Detection of woody species Schinopsis haenkeana using phenological spectral differences and NDVI texture measures in subtropical forests

SILVETTI LUNA; BELLIS LAURA M.

Remote Sensing Applications: Society and Environment

Elsevier

Lugar: Amsterdan; Año: 2024

2352-9385

Schinopsis haenkeana is a native tree species of great importance of South America.Different tree species diverge in their vegetation phenology, providing the opportunityto map their presence based on the seasonal dynamics of vegetation indices.Currently, spatially explicit information on tree species composition provides valuableinsights for biodiversity conservation. The objective of this study was to detect thepresence of S. haenkeana and its forest status in subtropical forests in centralArgentina. We used a combination of RGB-NIR bands and indices (NDVI, EVI, GLI,RGR) derived from Sentinel-2 images. The analyses were processed using the EarthEngine platform and the random forest algorithm was used to discriminate S.haenkeana from other plant species. NDVI texture indices were also used todiscriminate different forest states where the species is present. A fruiting period and aleaf color change were detected in July, and spectral differences between fruiting andpreceding (May) or subsequent (October) months proved to be highly suitable fordiscriminating S. haenkeana. The final species presence map achieved an overallaccuracy of 91%. Only 0.76% of the total area corresponds to S. haenkeana denseforests. This analysis demonstrated the value of the proposed approach for regularlydetecting and mapping S. haenkeana using RGB-NIR spectral information, vegetationindices, and phenological spectral differences. Additionally, it highlighted theimportance of using texture indices to differentiate between forests and scrublands,providing suitable data for forest management.