20.500.12556/RUL-188356 Remote sensing of invasive alien plant species a review of species detectability, sensors, and monitoring approaches (2000–2025) Remote sensing (RS) has become a key tool for identifying, tracking, and managing invasive alien plant species (IAPS), particularly as biological invasions intensify under climate change, land-use change, and urban expansion. Despite rapid technological advances, RS applications for IAPS remain highly heterogeneous with respect to sensor types, spatial and spectral resolution, analytical methods, validation strategies, and species-specific detectability. This structured literature review synthesises global evidence on RS applications for IAPS published between 2000 and 2025, with particular attention to temperate ecosystems and the operational relevance of selected high-priority taxa for European management contexts: Ailanthus altissima, Asclepias syriaca, Heracleum mantegazzianum, Solidago spp., Reynoutria japonica, Impatiens glandulifera, Celastrus orbiculatus, Pueraria montana var. lobata, Phytolacca americana, and Buddleja davidii. We screened the Web of Science (WoS) and Scopus databases and analysed 219 eligible empirical studies according to sensor type, spatial and temporal resolution, analytical approach, validation design, reported accuracy, and ecological context. Multispectral satellite data dominated regional-scale mapping, whereas airborne hyperspectral imagery and UAV-based platforms were frequently used for fine-scale species discrimination and monitoring, especially for spectrally or structurally distinctive taxa. UAV-based approaches were valuable for local detection and post-eradication monitoring, although performance was often constrained by shadowing, canopy structure, and habitat heterogeneity. Recent trends, particularly after 2017, with a pronounced increase during 2023–2025, include the increasing use of deep learning, street-level imagery, crowdsourced photographs, and multisource data fusion. Species detectability varied widely among taxa and was strongly influenced by phenology, canopy position, habitat configuration, reference-data quality, and sensor characteristics. Overall, no single sensor or analytical approach was universally optimal. Instead, combining satellite, UAV, and ground-based data with species-specific ecological knowledge can improve detection efficiency, transferability, and operational monitoring of IAPS across global and temperate management contexts. Earth observation species detectability multisensor data fusion UAV imagery machine learning phenology management opazovanje Zemlje zaznavanje vrst združevanje podatkov iz več senzorjev posnetki z brezpilotnimi letalniki (UAV) strojno učenje fenologija upravljanje true false true Angleški jezik Slovenski jezik Članek v reviji 2026-09-21 13:32:59 2026-09-21 13:33:09 2026-09-22 04:04:54 0000-00-00 00:00:00 2026 0 0 31 str. Vol. 44, art. 102234 Dec. 2026 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 528.8:004.8 2352-9385 10.1016/j.rsase.2026.102234 290787331 https://www.sciencedirect.com/science/article/pii/S2352938526003678 1 29b8fe21-b5b0-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=248445 Potocnik_Buhvald...-Remote_sensing_of_invasive_alien_plant_species.pdf Potocnik_Buhvald...-Remote_sensing_of_invasive_alien_plant_species.pdf 1 5FAFB6157702D4ADB4E6DEEA902DE660 ab0ac08ecd1b3957c382e2e621cbe943f64adb5936ed181453f7a68686995636 63be308f-b5b0-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=248446 Fakulteta za gradbeništvo in geodezijo 0 0 0