Institutes & CentersInstitute for Earth Observation - Projects - ALGORITMI

ALGORITMI

Development of algorithms for estimation and monitoring of hydrological parameters by using satellite data and drones

The analysis of the hydrological cycle using remote sensing data is a research topic that presents interesting technical and scientific challenges to obtain a precise evaluation of the natural and anthropogenic contributions to the water balance. Significative examples are the estimates of the use of water resources, the extent and thickness of the snowpack, and agricultural-forest biomass. The monitoring of these individual contributions is fundamental for both the management of water resources and for the prediction of risk events (e.g. floods, avalanches, landslides).

The ALGORITMI project aims at developing innovative algorithms and techniques based on machine learning methods for the estimation of biophysical parameters like soil moisture, agricultural-forest biomass and snow related to characterizing the different components of the hydrological cycle. These algorithms, mainly based on the use of SAR satellite data, will be implemented, calibrated and validated by Eurac at regional scale (South Tyrol) and, in more detail, on the Mazia Valley for the study of agricultural-forestry coverage and on Val Senales for snow, with the support of ancillary data and in-situ measurements coming from field campaigns organized concurrently to satellite passes.

Contact person: Claudia Notarnicola claudia.notarnicola@eurac.edu and Giovanni Cuozzo giovanni.cuozzo@eurac.edu

Project duration: January 2019 - January 2022
Project status:
Funding:
ASI Italian Space Agency (National funding / Project)
Institutes: Institute for Earth Observation, Center for Sensing Solutions

Discover

See related experts, publications, and research topics.

Search for "ALGORITMI Development of al…"

Explore "ALGORITMI" in Discover

technology earth observation environmental monitoring

Project funded by

Scientific Publications

Journal article2021

Biomass retrieval based on genetic algorithm feature selection and support vector regression in Alpine grassland using ground-based hyperspectral and Sentinel-1 SAR data.

Chiarito E, Cigna F, Cuozzo G, Fontanelli G, Mejia Aguilar A, Paloscia S, Rossi M, Santi E,

Giovanni Cuozzo, Claudia Notarnicola

A general framework for the integration of multi-sensor data for dry and fresh biomass retrieval is proposed and tested in Alpine meadows and pastures. To this purpose, hyperspectral spectroradiometer (as simulation of hyperspectral imagery) and biomass samples were collected in field campaigns and Copernicus Sentinel-1 Interferometric Wide (IW) swath SAR backscattering coefficients were used. First, a genetic algorithm feature selection was performed on hyperspectral data, and afterwards the resulting most sensitive bands where combined with SAR data within a support vector regression (SVR) model. The most sensitive hyperspectral bands were mainly located in different regions of the SWIR range for both fresh and dry biomass, and in the red and near-infrared regions mainly for dry biomass, but with less influence for fresh biomass. The R² correlation values between the sampled and the estimated biomass range from 0.24 to 0.71. The relatively low performances are mainly related to the saturation effect in the optical bands, as well as to the paucity of points for high values of biomass. The methodology allows a better understanding of the interaction between grassland systems and the electromagnetic spectrum by offering a model with a reduced number of narrow bands in the context of a multi-sensor integration.

DOI Source

DOI: 10.1080/22797254.2021.1901063

Conference proceedings article2021

Snow water equivalent retrieval from COSMO-SkyMed observations through machine learning algorithms and model simulations

Santi E, Paloscia S, Pettinato S, Notarnicola C, Cuozzo G, De Gregorio L, Cigna F, Tapete D

Giovanni Cuozzo, Claudia Notarnicola

The monitoring of snow conditions in Alpine areas to support water management and avalanche warning applications would require the estimate of snow parameters, such as the snow water equivalent (SWE). In this research, COSMOSkyMed (CSK) X-band SAR data were exploited to estimate the SWE. In-situ snow measurements (depth, density, snow grain radius, temperature) collected in South Tyrol (Italy), were used to simulate the X-band backscatter with the Dense Medium Radiative Transfer (DMRT) electromagnetic model.
Two SWE retrieval algorithms based on machine learning approach were implemented. The algorithms are based on Artificial Neural Networks (ANN) and Support Vector Regression (SVR) and have been trained with both experimental data and DMRT model simulations. These algorithms were applied to a selection of CSK StripMap HIMAGE HH-polarized scenes collected over the test area.
The obtained results are promising and they confirm the potential of SAR data at X-band to retrieve snow parameters, although the algorithm validation should be improved in the future, with more consistent measurement dataset.

DOI Source

DOI: 10.1109/IGARSS47720.2021.9553985

Conference proceedings article2020

SAR multi-frequency observations of vegetation in agricultural and mountain areas

Paloscia S, Fontanelli G, Lapini A, Santi E, Pettinato S, Notarnicola C, Chiarito E, Cuozzo G,

Giovanni Cuozzo, Claudia Notarnicola

In this paper, the potential of space-borne Synthetic Aperture Radar (SAR) sensors combined with optical ones has been exploited by analyzing datasets collected on two vegetated areas in Italy, by using COSMO-SkyMed X-band and Sentinel-1 C-band SAR, PRISMA hyperspectral and Sentinel-2 multispectral imagery, combined with field measurements acquired with spectroradiometers. On the mountain area in Alto Adige, a biomass estimation approach was developed by combining Sentinel-1 SAR and spectroradiometer hyperspectral data. On Val d’Elsa area in Tuscany, COSMO-SkyMed StripMap HIMAGE and Sentinel-1 Interferometric Wide swath mode SAR data have been integrated with Sentinel-2 imagery for improving the classification of agricultural crops. Convolutional Neural Networks (CNN) have been used for the classification of agricultural areas using these three sensors.

