Mapping and Classification of Trees Outside Forests using Deep Learning

2025-10-29

AI Summary

Traditional approaches to “trees outside forests” (TOF) often oversimplify them into a single class or rely on rigid thresholds, limiting ecological representativeness. Method: This study proposes a fine-grained semantic segmentation framework for TOF using high-resolution aerial imagery, introducing the first systematic four-class taxonomy—forest, patch, linear structure, and individual tree—and evaluating six models (U-Net, ABCNet, LSKNet, FT-UNetFormer, DC-Swin, BANet) with CNN, ViT, and hybrid architectures to assess spatial context modeling for complex vegetation delineation. Results: FT-UNetFormer achieves state-of-the-art performance (mean IoU = 0.74, F1 = 0.84), excelling in forest and linear structure segmentation; patch and individual-tree classes remain challenging due to dense boundaries. We release the first publicly available multi-class TOF dataset with pixel-level annotations and open-source code, substantially enhancing model reproducibility and regional generalizability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Distributed Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Trees Outside Forests (TOF) play an important role in agricultural landscapes by supporting biodiversity, sequestering carbon, and regulating microclimates. Yet, most studies have treated TOF as a single class or relied on rigid rule-based thresholds, limiting ecological interpretation and adaptability across regions. To address this, we evaluate deep learning for TOF classification using a newly generated dataset and high-resolution aerial imagery from four agricultural landscapes in Germany. Specifically, we compare convolutional neural networks (CNNs), vision transformers, and hybrid CNN-transformer models across six semantic segmentation architectures (ABCNet, LSKNet, FT-UNetFormer, DC-Swin, BANet, and U-Net) to map four categories of woody vegetation: Forest, Patch, Linear, and Tree, derived from previous studies and governmental products. Overall, the models achieved good classification accuracy across the four landscapes, with the FT-UNetFormer performing best (mean Intersection-over-Union 0.74; mean F1 score 0.84), underscoring the importance of spatial context understanding in TOF mapping and classification. Our results show good results for Forest and Linear class and reveal challenges particularly in classifying complex structures with high edge density, notably the Patch and Tree class. Our generalization experiments highlight the need for regionally diverse training data to ensure reliable large-scale mapping. The dataset and code are openly available at https://github.com/Moerizzy/TOFMapper

Problem

• Classifying Trees Outside Forests using deep learning models
• Mapping four woody vegetation categories from aerial imagery
• Addressing regional adaptability in tree classification systems

Innovation

• Deep learning models for tree classification
• Hybrid CNN-transformer architecture FT-UNetFormer
• Open dataset with four woody vegetation categories