Mapping and Classification of Trees Outside Forests using Deep Learning

TL;DR

Addressing multiclass Trees Outside Forests (TOF) mapping, the paper benchmarks six architectures (ABCNet, BANet, LSKNet, DC-Swin, FT-UNetFormer, U‑Net) on four TOF classes (Forest, Patch, Linear, Tree) using high-resolution RGB imagery from four German landscapes. The FT-UNetFormer emerges as the best model with $mIoU=0.74$ and $mF1=0.84$, underscoring the importance of spatial context modeling for boundary-rich TOF structures. A principled ground-truth generation workflow and a three-way spatial-generalization evaluation demonstrate the need for regionally diverse training data for large-scale TOF mapping, and the dataset and code are openly released. This work advances fine-grained ecological mapping in agricultural landscapes and supports scalable, policy-relevant agroforestry monitoring.

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

Figures (6)

• Figure 1: Location of the study areas in Germany with detailed insets for each region. The four study areas—Brandenburg (BB), North Rhine-Westphalia North (NRW_N), North Rhine-Westphalia South (NRW_S), and Schleswig-Holstein (SH) are outlined in different colors. White boxes indicate the locations of the representative testing tiles.
• Figure 2: Examples of the Trees Outside Forest (TOF) classes: Forest, Patch, Linear, and Tree.
• Figure 3: Training loss and validation mean Intersection over Union (mIoU) for the tested models (ABCNet, LSKNet, FT-UNetFormer, DC-Swin, BANet, and U-Net). Solid lines represent training loss, while dashed lines indicate validation mIoU.
• Figure 4: Comparison of Trees Outside Forest (TOF) mapping and classification results for all tested models in selected subregions.
• Figure 5: Results of the best-performing model (FT-UNetFormer) in four testing tiles.