

Visiting Professor, Φ-Lab, European Space Agency

Co-Chair of the IEEE Iceland Section

Read my CV

Research Topics

Remote Sensing

—

High Performance Computing

—

Machine Learning

—

Quantum Computing

Guest lectures, presentations, workshops

Talks

All talks

Next-Generation Supercomputing: Europe’s Ecosystem for AI in the Exascale Era

Read article

ESA Phinnovation Summit

Next-Generation Supercomputing: Europe’s Ecosystem for AI in the Exascale Era

Supercomputing combines thousands of interconnected CPU- and GPU-based nodes with large-scale memory, high-speed networks, and specialized storage, acting as a scientific instrument that enables massive simulations, data-intensive analysis, and AI workloads to address complex challenges in physics, chemistry, medicine, energy, climate change and Earth observation.

2026

High Performance Embedded Architectures and Compilers (HiPEAC)

Quantum Computing for Earth Observation:Searching for Quantum Advantage

2026

Cremona (Italy)

Erasmus+ BIP Machine Learning for Earth Observation and Data Fusion

2025

ESA-NASA International Workshop on AI Foundation Model for EO (ESA-ESRIN, Frascati, Italy)

Next-Generation Supercomputing In Europe: A Community in Action Advancing Hardware, Software, And Application Performance for the Exascale Era

2025

Courses, lectures, materials

Teaching

All teaching

Machine Learning for Earth Observation powered by Supercomputers

Read article

University of Iceland

Machine Learning for Earth Observation powered by Supercomputers

This course exposes the students to the physical principles underlying satellite observations of Earth by passive sensors, as well as parallel Deep Learning (DL) algorithms that scale on High Performance Computing (HPC) systems.

Every Spring Semester

IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium

Calls for papers, funding, vacancies

News and events

All news and events

Amer Delilbasic's Successful PhD Defense: Advancing Earth Observation with Hybrid Quantum-Classical Computing

Read article

University of Iceland

Amer Delilbasic's Successful PhD Defense: Advancing Earth Observation with Hybrid Quantum-Classical Computing

Amer Delilbasic successfully defended his PhD thesis, introducing innovative methods to integrate quantum computing with High-Performance Computing (HPC) for Earth Observation applications

14 April 2026

ESA-ECMWF ML4ESOP Workshop (ESA-ESRIN - Frascati, Italy)

Democratizing Foundation Models for Earth Observation Applications

07/05/2024

Reykjavik (Iceland)

Summer School on High Performance and Disruptive Computing in Remote Sensing 2023

29 May - 1 June, 2023

University of Iceland

Rocco Sedona's Successful PhD Defense: Making HPC for Deep Learning More Accessible in Earth Observation

May 4, 2023

Materials, thoughts, tips

Blog

All blog posts

No items found.

Academic papers

Recent Publications

All publications

Conference Papers

C. Paris, M. F. Celik, S. Maurogiovanni, R. Sedona, G. Cavallaro, R. Cartuyvels, and V. Marsocci

European Geosciences Union (EGU)

