Combining machine learning and publicly available aerial data (NAIP and NEON) to achieve high-resolution remote sensing of grass-shrub-tree mosaics in the Central Great Plains (U.S.A.)

Abstract

Woody plant encroachment (WPE)—a phenomenon similar to species invasion—is shifting many grasslands and savannas into shrub and evergreen-dominated ecosystems. Tracking WPE is difficult because shrubs and small trees are much smaller than the coarse resolution of common remote sensing platforms (> 10 m 2 ) and the impassibility of encroaching woody thickets slows ground-based approaches. Many agencies have been investing in fine resolution ( 90%), with the NEON-based models a few percent more accurate than NAIP. A model using both inputs had the highest accuracy. However, the accuracies of NAIP and NEON models differed for woody vegetation: compared to NEON, NAIP accuracy was, 82-93% compared to 94-98% for shrubs, 72-92% compared to 93-98% for deciduous trees, and 52-78% compared to 83-86% for evergreen trees (specifically Juniperus virginiana ). NEON-based models relied on canopy height (LiDAR) to make classifications, whereas the several bands of light make similar contributions to accuracy in the NAIP models. Finally, we found that both machine learning approaches had similar accuracy, but random forests ran substantially faster. We conclude that with large training datasets, publicly available aerial imagery and similar products (e.g., UAVs, micro-satellites) can produce fine-scale, high-accuracy remote sensing of WPE in this region with low up-front costs.

Plant phenotyping relevance

航空画像・LiDARと機械学習を用いて低木・樹木の植生状態を高解像度で推定し、NAIPとNEONおよび手法間の精度を比較しており、植物状態の取得・推定法が研究の中心である。

Code and data availability

The authors deposited their paper-specific training/classification dataset (ground-truthed and computer-drawn vegetation polygons for Konza Prairie) publicly on EDI. The analysis code is only 'private-for-peer review' on Figshare, so it does not qualify as a public asset. NEON and NAIP imagery are generic third-party平台