Abstract
The classification of tree species through remote sensing data is of great significance to monitoring forest disturbances, biodiversity assessment, and carbon estimation. The dense time series and a wide swath of Sentinel-2 data provided the opportunity to map tree species accurately and in a timely manner over a large area. Many current studies have applied machine learning (ML) algorithms combined with Sentinel-2 images to classify tree species, but it is still unclear, which algorithm is more effective in the automotive extraction of tree species. In this study, five ML algorithms were compared to identify the composition of tree species with multitemporal Sentinel-2 images in the JianShe forest farm, Northeast China. Three major types of deep neural networks [Conv1D, AlexNet, and long short-term memory (LSTM)] were tested to classify Sentinel-2 time series, which represent three disparate but effective strategies to apply sequential data. The other two models are support vector machine (SVM) and random forest (RF), which are renowned for extensive adoption and high performance for various remote sensing applications. The results show that the overall accuracy of neural network models is better than that of SVM and RF. The Conv1D model had the highest classification accuracy (84.19%), followed by the LSTM model (81.52%), and the AlexNet model (76.02%). For non-neural network models, RF's classification accuracy (79.04%) is higher than that of SVM (72.79%), but lower than that of Conv1D and LSTM. Therefore, the deep neural networks combined with multitemporal Sentinel-2 images can efficiently improve the accuracy of tree species classification.
Highlights
THE number and distribution of tree species are related to ecosystem parameters such as biodiversity and habitat quality and are important indicators of forest ecological value [1], [2]
Support Vector Machine (SVM) and Random Forest (RF) as the representative non-neural-network classifier to compare with three neural network models, since these classifiers is renowned for high performance and is often established as the baseline model in classification tasks
Based on Sentinel-2 time series, the utility of five machine learning algorithms were evaluated for mapping tree species; the overall accuracy of all models is higher than 70%, especially deep neural network models
Summary
THE number and distribution of tree species are related to ecosystem parameters such as biodiversity and habitat quality and are important indicators of forest ecological value [1], [2]. Immitzer et al [9] analyzed 12 tree species classes in Central Europe with all possible combinations of multi-temporal Sentinel-2 scenes throughout year. They achieved overall accuracies of up to 85.7%. Lim et al [14] achieved an overall accuracy of 90% in the classification of five tree species in Goseong-gun, South Korea with multi-temporal Sentinel-2 images. These studies clearly demonstrate that the combination of abundant spectral information and time series Sentinel images provide an extraordinary advantage in distinguishing tree species
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