Recent advances in Earth Observation (EO) data and multimodal Geo-Foundation Models have sharply improved the ability to generate accurate crop-type maps by leveraging rich spatio-temporal representations. These models are inherently scalable across diverse and heterogeneous agricultural landscapes, thus exhibiting strong generalisation. However, timely and high-quality reference data remain a major bottleneck for reliable agricultural mapping and monitoring. Agricultural landscapes are highly dynamic, with frequent crop rotations that require seasonal or annual updates. In addition, European agriculture is increasingly affected by weather extremes (e.g., droughts, hail, and storms), which are expected to intensify in both magnitude and frequency. Traditional approaches rely on time-consuming and costly manual annotations or field surveys, which are difficult to sustain on a continuous basis and at large spatial scales (e.g., continental monitoring). In this context, geo- and time-tagged field photos represent a promising complementary data source. Each field photo can be linked to satellite image time series acquired over the same location up to the acquisition date. Compared to conventional in-situ surveys based on manual annotations, the combined use of satellite image time series and field photos provides a richer semantic representation of agricultural areas. While satellite image time series capture the temporal dynamics of crop development, field photos offer ground-level information at high resolution on crop condition, phenological stage, and management practices. Despite their potential, the operational use of field photos in agricultural monitoring remains limited, in part due to challenges in translating heterogeneous images into structured information. Recent advances in Vision–Language Models (VLMs) have unlocked substantial progress in the automatic interpretation and semantic extraction of information from raw field photos. By aligning visual features with semantic concepts expressed in natural language, VLMs provide a powerful mechanism for mapping unstructured field photos to standardised crop-type labels. This study investigates the potential of combining satellite image time series and geo-tagged field photos to expand, update, and complement existing reference datasets to support continuous large-scale agricultural monitoring. Preliminary results of mapping seven crop types (i.e., maize, wheat, rape, sugarbeet, oat, barley, and sunflower) in Europe indicate that, even in a zero-shot setting and when using simple prompts, the CLIP VLM can correctly identify crop types from field photos when a distinct phenological stage is visible. Incorporating phenological information derived from the temporal patterns of satellite image time series is therefore crucial, as it allows for the filtering of irrelevant images (e.g., post-harvest fields) and the selection of samples for which reliable classification is feasible. Furthermore, when consistency of label predictions obtained independently from field photos (using CLIP) and from Sentinel-1 and Sentinel-2 time series (using a simple Random Forest classifier) is used as a data reliability strategy, highly accurate classification performance across all considered crop types can be obtained. Overall, these findings highlight the strong potential of jointly exploiting satellite image time series and geo-tagged field photos for the efficient and reliable preparation of crop-type reference datasets.

To the publication

S. Hashim, S., Mandal, R., Sedona, E., Zandi, G. Cavallaro and the 3D-ABC Team

European Geosciences Union (EGU)

The 3D-ABC project, developed within the Helmholtz Foundation Model Initiative, aims to create a foundation model for accurate mapping of global terrestrial above- and below-ground carbon stocks in vegetation and soils at high spatial resolution. The model integrates multimodal remote sensing data including Harmonized Landsat-Sentinel-2 (HLS) imagery, TanDEM-X InSAR coherence, and will also integrate climatic, topographic, and space-borne 3D lidar data. The architecture employs a multi-modal input processor, FM encoder, adaptive fusion neck, and task-specific prediction heads, trained via masked autoencoder pretraining followed by supervised fine-tuning. Training leverages JSC's JUWELS Booster and the forthcoming JUPITER exascale system. BioMassters, a dataset that encompasses satellite imagery and associated forest biomass estimates for large-scale above-ground biomass mapping, provides an ideal initial evaluation framework for 3D-ABC for several compelling reasons. Above Ground Biomass (AGB) estimation represents a core downstream task for carbon monitoring. BioMassters specifically targets this capability using Sentinel-1 SAR and Sentinel-2 MSI time series, modalities that overlap substantially with 3D-ABC's input data streams. This alignment allows direct assessment of whether 3D-ABC's learned representations capture vegetation structure and biomass-relevant features. The dataset derives AGB labels from Finnish Forest Centre airborne LiDAR campaigns at 5 points per square meter density, combined with field measurements and calibrated allometric equations. This produces reference data with approximately 8% RMSE for key tree attributes, far more reliable than existing global products and essential for meaningful foundation model evaluation. With 310,000 patches of size 224x224 covering 8 million hectares across five years, BioMassters offers the statistical power needed to assess foundation model generalization. The temporal dimension, 12 monthly observations per sample, tests whether 3D-ABC effectively captures phenological dynamics crucial for vegetation monitoring. Beyond its scale and temporal richness, BioMassters also benefits from a strong benchmarking ecosystem. The NeurIPS 2023 competition produced well-documented baseline performance: U-TAE achieved 27.49 t/px RMSE overall, with results stratified by biomass density (15.24 t/px for low density, 37.59 t/px for high density). These benchmarks enable rigorous comparison of 3D-ABC against state-of-the-art task-specific models. Current global biomass products operate at 100m resolution with RMSE values of 30-50 t/px. BioMassters operates at 10m resolution, allowing assessment of whether 3D-ABC's multimodal fusion can advance both accuracy and spatial detail simultaneously. The dataset reveals where current approaches struggle, accuracy degrades with increasing forest density due to SAR backscatter and MSI reflectance saturation. This provides a specific challenge for 3D-ABC's multi-modal fusion architecture, and in future work we will be testing whether incorporating additional modalities (particularly 3D space-borne lidar) addresses these saturation effects. While BioMassters covers boreal forests exclusively, it establishes whether 3D-ABC's pretrained representations provide a foundation for fine-tuning to other biomes, a critical test of foundation model utility before deploying resources on global-scale evaluation, e.g. in the arctic region.

