ReFuse: Generating Imperviousness Maps from Multi-Spectral Sentinel-2 Satellite Imagery

Giovanni Giacco (), Stefano Marrone, Giuliano Langella and Carlo Sansone ()
Additional contact information
Giovanni Giacco: Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, Italy
Stefano Marrone: Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, Italy
Giuliano Langella: Department of Agriculture, University of Naples Federico II, Via Università 100, 80055 Naples, Italy
Carlo Sansone: Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio 21, 80125 Naples, Italy

Future Internet, 2022, vol. 14, issue 10, 1-20

Abstract: Continual mapping and monitoring of impervious surfaces are crucial activities to support sustainable urban management strategies and to plan effective actions for environmental changes. In this context, impervious surface coverage is increasingly becoming an essential indicator for assessing urbanization and environmental quality, with several works relying on satellite imagery to determine it. However, although satellite imagery is typically available with a frequency of 3–10 days worldwide, imperviousness maps are released at most annually as they require a huge human effort to be produced and validated. Attempts have been made to extract imperviousness maps from satellite images using machine learning, but (i) the scarcity of reliable and detailed ground truth (ii) together with the need to manage different spectral bands (iii) while making the resulting system easily accessible to the end users is limiting their diffusion. To tackle these problems, in this work we introduce a deep-learning-based approach to extract imperviousness maps from multi-spectral Sentinel-2 images leveraging a very detailed imperviousness map realised by the Italian department for environment protection as ground truth. We also propose a scalable and portable inference pipeline designed to easily scale the approach, integrating it into a web-based Geographic Information System (GIS) application. As a result, even non-expert GIS users can quickly and easily calculate impervious surfaces for any place on Earth (accuracy > 95 % ), with a frequency limited only by the availability of new satellite images.

Keywords: FuseNet; U-Net; ResNet; impervious; land cover; remote sensing; deep learning; CNN; Sentinel-2 (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/10/278/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/10/278/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:10:p:278-:d:928339

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().