TreeFinder is a large-scale, high-resolution benchmark dataset for mapping individual dead trees across the contiguous United States. The dataset is built from 0.6 m National Agriculture Imagery Program (NAIP) aerial imagery and provides pixel-level annotations and ecological metadata. It was created by ai-spatial and last updated on 2026-05-09.
Use Cases
- Train object detection models to identify dead trees based on high-resolution aerial imagery.
- Benchmark model performance for individual tree mortality mapping across diverse ecosystems.
- Analyze spatial patterns of tree mortality based on provided ecological metadata.
- Develop monitoring tools for forest health and pest/disease outbreaks.
Strengths
- Provides high-resolution 0.6 m aerial imagery from the National Agriculture Imagery Program.
- Covers a large geographic scale across the contiguous United States.
- Includes pixel-level annotations for individual dead trees.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Last updated 2026-05-09; freshness should be verified.
Provenance
- Source
- National Agriculture Imagery Program (NAIP) aerial imagery.
- Collection Method
- Built from aerial imagery with pixel-level annotations added.
- Freshness
- Last updated 2026-05-09 22:52:37.
- Geography
- Contiguous United States (CONUS).