English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Logged forests cover four million square kilometres of the tropics andrestoring these forests is essential if we are to avoid the worst impacts ofclimate change, yet monitoring recovery is challenging. Tracking the abundanceof visually identifiable, early-successional species enables successionalstatus and thereby restoration progress to be evaluated. Here we present a newpipeline, SLIC-UAV, for processing Unmanned Aerial Vehicle (UAV) imagery to mapearly-successional species in tropical forests. The pipeline is novel becauseit comprises: (a) a time-efficient approach for labelling crowns from UAVimagery; (b) machine learning of species based on spectral and texturalfeatures within individual tree crowns, and (c) automatic segmentation oforthomosaiced UAV imagery into 'superpixels', using Simple Linear IterativeClustering (SLIC). Creating superpixels reduces the dataset's dimensionalityand focuses prediction onto clusters of pixels, greatly improving accuracy. Todemonstrate SLIC-UAV, support vector machines and random forests were used topredict the species of hand-labelled crowns in a restoration concession inIndonesia. Random forests were most accurate at discriminating species forwhole crowns, with accuracy ranging from 79.3% when mapping five commonspecies, to 90.5% when mapping the three most visually-distinctive species. Incontrast, support vector machines proved better for labelling automaticallysegmented superpixels, with accuracy ranging from 74.3% to 91.7% for the samespecies. Models were extended to map species across 100 hectares of forest. Thestudy demonstrates the power of SLIC-UAV for mapping characteristicearly-successional tree species as an indicator of successional stage withintropical forest restoration areas. Continued effort is needed to developeasy-to-implement and low-cost technology to improve the affordability ofproject management.

SLIC-UAV: A Method for monitoring recovery in tropical restoration projects through identification of signature species using UAVs