To the publication

Journals

Book chapters

About me

I graduated in telecommunications with the University of Trento, where I received both my Bachelor's and Master's degree.
‍
I did my Erasmus at the University of Iceland, which eventually led to three years of doctoral studies and earning the title of PhD.
‍
Since then, I've been a research assistant at JSC - Jülich Supercomputing Centre, later becoming Head of Simulation and Data Lab. Since 2024, I have been granted assistant Professorship at the University of Iceland in Reykjavík. I work at the intersection of Remote Sensing (RS), High Performance Computing (HPC), Quantum Computing (QC) and Machine Learning (ML).
‍
You can contact me at
g.cavallaro@fz-juelich.de
gcavallaro@hi.is

Read my CV

Let’s connect on LinkedIn

Prof. Gabriele Cavallaro

Affiliations

Research Topics

Remote Sensing

High Performance Computing

Machine Learning

Quantum Computing

Talks

Next-Generation Supercomputing: Europe’s Ecosystem for AI in the Exascale Era

Quantum Computing for Earth Observation: Searching for Quantum Advantage

Erasmus+ BIP Machine Learning for Earth Observation and Data Fusion

Next-Generation Supercomputing In Europe: A Community in Action Advancing Hardware, Software, And Application Performance for the Exascale Era

Teaching

Machine Learning for Earth Observation powered by Supercomputers

Quantum Computing for Earth Observation

Machine Learning for Earth Observation powered by Supercomputers

Scalable Machine Learning with High Performance and Cloud Computing

News and events

Amer Delilbasic's Successful PhD Defense: Advancing Earth Observation with Hybrid Quantum-Classical Computing

Democratizing Foundation Models for Earth Observation Applications

Summer School on High Performance and Disruptive Computing in Remote Sensing 2023

Rocco Sedona's Successful PhD Defense: Making HPC for Deep Learning More Accessible in Earth Observation

Blog

Recent Publications

Conference Papers

From Satellite Data and Geo-tagged Field Photos to Reliable Agricultural Reference Data

BioMassters as Initial Benchmark for 3D-ABC

TerraMind: Large-Scale Generative Multimodality for Earth Observation

Journals

Leveraging a Hybrid Quantum-Classical Framework for Subsurface Target Detection in Radar Sounding System: Challenges and Opportunities

From MODIS to Sentinel-2: A Regional Comparative Analysis of Crop-Yield Prediction with Matched Spatiotemporal Data

Lossy Neural Compression for Geospatial Analytics: A review

Book chapters

Quantum Computing for Remote Sensing Image Analysis

Proven Approaches of Using Innovative High-Performance Computing Architectures in Remote Sensing

Remote Sensing Data Fusion: Markov Models and Mathematical Morphology for Multisensor, Multiresolution, and Multiscale Image Classification

About me

Quantum Computing for Earth Observation:Searching for Quantum Advantage