DOI Source

DOI: 10.23919/URSIGASS49373.2020.9232372

Conference proceedings article2020

SWE retrieval in Alpine areas with high-resolution COSMO-SkyMed X-band SAR data using Artificial Neural Networks and Support Vector Regression techniques

Santi E, Paloscia S, Pettinato S, De Gregorio L, Cuozzo G, Jacob A, Notarnicola C, Cigna F,

Giovanni Cuozzo, Claudia Notarnicola, Alexander Jacob

URSI GASS 2020, Rome, Italy, 29 August - 5 September 2020
SWE retrieval in Alpine areas with high-resolution COSMO-SkyMed X-band SAR data using
Artificial Neural Networks and Support Vector Regression techniques
Emanuele Santi(1), Simonetta Paloscia* (1), Simone Pettinato(1), Ludovica De Gregorio(2), Giovanni Cuozzo(2),
Alexander Jacob(2), Claudia Notarnicola(2), Francesca Cigna(3), and Deodato Tapete(3)
(1) Institute of Applied Physics, National Research Council – CNR-IFAC, Florence 50019, Italy
(2) EURAC Research, viale Druso, 1-39100 Bolzano, Italy
(3) Italian Space Agency – ASI, Via del Politecnico s.n.c., 00133 Rome, Italy
Abstract
The potential of satellite Synthetic Aperture Radar (SAR) sensors for Snow Water Equivalent (SWE) retrieval in Alpine areas is assessed in this study. X-band HH-polarized SAR backscatter from 2012-2015 images
acquired by the COSMO-SkyMed constellation over the South Tyrol province in northern Italy is compared with SWE in-situ measurements and nivo-meteorological station records. The resulting relationship is compared with simulations based on the Dense Media Radiative Transfer – Quasi Mie Scattering (DMRT – QMS) model. Artificial Neural Networks (ANN) and Support Vector Regression (SVR) machine learning techniques are trained and used for SWE retrieval from COSMO-SkyMed data. Good accuracy and small computational cost are observed for both ANN and SVR. The resulting SWE maps agree with snow conditions measured in-situ.

DOI Source

DOI: 10.23919/URSIGASS49373.2020.9232247

All Publications

Biomass retrieval based on genetic algorithm feature selection and support vector regression in Alpine grassland using ground-based hyperspectral and Sentinel-1 SAR data.
Chiarito E, Cigna F, Cuozzo G, Fontanelli G, Mejia Aguilar A, Paloscia S, Rossi M, Santi E, Tapete D, Notarnicola C (2021)
Journal article
European Journal of Remote Sensing

More information: https://www.tandfonline.com/doi/full/10.1080/22797254.20 ...

https://doi.org/10.1080/22797254.2021.1901063

https://hdl.handle.net/10863/18197

Snow water equivalent retrieval from COSMO-SkyMed observations through machine learning algorithms and model simulations
Santi E, Paloscia S, Pettinato S, Notarnicola C, Cuozzo G, De Gregorio L, Cigna F, Tapete D
(2021)
Conference proceedings article

Conference: IGARSS 2021 - Virtual Conference | Bruxelles | 12.7.2021 - 16.7.2021

More information: https://ieeexplore.ieee.org/abstract/document/9553985

https://doi.org/10.1109/IGARSS47720.2021.9553985

https://hdl.handle.net/10863/19665

Conference: IGARSS 2021 - Virtual Conference | Bruxelles | 12.7.2021 - 16.7.2021

More information: https://igarss2021.com/view_paper.php?PaperNum=3254

https://hdl.handle.net/10863/18617

Our partners

Italian Space Agency

Nello Carrara Institute of Applied Physics

Project Team

Giovanni Cuozzo

Project Manager

Claudia Notarnicola

Vice Manager

Daniela Dellantonio

Team Member

Ludovica De Gregorio

Team Member

Alexander Jacob

Carlo Marin

Scientific Advisory Board

Awards

Products

Technical
These cookies are necessary for the website to function and cannot be switched off.

Service	Decline/Accept	Terms Link
Youtube		https://support.google.com/youtube/answer/7671399?...
Vimeo		https://vimeo.com/terms
Flourish		https://flourish.studio/terms/
Datawrapper		https://www.datawrapper.de/terms
Power BI		https://www.microsoft.com/en/servicesagreement/
Facebook		https://www.facebook.com/policies/cookies/
Instagram		https://help.instagram.com/1896641480634370?ref=ig
X		https://help.twitter.com/en/rules-and-policies/twi...
Google Maps		https://maps.google.com/help/terms_maps/
LinkedIn		https://www.linkedin.com/legal/cookie-policy

Conference proceedings article2020

SWE retrieval in Alpine areas with high-resolution COSMO-SkyMed X-band SAR data using Artificial Neural Networks and Support Vector Regression techniques

Santi E, Paloscia S, Pettinato S, De Gregorio L, Cuozzo G, Jacob A, Notarnicola C, Cigna F,

Giovanni Cuozzo, Claudia Notarnicola, Alexander Jacob

DOI Source

DOI: 10.23919/URSIGASS49373.2020.9232247

ALGORITMI