[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123242-en":3,"doc-seo-123242-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123242,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning","Plastic waste has become a critical environmental issue, requiring accurate detection and continuous monitoring methods. This article proposes a machine-learning-based approach and an embedded solution that identifies plastic litter using an airborne hyperspectral sensor in the short-wave infrared (SWIR) band. Drone-based experiments collect data across natural and controlled settings, followed by spectral preprocessing to equalize measurements across the band and varying conditions. Optimized spectrum calibration, feature selection, and classification algorithms deliver high-specificity results across cross-validation, supporting deployment in new environments without complex manual recalibration.","Article  \nPlastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning  \nMarco Balsi 1, *, Monica Moroni 2 and Soufyane Bouchelaghem 1  \nAcademic Editor: Magaly Koch  \nReceived: 3 January 2025  \nRevised: 21 February 2025  \nAccepted: 4 March 2025  \nPublished: 6 March 2025  \nCitation: Balsi, M.; Moroni, M.; Bouchelaghem, S. Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning. Remote Sens. 2025, 17, 938. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/rs17050938](10.3390/rs17050938)  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, 00184 Rome, Italy; [soufyane.bouchelaghem@uniroma1.it](soufyane.bouchelaghem@uniroma1.it)  \n2 Department of Civil, Building, and Environmental Engineering (DICEA), Sapienza University of Rome, 00184 Rome, Italy; [monica.moroni@uniroma1.it](monica.moroni@uniroma1.it)  \n* [Correspondence: marco.balsi@uniroma1.it](Correspondence: marco.balsi@uniroma1.it); Tel.: +39-320-435-7195  \nAbstract: 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.  \nKeywords: drones; environmental monitoring; hyperspectral sensors; plastic waste  \n1. Introduction  \nPlastic pollution has recently become a significant global concern [1], threatening both terrestrial and marine ecosystems, and is the object of the United Nations Sustainable Development Goal (SDG) Target 14.1 [2] . The detection of plastic litter in the environment is necessary to prevent its scattering and eventual clustering in the oceans and on the coastsand to plan and execute clean-up action. To this purpose, remote sensing, at all scales, plays an essential role [3–5] . Satellite data may be used to detect large-scale clusters of plastic debris [6–9], but higher-detail data [10–14] are necessary to detect low-density litter in relatively small areas, e.g., on the coasts and in rivers, and to guide collection teams and vessels effectively to polluted areas.  \nSeveral sensing approaches have been considered recently; specifically, visiblespectrum and NIR multispectral imaging have attracted considerable interest. However, hyperspectral imaging, in particular in the SWIR (short-wave infrared) spectrum range (1000–2500 nm, often limited to 1000–1700 nm for technological reasons) is known to contain the most relevant information for plastic polymer detections because specific narrowband absorption peaks charact","cbCaitFtd0sDPzN7","https://ap.wps.com/l/cbCaitFtd0sDPzN7","pdf",7998537,1,18,"English","en",105,"# Introduction\n## Remote sensing and the need for plastic litter detection\n## Limits of VIS/NIR and the value of SWIR hyperspectral data\n# Methodology and Data Processing\n## Sensing setup and drone-based SWIR data collection\n## Spectral preprocessing and equalization\n## Machine learning approaches and model comparison\n# Results and Deployment Feasibility\n## Cross-validation performance and classification outcomes\n## Specificity to plastic polymers vs VIS/NIR limitations","[{\"question\":\"Why is SWIR hyperspectral imaging important for plastic polymer detection?\",\"answer\":\"SWIR hyperspectral data contain narrowband absorption peaks that characterize the reflection patterns of different polymers. This improves discrimination between plastics and other natural or artificial materials compared with VIS/NIR data.\"},{\"question\":\"How are the hyperspectral data collected and prepared for modeling?\",\"answer\":\"Experimental data are obtained from drone flights in natural and controlled case studies. The spectra are preprocessed to equalize measurements across the full band and across different environmental conditions before applying learning algorithms.\"},{\"question\":\"Which techniques are used to detect plastics and how is performance validated?\",\"answer\":\"The approach uses machine-learning methods for detection, with optimized steps including spectrum calibration, feature selection, and classification. Results are evaluated using cross-validation to ensure reliable, high-quality performance and supports deployment across environments without complicated manual adjustments.\"}]","Plastic Litter Detection in the Environment Using Hyperspectral Aerial Remote Sensing and Machine Learning | PDF",1785815407,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"plastic-litter-detection-in-the-environment-using-hyperspectral-aerial-remote-sensing-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/plastic-litter-detection-in-the-environment-using-hyperspectral-aerial-remote-sensing-and-machine-learning/123242/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is SWIR hyperspectral imaging important for plastic polymer detection?","Question",{"text":75,"@type":76},"SWIR hyperspectral data contain narrowband absorption peaks that characterize the reflection patterns of different polymers. This improves discrimination between plastics and other natural or artificial materials compared with VIS/NIR data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the hyperspectral data collected and prepared for modeling?",{"text":80,"@type":76},"Experimental data are obtained from drone flights in natural and controlled case studies. The spectra are preprocessed to equalize measurements across the full band and across different environmental conditions before applying learning algorithms.",{"name":82,"@type":73,"acceptedAnswer":83},"Which techniques are used to detect plastics and how is performance validated?",{"text":84,"@type":76},"The approach uses machine-learning methods for detection, with optimized steps including spectrum calibration, feature selection, and classification. Results are evaluated using cross-validation to ensure reliable, high-quality performance and supports deployment across environments without complicated manual adjustments.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]