ac

Comparative Analysis of Machine Learning Algorithms for Multi-Class Tree Species Classification Using Airborne LiDAR Data

Authors

  • Gregorius Airlangga Atma Jaya Catholic University of Indonesia

DOI:

10.47709/brilliance.v4i1.3673

Keywords:

LiDAR Remote Sensing, Tree Species Classificatio, Machine Learning Algorithms, Forest Ecology, Airborne LiDAR Data Analysis

Dimension Badge Record



Abstract

Forests hold vital ecological significance, and the ability to accurately classify tree species is integral to conservation and management practices. This research investigates the application of machine learning techniques to airborne Light Detection and Ranging (LiDAR) data for the multi-class classification of tree species, specifically Alder, Aspen, Birch, Fir, Pine, Spruce, and Tilia. High-density LiDAR data from varied forest landscapes were subjected to a rigorous preprocessing and noise reduction protocol, followed by feature extraction to discern structural characteristics indicative of species identity. We assessed the performance of six machine learning models: Logistic Regression, Decision Tree, Random Forest, Support Vector Classifier (SVC), k-Nearest Neighbors (KNN), and Gradient Boosting. The analysis was based on metrics of accuracy, precision, recall, and F1 score. Logistic Regression and Random Forest models outperformed others, achieving accuracies of 0.81, precision of 0.80, recall of 0.81, and an F1 score of 0.80. In contrast, the KNN algorithm had the lowest accuracy of 0.60, precision and recall of 0.60, and an F1 score of 0.59. These results demonstrate the robustness of Logistic Regression and Random Forest for classifying complex LiDAR datasets. The study underscores the potential of these models to support ecological monitoring, enhance forest management, and aid in biodiversity conservation. Future research directions include the fusion of LiDAR data with other environmental variables, application of deep learning for improved feature extraction, and validation of the models across broader species and geographical ranges. This research marks a significant step towards leveraging advanced machine learning to interpret and utilize LiDAR data for environmental and ecological applications.

Google Scholar Cite Analysis
Abstract viewed = 63 times

References

Blanco, J. A., Ameztegui, A., & Rodr’iguez, F. (2020). Modelling Forest Ecosystems: A crossroad between scales, techniques and applications. Ecological Modelling, Vol. 425, p. 109030. Elsevier.

Camarretta, N., Harrison, P. A., Bailey, T., Potts, B., Lucieer, A., Davidson, N., & Hunt, M. (2020). Monitoring forest structure to guide adaptive management of forest restoration: a review of remote sensing approaches. New Forests, 51, 573–596.

Chehreh, B., Moutinho, A., & Viegas, C. (2023). Latest Trends on Tree Classification and Segmentation Using UAV Data—A Review of Agroforestry Applications. Remote Sensing, 15(9), 2263.

El-Omairi, M. A., & El Garouani, A. (2023). A review on advancements in lithological mapping utilizing machine learning algorithms and remote sensing data. Heliyon.

Gao, Y., Skutsch, M., Paneque-Gálvez, J., & Ghilardi, A. (2020). Remote sensing of forest degradation: a review. Environmental Research Letters, 15(10), 103001.

Gharineiat, Z., Tarsha Kurdi, F., & Campbell, G. (2022). Review of automatic processing of topography and surface feature identification LiDAR data using machine learning techniques. Remote Sensing, 14(19), 4685.

Hastings, J. H., Ollinger, S. V, Ouimette, A. P., Sanders-DeMott, R., Palace, M. W., Ducey, M. J., … Orwig, D. A. (2020). Tree species traits determine the success of LiDAR-based crown mapping in a mixed temperate forest. Remote Sensing, 12(2), 309.

Iljas, T. (2022). Using Very High Resolution Remotely Piloted Aircraft Imagery to Map Peatland Vegetation Composition and Configuration Patterns within an Elevation Gradient. University of Waterloo.

Illarionova, S., Trekin, A., Ignatiev, V., & Oseledets, I. (2021). Tree species mapping on sentinel-2 satellite imagery with weakly supervised classification and object-wise sampling. Forests, 12(10), 1413.

Krivoguz, D. (2024). Geo-spatial analysis of urbanization and environmental changes with deep neural networks: Insights from a three-decade study in Kerch peninsula. Ecological Informatics, 102513.

Ma, Y., Zhao, Y., Im, J., Zhao, Y., & Zhen, Z. (2024). A deep-learning-based tree species classification for natural secondary forests using unmanned aerial vehicle hyperspectral images and LiDAR. Ecological Indicators, 159, 111608.

Mackey, B., Kormos, C. F., Keith, H., Moomaw, W. R., Houghton, R. A., Mittermeier, R. A., … Hugh, S. (2020). Understanding the importance of primary tropical forest protection as a mitigation strategy. Mitigation and Adaptation Strategies for Global Change, 25(5), 763–787.

Micha?owska, M., & Rapi?ski, J. (2021). A review of tree species classification based on airborne LiDAR data and applied classifiers. Remote Sensing, 13(3), 353.

Mohammadpour, P., & Viegas, C. (2022). Applications of Multi-Source and Multi-Sensor Data Fusion of Remote Sensing for Forest Species Mapping. Advances in Remote Sensing for Forest Monitoring, 255–287.

Muluneh, M. G. (2021). Impact of climate change on biodiversity and food security: a global perspective—a review article. Agriculture & Food Security, 10(1), 1–25.

Nitoslawski, S. A., Wong-Stevens, K., Steenberg, J. W. N., Witherspoon, K., Nesbitt, L., & van den Bosch, C. C. (2021). The digital forest: Mapping a decade of knowledge on technological applications for forest ecosystems. Earth’s Future, 9(8), e2021EF002123.

Rapinel, S., & Hubert-Moy, L. (2021). One-class classification of natural vegetation using remote sensing: a review. Remote Sensing, 13(10), 1892.

Sentinel3734. (2023). UAV Point Clouds of Individual Trees.

Wang, C. K. (2023). Sentiment Analysis Using Support Vector Machines, Neural Networks, and Random Forests. 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023), 23–34.

Xi, Z., Hopkinson, C., & Chasmer, L. (2024). Supervised terrestrial to airborne laser scanner model calibration for 3D individual-tree attribute mapping using deep neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, 209, 324–343.

Xu, D., Wang, H., Xu, W., Luan, Z., & Xu, X. (2021). LiDAR applications to estimate forest biomass at individual tree scale: Opportunities, challenges and future perspectives. Forests, 12(5), 550.

Yip, K. H. A., Liu, R., Wu, J., Hau, B. C. H., Lin, Y., & Zhang, H. (2024). Community-based plant diversity monitoring of a dense-canopy and species-rich tropical forest using airborne LiDAR data. Ecological Indicators, 158, 111346.

Downloads

ARTICLE Published HISTORY

Submitted Date: 2024-02-29
Accepted Date: 2024-03-01
Published Date: 2024-03-08

How to Cite

Airlangga, G. (2024). Comparative Analysis of Machine Learning Algorithms for Multi-Class Tree Species Classification Using Airborne LiDAR Data. Brilliance: Research of Artificial Intelligence, 4(1), 32-37. https://doi.org/10.47709/brilliance.v4i1.3673