Focal Interest
Focal Interest

Geospatial analysis

  1. Geospatial foundation models improved tree species mapping accuracy
    Foundation models outperform conventional satellite methods for tree species classification in mountain forests, achieving high accuracy with minimal training data but requiring nonlinear classifiers.
  2. Target-only PFAS data can still differentiate overlapping sources
    Tiered PFAS fingerprinting framework for source differentiation using targeted analytics, diagnostic ratios, isomer patterns, and geospatial analysis in complex industrial groundwater settings.
  3. geeLite simplifies local databases for Google Earth Engine outputs
    geeLite R package simplifies building local SQLite databases from Google Earth Engine data, enabling longitudinal environmental monitoring and time series analysis with portable.