<i>Suaeda Salsa</i> Hyperspectral Index (SSHI) for mapping <i>S. salsa</i> in coastal wetlands using hyperspectral satellite imagery: case studies in northern coastal China

<i>Suaeda Salsa (S. salsa)</i>, a pioneer species with short and red-purplish plants in the intertidal zones, has significant ecological, economic, recreational and tourism values. Timely monitoring of <i>S. salsa</i> is crucial for understanding its dynamics and sustainable management of coastal wetlands. Hyperspectral satellite offers valuable opportunities due to its detailed spectral information. This study proposed a <i>Suaeda Salsa</i> Hyperspectral Index (SSHI) for <i>S. salsa</i> mapping based on hyperspectral satellite imagery. SSHI was developed by considering the large within-class spectral variations of cover types at coastal wetlands, accounting for the spectral correlations in hyperspectral data, and employing dynamic band selection on a per-pixel basis to optimize the separation of <i>S. salsa</i> from other land covers. SSHI=Sgnρ620−maxρi∗ρ860−minρj ρ860+ρ620+L∗1+L, where i∈[499 nm, 611 nm], j∈[628 nm, 851 nm], L=0.5. We applied SSHI on ZY1-02D/E AHSI images over Yellow River Delta (YRD) and Liao River Delta (LRD), China during 2021–2023. To evaluate the performance of SSHI, a simple thresholding method and a random forest (RF) model were used to map <i>S. salsa</i>, respectively. Our results showed that the overall accuracies of <i>S. salsa</i> maps achieved 87.96~89.43% (YRD) and 92.03~93.36% (LRD) using thresholds, and 92.62~94.05% (YRD) and 94.74~94.79% (LRD) using RF. For RF, incorporating SSHI improves <i>S. salsa</i> producer’s accuracies (user’s accuracies) by 1.02~6.85% (2.26~6.25%) compared to those without SSHI, proving the effectiveness of SSHI. The <i>S. salsa</i> maps reveal notable temporal variations, reflecting the impacts of climate change and human activities. Compared to existing hyperspectral indices related to red pigments, SSHI depicts greater separability between <i>S. salsa</i> and non-<i>S. salsa</i>. Meanwhile, SSHI is also applicable to other hyperspectral images such as GF-5B and PRISMA. SSHI has shown good adaptability and robustness for different time periods, regions, and hyperspectral satellite images, indicating that SSHI presents significant potential in accurately and effectively detecting <i>S. salsa</i> to facilitate sustainable coastal wetland monitoring and management.