Abstract
Remote sensing technology provides an economical and efficient means for obtaining the distribution of dominant tree species. However, remote sensing mapping of dominant tree species have remained an ongoing challenge, such as massive data and low accuracy of a single machine learning method, especially over large-scale mountainous areas. In this study, the multi-source variables and multi-classifier decision fusion was used to separate the dominant tree species on the Google Earth Engine cloud computing platform. We combined with multi-source data such as Sentinel-2 satellite imagery, bioclimate, topography, and forest inventory data and constructed time series for NDVI and REP to evaluate different variables combinations. At the same time, tree species classification was carried out following two approaches: non-stratified and stratified. Four different Machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), XGBoost, and Maximum Entropy (MaxEnt) were used as component classifiers to construct two decision fusion models of serial integration and Bayesian parallel integration respectively and completed the spatial distribution of 10 main dominant tree species mapping in the mountainous areas of northwest Yunnan. The nine tree species were classified with an overall accuracy of 74.44% using serial integration of MaxEnt and RF. This study confirmed that combination of multi-source data multi-source variables and the decision fusion method can be used to provide a reference for the classification of dominant tree species in large-scale mountainous areas.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Torahi, A.A., Chand Rai, S.: Land cover classification and forest change analysis, using satellite imagery-a case study in Dehdez area of Zagros Mountain in Iran. J. Geogr. Inf. Syst. 3(1), 1 (2011)
White, J.C., et al.: Remote sensing technologies for enhancing forest inventories: a review. Can. J. Remote Sens. 42(5), 619–641 (2016)
Chambers, D., et al.: Challenges in modelling the abundance of 105 tree species in eastern North America using climate, edaphic, and topographic variables. For. Ecol. Manag. 291, 20–29 (2013)
Lehmann, J.R.K., et al.: Analysis of unmanned aerial system-based CIR images in forestry—A new perspective to monitor pest infestation levels. Forests 6(3), 594–612 (2015)
Shang, X., Chisholm, L.A.: Classification of Australian native forest species using hyperspectral remote sensing and machine-learning classification algorithms. IEEE J. Select. Topics Appl. Earth Observ. Remote Sens. 7(6), 2481–2489 (2013)
Hyde, P., et al.: Mapping forest structure for wildlife habitat analysis using multi-sensor (LiDAR, SAR/InSAR, ETM+, Quickbird) synergy. Remote Sens. Environ. 102(1–2), 63–73 (2006)
Holmgren, P., Thuresson, T.: Satellite remote sensing for forestry planning—a review. Scand. J. For. Res. 13(1–4), 90–110 (1998)
Ferro-Famil, L., Pottier, E., Lee, J.-S.: Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier. IEEE Trans. Geosci. Remote Sens. 39(11), 2332–2342 (2001)
Korpela, I., et al.: Tree species classification using airborne LiDAR–effects of stand and tree parameters, downsizing of training set, intensity normalization, and sensor type. Silva Fennica 44(2), 319–339 (2010)
Fricker, G.A., et al.: A convolutional neural network classifier identifies tree species in mixed-conifer forest from hyperspectral imagery. Remote Sens. 11(19), 2326 (2019)
Hartling, S., et al.: Urban tree species classification using a WorldView-2/3 and LiDAR data fusion approach and deep learning. Sensors 19(6), 1284 (2019)
Hościło, A., Lewandowska, A.: Mapping forest type and tree species on a regional scale using multi-temporal Sentinel-2 data. Remote Sens. 11(8), 929 (2019)
Kollert, A., et al.: Exploring the potential of land surface phenology and seasonal cloud free composites of one year of Sentinel-2 imagery for tree species mapping in a mountainous region. Int. J. Appl. Earth Observ. Geoinf. 94, 102208 (2021)
Grabska, E., Frantz, D., Ostapowicz, K.: Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the polish carpathians. Remote Sens. Environ. 251, 112103 (2020)
Cheng, K., Wang, J., Yan, X.: Mapping forest types in China with 10 m resolution based on spectral–spatial–temporal features. Remote Sens. 13(5), 973 (2021)
Ponti Jr, M.P.: Combining classifiers: from the creation of ensembles to the decision fusion. In: 2011 24th SIBGRAPI Conference on Graphics, Patterns, and Images Tutorials. IEEE (2011)
Vasilakos, C., Kavroudakis, D., Georganta, A.: Machine learning classification ensemble of multitemporal Sentinel-2 images: the case of a mixed mediterranean ecosystem. Remote Sens. 12(12), 2005 (2020)
Gorelick, N., et al.: Google earth engine: planetary-scale geospatial analysis for everyone. Remote Sens. Environ. 202, 18–27 (2017)
Qiu, Y., et al.: Spatiotemporal fusion method to simultaneously generate full-length normalized difference vegetation index time series (SSFIT). Int. J. Appl. Earth Observ. Geoinf. 100, 102333 (2021)
Gandhi, I., Pandey, M.: Hybrid ensemble of classifiers using voting. In: 2015 International Conference on Green Computing and Internet of Things (ICGCIoT). IEEE (2015)
Modzelewska, A., et al.: Multitemporal hyperspectral tree species classification in the Białowieża forest world heritage site. For.: Int. J. For. Res. 94(3), 464–476 (2021)
Zhong, L., Gong, P., Biging, G.S.: Efficient corn and soybean mapping with temporal extendability: a multi-year experiment using Landsat imagery. Remote Sens. Environ. 140, 1–13 (2014)
Zeng, L., et al.: A review of vegetation phenological metrics extraction using time-series, multispectral satellite data. Remote Sens. Environ. 237, 111511 (2020)
Wang, C., et al.: Phenology-assisted classification of C3 and C4 grasses in the US Great Plains and their climate dependency with MODIS time series. Remote Sens. Environ. 138, 90–101 (2013)
Li, R., et al.: Classifying forest types over a mountainous area in southwest China with landsat data composites and multiple environmental factors. Forests 13(1), 135 (2022)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grants 32160369, 31860182, 41961053, and 41771375, in part by the Key Development and Promotion Project of Yunnan Province under Grant 202102AE090051; in part by the Fund of Reserve Talents for Young and Middle-Aged Academic and Technological Leaders of Yunnan Province under Grant 2018HB026.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zheng, P., Fang, P., Liu, P., Xu, W., Wang, G., Wang, L. (2023). Dominate Tree Species Classification on Large-Scale Mountainous Areas Using Voting Strategy-Based Ensemble Learning Method. In: Wang, L., Wu, Y., Gong, J. (eds) Proceedings of the 8th China High Resolution Earth Observation Conference (CHREOC 2022). CHREOC 2022. Lecture Notes in Electrical Engineering, vol 969. Springer, Singapore. https://doi.org/10.1007/978-981-19-8202-6_10
Download citation
DOI: https://doi.org/10.1007/978-981-19-8202-6_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8201-9
Online ISBN: 978-981-19-8202-6
eBook Packages: EngineeringEngineering (R0)