Summary
This study validates satellite-based remote sensing as a tool for detecting liana infestation patterns in tropical forests, using Sentinel-2 imagery and neural network classification trained on airborne hyperspectral data across a primary and selectively logged forest in Borneo. Liana infestation increased significantly between 2016 and 2019, with strong positive correlation to Greenness Index observed across forest types and both drought and wet years, suggesting the method has broad applicability across tropical forest ecosystems.
Regional applicability
This research is not directly applicable to United Kingdom farming or forestry systems, as it focuses on tropical forest dynamics in Southeast Asia. However, the remote sensing methodology and neural network classification approach could potentially be adapted for monitoring woody vine encroachment or invasive climber species in UK woodland management, though validation in temperate forest conditions would be required.
Key measures
Percentage of severely (>75%) liana infested pixels; Greenness Index (GI); neural network classification accuracy; temporal trends 2016–2019; validation against airborne hyperspectral data
Outcomes reported
The study demonstrated that satellite-based imagery (Sentinel-2) can accurately detect liana infestation across closed-canopy tropical forests using neural network classification trained on hyperspectral data. Liana infestation increased from 12.9% severely infested pixels in 2016 to 17.3% in 2019, and was positively associated with Greenness Index across different forest types and climatic conditions.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.