Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning

Plastic waste has become a critical environmental issue, necessitating effective methods for detection and monitoring. This article presents a machine-learning-based methodology and embedded solution to detect plastic waste in the environment using an airborne hyperspectral sensor operating in the s...

Full description

Saved in:
Bibliographic Details
Main Authors: Marco Balsi, Monica Moroni, Soufyane Bouchelaghem
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/5/938
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222775679057920
author Marco Balsi
Monica Moroni
Soufyane Bouchelaghem
author_facet Marco Balsi
Monica Moroni
Soufyane Bouchelaghem
author_sort Marco Balsi
collection DOAJ
description Plastic waste has become a critical environmental issue, necessitating effective methods for detection and monitoring. This article presents a machine-learning-based methodology and embedded solution to detect plastic waste in the environment using an airborne hyperspectral sensor operating in the short-wave infrared (SWIR) band. Experimental data were obtained from drone flights in several case studies in natural and controlled environments. Data were preprocessed to simply equalize the spectra across the whole band and across different environmental conditions, and machine learning techniques were applied to detect plastics even in real-time. Several algorithms for spectrum calibration, feature selection, and classification were optimized and compared to obtain an optimal solution that has high-quality results under cross-validation. This way, deploying the system in different environments without requiring complicated manual adjustments or re-learning is possible. The results of this work prove the feasibility of the proposed plastic litter detection approach using high-definition aerial remote sensing, with high specificity to plastic polymers that are not obtained using visible and NIR data.
format Article
id doaj-art-ec51f74189234e8a93b6ee83f6b6cd53
institution OA Journals
issn 2072-4292
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-ec51f74189234e8a93b6ee83f6b6cd532025-08-20T02:06:13ZengMDPI AGRemote Sensing2072-42922025-03-0117593810.3390/rs17050938Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine LearningMarco Balsi0Monica Moroni1Soufyane Bouchelaghem2Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, 00184 Rome, ItalyDepartment of Civil, Building, and Environmental Engineering (DICEA), Sapienza University of Rome, 00184 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, 00184 Rome, ItalyPlastic waste has become a critical environmental issue, necessitating effective methods for detection and monitoring. This article presents a machine-learning-based methodology and embedded solution to detect plastic waste in the environment using an airborne hyperspectral sensor operating in the short-wave infrared (SWIR) band. Experimental data were obtained from drone flights in several case studies in natural and controlled environments. Data were preprocessed to simply equalize the spectra across the whole band and across different environmental conditions, and machine learning techniques were applied to detect plastics even in real-time. Several algorithms for spectrum calibration, feature selection, and classification were optimized and compared to obtain an optimal solution that has high-quality results under cross-validation. This way, deploying the system in different environments without requiring complicated manual adjustments or re-learning is possible. The results of this work prove the feasibility of the proposed plastic litter detection approach using high-definition aerial remote sensing, with high specificity to plastic polymers that are not obtained using visible and NIR data.https://www.mdpi.com/2072-4292/17/5/938dronesenvironmental monitoringhyperspectral sensorsplastic waste
spellingShingle Marco Balsi
Monica Moroni
Soufyane Bouchelaghem
Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
Remote Sensing
drones
environmental monitoring
hyperspectral sensors
plastic waste
title Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
title_full Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
title_fullStr Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
title_full_unstemmed Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
title_short Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning
title_sort plastic litter detection in the environment using hyperspectral aerial remote sensing and machine learning
topic drones
environmental monitoring
hyperspectral sensors
plastic waste
url https://www.mdpi.com/2072-4292/17/5/938
work_keys_str_mv AT marcobalsi plasticlitterdetectionintheenvironmentusinghyperspectralaerialremotesensingandmachinelearning
AT monicamoroni plasticlitterdetectionintheenvironmentusinghyperspectralaerialremotesensingandmachinelearning
AT soufyanebouchelaghem plasticlitterdetectionintheenvironmentusinghyperspectralaerialremotesensingandmachinelearning