# Monitoring the Spatiotemporal Dynamics of Invasive Pedicularis kansuensis in Bayinbuluke Alpine Wetlands: A Novel Spectral Index Framework Using PlanetScope Time Series (2021–2025)

## TL;DR

A new spectral index called PKI was developed to monitor the invasive plant Pedicularis kansuensis in alpine wetlands using satellite data, enabling accurate and efficient tracking of its spread.

## Contribution

The novel Pedicularis kansuensis Index (PKI) provides a rapid and reliable method for monitoring invasive species in heterogeneous alpine environments.

## Key findings

- The PKI achieved an overall accuracy of 93.52% and an F1-score of 93.28% in identifying Pedicularis kansuensis.
- The invaded area increased to 2168 ha in 2022 but decreased to 160 ha in 2025, showing a dynamic pattern of invasion.
- 161.6 ha of invasion hotspots were identified as stable targets for long-term containment.

## Abstract

The expansion of the invasive species Pedicularis kansuensis threatens the ecological integrity of alpine wetlands, particularly in the Bayinbuluke, northwestern China. However, operational monitoring remains challenging. Conventional indices often lack specificity in heterogeneous alpine backgrounds, while deep learning models are typically too data-intensive to support consistent, multi-year mapping. To develop a rapid, reliable, and operational method for monitoring this invader, we proposed a novel, species-specific spectral index, the Pedicularis kansuensis Index (PKI), using the blue, green, and red-edge bands of high-resolution (3 m) PlanetScope imagery. The PKI constructs a robust target signal by integrating distinct spectral features derived from in situ hyperspectral measurement with a grayscale morphological opening (GrMO) refinement to suppress background noise. A comprehensive validation against seven established benchmarks indices (e.g., NDVI, RI, and ARI) demonstrated the superior performance of PKI across the central alpine wetlands of Bayinbuluke (2841 km2). It achieved the highest separability with an M-statistic of 1.36. Furthermore, the index attained an overall accuracy of 93.52% (95% CI: 92.3–94.7%), and an F1-score of 93.28% (95% CI: 92.0–94.5%), effectively minimizing confusion with co-occurring native vegetation and background. Applying this framework to a five-year time series (2021–2025) revealed a distinct cycle of outbreaks and relaxation. Specifically, the invaded area increased to 2168 ha in 2022, then decreased to 160 ha in 2025. Spatial analysis further identified stable invasion hotspots of 161.6 ha, highlighting key targets for long-term containment. Meanwhile, 94.4% of the invaded area was transient, lasting only one year (4824.7 ha). These results confirm that the PKI is a physically interpretable, accurate, and computationally efficient tool for monitoring invasive species in heterogeneous alpine environments. It facilitates timely and targeted ecosystem management.