Mining Field Data for Tree Species Recognition at Scale

TL;DR

This paper introduces a method to automatically extract tree species labels from public forest data using pretrained detection models, enabling large-scale species mapping with minimal human effort.

Contribution

It presents a novel approach to mine species labels from existing data sources, reducing the need for expert annotation and facilitating large-scale ecological studies.

Findings

Adding noisy or unlabeled data improves species recognition accuracy.

The methodology achieves near-zero human involvement in data labeling.

Large-scale individual species mapping is feasible with the proposed approach.

Abstract

Individual tree species labels are particularly hard to acquire due to the expert knowledge needed and the limitations of photointerpretation. Here, we present a methodology to automatically mine species labels from public forest inventory data, using available pretrained tree detection models. We identify tree instances in aerial imagery and match them with field data with close to zero human involvement. We conduct a series of experiments on the resulting dataset, and show a beneficial effect when adding noisy or even unlabeled data points, highlighting a strong potential for large-scale individual species mapping.