Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Low-Cost Tree Crown Dieback Estimation Using Deep Learning-Based Segmentation

M. J. Allen, D. Moreno-Fernández, P. Ruiz-Benito, S. W. D. Grieve, E. R. Lines

TL;DR

The paper tackles the challenge of large-scale, high-frequency forest dieback monitoring by combining low-cost RGB drone imagery with deep learning to automatically delineate individual tree crowns (ITCs) and derive crown-based dieback metrics. It demonstrates that Mask R-CNN can reliably segment ITCs in a structurally complex, monospecific Pinus pinea canopy, and that green chromatic coordinate (GCC) derived from these crown footprints correlates significantly with field-based defoliation estimates (R^2 ≈ 0.34–0.35). Importantly, the dieback estimates remain robust when replacing model-derived crowns with manual crowns, indicating resilience to segmentation accuracy and potential for non-expert deployment. The work provides open code and data, highlights substantial speed and cost reductions over traditional field campaigns, and lays the groundwork for scalable, RGB-based forest health monitoring in drought-affected ecosystems.

Abstract

The global increase in observed forest dieback, characterised by the death of tree foliage, heralds widespread decline in forest ecosystems. This degradation causes significant changes to ecosystem services and functions, including habitat provision and carbon sequestration, which can be difficult to detect using traditional monitoring techniques, highlighting the need for large-scale and high-frequency monitoring. Contemporary developments in the instruments and methods to gather and process data at large-scales mean this monitoring is now possible. In particular, the advancement of low-cost drone technology and deep learning on consumer-level hardware provide new opportunities. Here, we use an approach based on deep learning and vegetation indices to assess crown dieback from RGB aerial data without the need for expensive instrumentation such as LiDAR. We use an iterative approach to match crown footprints predicted by deep learning with field-based inventory data from a Mediterranean ecosystem exhibiting drought-induced dieback, and compare expert field-based crown dieback estimation with vegetation index-based estimates. We obtain high overall segmentation accuracy (mAP: 0.519) without the need for additional technical development of the underlying Mask R-CNN model, underscoring the potential of these approaches for non-expert use and proving their applicability to real-world conservation. We also find colour-coordinate based estimates of dieback correlate well with expert field-based estimation. Substituting ground truth for Mask R-CNN model predictions showed negligible impact on dieback estimates, indicating robustness. Our findings demonstrate the potential of automated data collection and processing, including the application of deep learning, to improve the coverage, speed and cost of forest dieback monitoring.

Low-Cost Tree Crown Dieback Estimation Using Deep Learning-Based Segmentation

TL;DR

The paper tackles the challenge of large-scale, high-frequency forest dieback monitoring by combining low-cost RGB drone imagery with deep learning to automatically delineate individual tree crowns (ITCs) and derive crown-based dieback metrics. It demonstrates that Mask R-CNN can reliably segment ITCs in a structurally complex, monospecific Pinus pinea canopy, and that green chromatic coordinate (GCC) derived from these crown footprints correlates significantly with field-based defoliation estimates (R^2 ≈ 0.34–0.35). Importantly, the dieback estimates remain robust when replacing model-derived crowns with manual crowns, indicating resilience to segmentation accuracy and potential for non-expert deployment. The work provides open code and data, highlights substantial speed and cost reductions over traditional field campaigns, and lays the groundwork for scalable, RGB-based forest health monitoring in drought-affected ecosystems.

Abstract

The global increase in observed forest dieback, characterised by the death of tree foliage, heralds widespread decline in forest ecosystems. This degradation causes significant changes to ecosystem services and functions, including habitat provision and carbon sequestration, which can be difficult to detect using traditional monitoring techniques, highlighting the need for large-scale and high-frequency monitoring. Contemporary developments in the instruments and methods to gather and process data at large-scales mean this monitoring is now possible. In particular, the advancement of low-cost drone technology and deep learning on consumer-level hardware provide new opportunities. Here, we use an approach based on deep learning and vegetation indices to assess crown dieback from RGB aerial data without the need for expensive instrumentation such as LiDAR. We use an iterative approach to match crown footprints predicted by deep learning with field-based inventory data from a Mediterranean ecosystem exhibiting drought-induced dieback, and compare expert field-based crown dieback estimation with vegetation index-based estimates. We obtain high overall segmentation accuracy (mAP: 0.519) without the need for additional technical development of the underlying Mask R-CNN model, underscoring the potential of these approaches for non-expert use and proving their applicability to real-world conservation. We also find colour-coordinate based estimates of dieback correlate well with expert field-based estimation. Substituting ground truth for Mask R-CNN model predictions showed negligible impact on dieback estimates, indicating robustness. Our findings demonstrate the potential of automated data collection and processing, including the application of deep learning, to improve the coverage, speed and cost of forest dieback monitoring.
Paper Structure (20 sections, 1 equation, 5 figures, 2 tables, 1 algorithm)

This paper contains 20 sections, 1 equation, 5 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Material & Methodology
  3. Data
  4. Study Area & Inventory
  5. Drone Imagery
  6. Manual Delineation & Training Data
  7. Methods
  8. ITC Delineation via Instance Segmentation
  9. Vegetation Index-Based Dieback Estimates at the Tree Level
  10. Results
  11. Discussion
  12. Conclusions
  13. Residual Plots
  14. Crown Matching
  15. Abbreviations
  16. ...and 5 more sections

Figures (5)

  • Figure 1: (a) Map showing the location of the site described by our data in the Iberian peninsula. Map data from openstreetmap. (b) Histogram of visually estimated defoliation (percentage needles missing) of adult trees in our field data. An estimate of 1.0 corresponds to a tree for which all foliage is dead, and 0.0 to a tree with completely healthy foliage. 453 adult trees (DBH > 7.5cm) were surveyed in total.
  • Figure 2: (a) Unlabelled, (b) manual, and (c) automatically predicted crown polygons for both healthy crowns (left, bottom right) and crowns exhibiting dieback (top centre, bottom centre). Numbers next to the class name 'tree' denote confidence score corresponding to each prediction. Images in this figure span approximately 30m.
  • Figure 3: Dispersion plots of Estimated Green Chromatic Coordinate (GCC) vs. field-based defoliation at the individual tree level.
  • Figure 4: Correlation between Green Chromatic Coordinate (GCC) estimated using manually labelled vs. automatically segmented crowns. Crowns are matched according to the corresponding inventory trunk location from the crown matching algorithm. The RMSE between the two GCC estimates was found to be 0.01, with $p<3\times10^{-72}$.
  • Figure 5: Plot of GCC residuals from OLS vs. Distance from inventory trunk location to matched polygon.