article · Computers and Electronics in Agriculture
Uncrewed aerial vehicles offer flexible, high-resolution alternatives to ground surveys for assessing forest health. Combining ground observations with multispectral drone imagery collected across 235 monitoring plots in Bavaria over three years produced a standardised reference pipeline. Using the EfficientNet convolutional neural network, the system classified 14 categories encompassing five tree species, three genus-level groups, dead trees, and specific health conditions. The model attained an average macro F1-score of 0.61, performing best on dead trees with an F1-score of 0.97 and healthy Norway spruce with 0.80. This open-source approach demonstrates how integrating automated aerial data with ground surveys can streamline crown condition assessments across varied lighting and stand environments, lowering operational monitoring costs.
Traditional ground-based surveys of forest canopies are labour-intensive and costly to maintain over vast regions. Using drones equipped with multispectral cameras alongside deep learning models allows forestry organisations to track crown conditions and tree mortality across heterogeneous landscapes. This semi-automated approach supports more frequent and scalable environmental assessments, assisting land managers in detecting forest stress and guiding conservation measures under varying weather conditions.
The methodology offers applied data pipelines and neural network models for forest management agencies, conservation organisations, and forestry survey contractors. As an applied, tested system using open-source tools across multi-year field trials, it provides immediate utility for large-scale programmes such as ICP Forests. Integrating these automated drone workflows enables users to reduce manual ground surveys, cutting operational monitoring expenses while maintaining consistent regional canopy health data.
AI-generated from the published abstract. Always read the original work before citing.
Uncrewed Aerial Vehicles (UAVs) have emerged as a promising tool for complementing terrestrial surveys, offering unique advantages for forest health monitoring (FHM). UAVs have the potential to improve or even replace core tasks such as crown condition assessment, bridging the gap between ground-based surveys and traditional remote sensing platforms. However, present approaches have not yet fully exploited the very high temporal resolution and flexible and convenient utilization that UAVs offer even under cloudy skies. In this paper, we provide a standardized data pipeline to semi-automatically generate reference data and for monitoring forest health by merging ground-based and UAV-based data related to species-specific forest health. Furthermore, we investigated the potential of Convolutional Neural Networks (CNNs) to classify the main tree species and their crown conditions based on the reference data. Therefore, we acquired high resolution multispectral drone imagery of 235 different ICP large scale forest monitoring plots (Level-I plots) distributed across Bavaria for three consecutive years (2020–2022). Using this highly heterogeneous time-series dataset, encompassing diverse weather and lighting conditions, forest stand characteristics, and spatial distribution of study areas, we successfully classified five tree species, three genus level classes and dead trees, including the health status of the main tree species occurring in Germany. This way we managed to classify 14 distinct classes with an average macro F1-score of 0.61 using the EfficientNet CNN architecture. The highest class-specific F1-score apart from the class of dead trees (0.97) was achieved by the class of Picea abies healthy (0.80). If participating countries of the ICP Forests program adopt our approach to harmonize terrestrial and UAV-based monitoring, many ground-based tasks could be reduced or replaced, leading to significant time and cost savings. We provide standardized and open-source monitoring and analysis strategies that can be potentially extended throughout Europe. Our findings demonstrate that UAV monitoring and deep learning can modernize forest management for efficiency and sustainability. We recommend integrating drones with ground surveys in forest monitoring systems to take advantage of their benefits.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.compag.2024.108785
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
