Leveraging phenology to assess seasonal variations of plant communities for mapping dynamic ecosystems
Seasonally dynamic plant communities complicate remote mapping, but phenology can reveal periods of maximum spectral distinction. In a temperate wetland complex, NDVI time‑series from Sentinel imagery were used to identify optimal months for classifying vegetation. Ground‑referenced phenology showed strong seasonal differences, with April–June and September-October providing the clearest separation among communities. Merging phenologically similar groups improved accuracy, and combining April and September imagery produced the highest classification performance (~77%). Random Forest models relied heavily on elevation, near‑infrared and tasseled cap indices. Despite higher spatial resolution, PlanetScope underperformed due to limited spectral separation. Integrating phenology into mapping frameworks enhances detection of rare and ephemeral vegetation, supporting more effective conservation planning.
Subject Tags
- Wetlands
- Biodiversity
- Conservation Planning
Abstract
Seasonally dynamic plant communities present challenges for remote mapping, but estimating phenology can help identify periods of peak spectral distinction. While phenology is widely used in environmental and agricultural mapping, its broader ecological applications remain underexplored. Using a temperate wetland complex as a case study, we leveraged NDVI time series from Sentinel imagery to refine a wetland classification scheme by identifying periods of maximum plant community distinction. We estimated plant phenology with ground-reference points and mapped the study area using Random Forest (RF) with both Sentinel and PlanetScope imagery. Most plant communities showed distinct phenological variations between April–June (growing season) and September–October (transitional season). Merging phenologically similar communities improved classification accuracy, with April and September imagery yielding better results than the peak summer months. Combining both seasons achieved the highest classification accuracy (~77%), with key RF predictors including digital elevation, and near-infrared and tasseled cap indices. Despite its higher spatial resolution, PlanetScope underperformed compared to Sentinel, as spectral similarities between plant communities limited classification accuracy. While Sentinel provides valuable data, higher spectral resolution is needed for distinguishing similar plant communities. Integrating phenology into mapping frameworks can improve the detection of rare and ephemeral vegetation, aiding conservation efforts.
Citation
Surasinghe, T. D., Singh, K. K., & Smart, L. S. (2025). Leveraging phenology to assess seasonal variations of plant communities for mapping dynamic ecosystems. Remote Sensing, 17(10), 1778. https://doi.org/10.3390/rs17101778
TNC Authors
-
Lindsey S. Smart
Adaptation and Resilience Scientist
The Nature Conservancy
Email: lindsey.smart@tnc.org