Neural-Based Hierarchical Approach for Detailed Dominant Forest Species Classification by Multispectral Satellite Imagery

Abstract

Among different forest inventory problems, one of the most basic is defining dominant species. These data are crucial in forest management to determine forest category, and a cheaper remote sensing-based approach would be a useful supplement to field surveys. We used WorldView multispectral satellite imagery to address this problem as an image segmentation task dividing the image into regions with particular dominant species. Neural networks have recently become one of the most useful tools for this kind of problem, including incomplete or erroneous training labels. However, it is still challenging to distinguish between such similar patterns as different forest compositions. To handle this, we represented the multiclass forest classification problem as a hierarchical set of binary classification tasks, which allowed us to reach better results with both high- and medium-resolution satellite imagery. We also examined supplementary data, such as tree height, to improve the species classification results for wider tree age diversity. We conducted experiments considering six neural network architectures to find the best one for each task in the hierarchical decomposition. The proposed approach was tested on sample territories in Leningrad Oblast of Russia, for which the field-based observations were acquired and made publicly available as a single dataset. The proposed approach showed significantly better results (average F1-score 0.84) than multiclass classification (average F1-score 0.7).

Keywords

• Convolutional neural network (CNN)
• forest species classification
• remote sensing
• semantic segmentation