Evaluating the Efficacy of Sentinel-2 versus Aerial Imagery in Serrated Tussock Classification

2025-12-11

AI Summary

High costs and scalability limitations hinder large-scale aerial monitoring of the invasive grass *Stipa splendens* in Victoria, Australia. Method: This study systematically evaluates the feasibility of substituting Sentinel-2 satellite imagery for aerial photography. We innovatively integrate multi-temporal red-edge bands, texture features, and vegetation indices to construct 11 distinct feature combinations and employ Random Forest classifiers. For the first time, we demonstrate that synergistic spectral enhancement and phenological features can overcome spatial resolution constraints. Results: The optimal Sentinel-2 model (M76*) achieves an overall accuracy of 68% (Kappa = 0.55), marginally surpassing the aerial-based model (67%, Kappa = 0.52). These results confirm Sentinel-2’s practical potential for cost-effective, scalable, large-area remote sensing monitoring of invasive grasses.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Ensemble Methods
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Invasive species pose major global threats to ecosystems and agriculture. Serrated tussock ( extit{Nassella trichotoma}) is a highly competitive invasive grass species that disrupts native grasslands, reduces pasture productivity, and increases land management costs. In Victoria, Australia, it presents a major challenge due to its aggressive spread and ecological impact. While current ground surveys and subsequent management practices are effective at small scales, they are not feasible for landscape-scale monitoring. Although aerial imagery offers high spatial resolution suitable for detailed classification, its high cost limits scalability. Satellite-based remote sensing provides a more cost-effective and scalable alternative, though often with lower spatial resolution. This study evaluates whether multi-temporal Sentinel-2 imagery, despite its lower spatial resolution, can provide a comparable and cost-effective alternative for landscape-scale monitoring of serrated tussock by leveraging its higher spectral resolution and seasonal phenological information. A total of eleven models have been developed using various combinations of spectral bands, texture features, vegetation indices, and seasonal data. Using a random forest classifier, the best-performing Sentinel-2 model (M76*) has achieved an Overall Accuracy (OA) of 68% and an Overall Kappa (OK) of 0.55, slightly outperforming the best-performing aerial imaging model's OA of 67% and OK of 0.52 on the same dataset. These findings highlight the potential of multi-seasonal feature-enhanced satellite-based models for scalable invasive species classification.

Problem

• Evaluating Sentinel-2 versus aerial imagery for invasive grass classification
• Assessing cost-effective landscape-scale monitoring of serrated tussock
• Leveraging multi-temporal satellite data for comparable classification accuracy

Innovation

• Multi-temporal Sentinel-2 imagery used for landscape-scale monitoring
• Random forest classifier applied to spectral and seasonal data
• Feature-enhanced satellite model outperforms aerial imagery accuracy