Abstract
Globally, we are in the midst of a biodiversity crisis, and megadiverse countries
become key targets for conservation. South Africa, the only country in Africa hosting
three biodiversity hotspots, harbours tremendous diversity of at-risk species requiring
protection intervention. However, the lengthy risk assessment process and the lack of
required data to complete assessments are serious limitation to conservation since
several species may slip into extinction while awaiting risk assessment. Here, we
employed deep neural network model integrating species climatic and geographic
features to predict the conservation status of 116 unassessed plant species. Our
analysis involved in total 1072 plant species and 96 963 occurrence points. Among the
1072 plant species, 956 served for the training of the model and 116 were reserved
for predictions. The best-performing model exhibits high accuracy, reaching up to
83.6% at the binary classification and 56.8% at the detailed classification. Our bestperforming
model at the simplified binary classification predicted that 25 species (32%)
and 3 species (8%) of Data Deficient and Not-Evaluated species are likely threatened,
respectively, amounting to a proportion of 24.1% of unassessed species facing a risk
of extinction. Interestingly, all unassessed species predicted to be threatened were
found both in and outside protected areas. However, these likely threatened species
were more abundant outside protected areas, revealing the effectiveness of South
Africa’s network of protected areas in conservation. Considering the limitation in
assessing only species with available data, there remains a possibility of a higher
proportion of unassessed species being imperilled.