PROJECT PRIN 2022 AIDA

"AI- and DIP-Enhanced DAta Augmentation for Remote Sensing of Soil Moisture and Forest Biomass"

Project Code : 20229FX3B9
CUP : J53D23000660001

Main Official Website

The European Union aims at becoming the first climate-neutral continent by 2050. It is committed to a 55% reduction in emissions by 2030 compared to 1990 levels. Studying climate changes is therefore fundamental to contribute to reaching this goal. Satellite data and products are a valuable tool for monitoring the life of our planet. They have been proved to be effective, e.g., for sensing parameters over ocean, ice, and land, and to contribute to characterizing Essential Climate Variables (ECVs). ECVs are key parameters of the Earth system to help to understand climate change and to guide mitigation measures.

AIDA aims at proposing advanced AI- and DIP-driven temporal and spatial data augmentation procedures for satellite data collected in the frame of space missions for Earth observation, which can be used to systemically and globally retrieve bio-geophysical variables connected to ECVs. Augmented data are used to enhance state-of-art processing implemented to retrieve soil moisture and forest biomass information. Data augmentation techniques offer unique opportunities to study climate change; understanding and limiting its risks is a gambit that requires responsive, evidence-based, and effective governance to be a winning strategy.

Our team

Davide Comite

Principal Investigator

Associate Professor
Università degli Studi di Roma
"La Sapienza"

View Google Scholar

Danilo Costarelli

Coordinator of the Perugia local unit

Associate Professor
Università degli Studi di Perugia

View Google Scholar

Domenico D. Bloisi

Coordinator of the UNINT local unit

Associate Professor
Università degli Studi Internazionali di Roma - UNINT

View Google Scholar

Isabella Mereu

Postdoctoral position
Università degli Studi di Roma "La Sapienza"

View Google Scholar

Mariarosaria Natale

Web Master

Postdoctoral position
Università degli Studi di Perugia

View Google Scholar

AIDA Review Paper

Mereu, M. Natale, M. Piconi, A. Troiani, V. Suriani, D.D. Bloisi, P. Burghignoli, D. Costarelli, A. Veneri, D. Comite, Interpolation Theory and Artificial Intelligence: A Roadmap for Satellite Data Augmentation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2025). DOI: 10.1109/JSTARS.2025.3577534.

This review was carried out as part of WP2, with the involvement of all project units.

It is a comprehensive review paper on data augmentation techniques for satellite RS data from classical models to
advanced AI techniques. It includes a detailed classification of existing techniques and a critical comparison of their strengths, limitations, and applicability to complex datasets, exploited for a plethora of applications. The review also outlines a roadmap offering valuable insights and to assist researchers in selecting appropriate techniques and developing novel approaches to enhance satellite RS data.

Read Now

Publications - Perugia Local Unit

D. Costarelli, Convergence and high order of approximation by Steklov sampling operators, Banach J. of Math. Anal., 18(4) (2024).
L. Boccali, D. Costarelli, G. Vinti, Convergence results in Orlicz spaces for sequences of max-product Kantorovich sampling operators, Journal of Computational and Applied Mathematics, 449 (2024), 115957.
L. Boccali, D. Costarelli, G. Vinti, Max-Product Sampling Kantorovich Operators: Quantitative Estimates in Functional Spaces, Numerical Functional Analysis and Optimization, 45(13–14) (2024), pp. 667–685.
D. Costarelli, M. Natale, G. Vinti, Estimation for the convex modular of the aliasing error of nonlinear sampling Kantorovich operators, Nonlinear Analysis: Modelling and Control, 30(2) (2025).
M. Cantarini, D. Costarelli, An application of the Euler-MacLaurin summation formula for estimating the order of approximation of sampling-type series, Dolomites Research Notes on Approximation, 18(2) (2025).
D. Costarelli, E. Russo, Modular convergence of Steklov sampling operators in Orlicz spaces, J. Pseudo-Differ. Oper. Appl., 16(80) (2025).
D. Costarelli, M. Natale, Advancements in nonlinear exponential sampling: convergence, quantitative analysis, and Voronovskaya-type formula, Communications in Nonlinear Science and Numerical Simulation, 152 Part B (2026).
D. Costarelli, M. Natale, M. Piconi, Image resizing by neural network operators and their convergence rate with respect to the L^p-norm and the dissimilarity index defined through the continuous SSIM, preprint arXiv:2501.14857 (2025).
D. Costarelli, M. Natale, Sampling Kantorovich operators for speckle noise reduction using a Down-Up scaling approach and gap filling in remote sensing images, preprint arXiv:2505.02422 (2025).

Keep checking back as we continue to work and publish more.

Events

Kick Off Meeting

Date: November 8th, 2023. at 11:00 a.m.
Location: Università degli Studi Internazionali di Roma - UNINT, Room 3.

For those who couldn't attend, the meeting was accessible online via MS Teams.

Contacts – Perugia Local Unit

Phone

075 5855040

Email

danilo.costarelli@unipg.it

PRIN 2022

‌

AI Website Generator