• Home
  • Search
  • Predicting Tree Mortality Using Spectral Indices Derived from Multispectral UAV Imagery
  • Cite Icon27
  • https://doi.org/10.3390/rs14092195Copy DOI Icon

Predicting Tree Mortality Using Spectral Indices Derived from Multispectral UAV Imagery

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Past research has shown that remotely sensed spectral information can be used to predict tree health and vitality. Recent developments in unmanned aerial vehicles (UAVs) have now made it possible to derive such information at the tree and stand scale from high-resolution imagery. We used visible and multispectral bands from UAV imagery to calculate a set of spectral indices for 52,845 individual tree crowns within 38 forest stands in western Canada. We then used those indices to predict the mortality of these canopy trees over the following year. We evaluated whether including multispectral indices leads to more accurate predictions than indices derived from visible wavelengths alone and how the performance varies among three different tree species (Picea glauca, Pinus contorta, Populus tremuloides). Our results show that spectral information can be effectively used to predict tree mortality, with a random forest model producing a mean area under the receiver operating characteristic curve (AUC) of 89.8% and a balanced accuracy of 83.3%. The exclusion of multispectral indices worsened the model performance, but only slightly (AUC = 87.9%, balanced accuracy = 81.8%). We found variation in model performance among species, with higher accuracy for the broadleaf species (balanced accuracy = 85.2%) than the two conifer species (balanced accuracy = 73.3% and 77.8%). However, all models overpredicted tree mortality by a major degree, which limits the use for tree mortality predictions on an individual level. Further improvements such as long-term monitoring, the use of hyperspectral data and cost-sensitive learning algorithms, and training the model with a larger and more balanced data set are necessary. Nevertheless, our results demonstrate that imagery from UAVs has strong potential for predicting annual mortality for individual canopy trees.

Loading PDF

Similar Papers
  • Preprint Article

Digital forest inventory based on UAV imagery

  • May 15, 2023
  • Steffen Dietenberger +7
  • Research Article

Estimating soil organic carbon using UAV and Sentinel-2 images and multilayer perceptron regression in Coastal Wetland

  • Jan 06, 2025
  • International Journal of Remote Sensing
  • Xia Lu +4
  • Research Article
  • Citations11

Estimating blue carbon accumulated in a halophyte community using UAV imagery: a case study of the southern coastal wetlands in South Korea

  • May 21, 2021
  • Journal of Coastal Conservation
  • Seong-Il Park +2
  • Research Article
  • Citations4

Height estimation of pine (Pinus eldarica) single trees using slope corrected shadow length on unmanned aerial vehicle (UAV) imagery in a plantation forest

  • Dec 27, 2023
  • Annals of Forest Research
  • Ali Hosingholizade +4
  • Research Article
  • Citations67

Multi-scale adversarial network for vehicle detection in UAV imagery

  • Sep 01, 2021
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Ruiqian Zhang +5
  • Preprint Article

3D Mapping of Rock Formations from Oblique and Nadir Viewing UAV Imagery

  • Mar 23, 2020
  • Kasper Johansen +8
  • Research Article
  • Citations25

Can reproducible comparisons of cereal genotypes be generated in field experiments based on UAV imagery using RGB cameras?

  • Apr 03, 2019
  • European Journal of Agronomy
  • Jesper Svensgaard +5
  • Research Article
  • Citations66

Estimating mangrove leaf area index based on red-edge vegetation indices: A comparison among UAV, WorldView-2 and Sentinel-2 imagery

  • Aug 13, 2021
  • International Journal of Applied Earth Observation and Geoinformation
  • Xianxian Guo +3
  • Research Article
  • Citations4

Beyond presence mapping: predicting fractional cover of non‐native vegetation in Sentinel‐2 imagery using an ensemble of MaxEnt models

  • Jan 17, 2023
  • Remote Sensing in Ecology and Conservation
  • Todd M Preston +3
  • Conference Article
  • Citations1

Development of field scale model for estimating barley growth based on UAV NDVI and meteorological factors

  • Oct 10, 2018
  • Chan-Won Park +4
  • PDF
  • Research Article
  • Citations9

UAV-Assisted Traffic Speed Prediction via Gray Relational Analysis and Deep Learning

  • Jun 02, 2023
  • Drones
  • Yanliu Zheng +3
  • Research Article
  • Citations10

Study on Reflectance and NDVI of Aerial Images using a Fixed-Wing UAV “Ebee”

  • Dec 01, 2016
  • Korean Journal of Soil Science and Fertilizer
  • Kyung­Do Lee +4
  • Research Article
  • Citations10

ELNet: An Efficient and Lightweight Network for Small Object Detection in UAV Imagery

  • Jun 18, 2025
  • Remote Sensing
  • Hui Li +2
  • Research Article
  • Citations19

Morpho-physiological variability of Pinus nigra populations reveals climate-driven local adaptation but weak water use differentiation

  • Jul 23, 2019
  • Environmental and Experimental Botany
  • Filippo Santini +6
  • Conference Article

Crown Segmentation of High-Resolution Coastal Mangrove Forest Imagery using Mask-RCNN: A Case in Batangas, Philippines

  • Dec 17, 2025
  • Amelia Abenoja +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.