Abstract:
The effective and efficient
monitoring of revegetation outcomes is a key component of ecosystem
restoration. Monitoring often involves labour intensive manual methods
which can be difficult to deploy when sites are inaccessible or involve
large areas of revegetation. This study aimed to identify plant species
and quantify α-diversity index on a sub-meter scale at Manlailiang Mine
Site in Northwestern China using unmanned aerial vehicles (UAVs) as a
means to semi-automate large-scale vegetation monitoring. UAVs equipped
with multispectral sensors were combined with three industry-standard
supervised classification algorithms (support vector machine (SVM),
maximum likelihood, and artificial neural network) to classify plant
species. Spectral vegetation indices (NDVI, DVI, VDVI, SAVI, MSAVI, EXG
- EXR) were used to assess vegetation diversity obtained from on-ground
survey plot data (Margalef, Pielou, Simpson, Shannon indices). Our
results showed that SVM outperformed other algorithms in species
identification accuracy (overall accuracy 84%). Significant
relationships were observed between vegetation indices and diversity
indices, with DVI performing significantly better than many more
commonly used indices such as NDVI. The findings highlight the potential
of combining UAV multispectral data, spectral vegetation indices and
ground surveys for effective and efficient fine-scale monitoring of
vegetation diversity in the ecological restoration of mining areas. This
has significant practical benefits for improving adaptive management of
restoration through improved monitoring tools.