Ultra-High Spatial Resolution Mapping of Urban Forest Canopy Height With Multimodal Remote Sensing Data and Deep Learning Method
Urban forest canopy height is an important indicator for urban carbon storage, vegetation ecosystems services, and devising effective forest management strategies to combat global climate change. Although both spaceborne or airborne light detection and ranging could offer forest canopy height inform...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10902494/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Urban forest canopy height is an important indicator for urban carbon storage, vegetation ecosystems services, and devising effective forest management strategies to combat global climate change. Although both spaceborne or airborne light detection and ranging could offer forest canopy height information, there presents a tradeoff between the spatial resolution and coverage. Addressing this, we aim to integrate the multimodal remote sensing data and digital elevation model (DEM) data to map ultra-high spatial resolution urban forest canopy height mapping over large urban area. We proposed ARFCNet, an innovative deep learning model that synergizes convolutional, self-attention, and upsampling mechanisms for precise forest canopy height mapping. ARFCNet processes data from autonomous aerial vehicles (AAV) imagery, Sentinel-1, and DEMs. We compare the potential of forest canopy height mapping under two data binning strategies: 1) involving aerial RGB imagery, Sentinel-1 HV, and 1-m resolution DEM, and 2) the same setup but with a 30-m resolution DEM. Our findings indicate that ARFCNet, under the first strategy, significantly outperforms than other models, achieving the highest <italic>R</italic><sup>2</sup> (0.98) and the lowest RMSE (1.33 m). The second strategy, utilizing 30-m resolution DEM, showed reduced accuracy, with an <italic>R</italic><sup>2</sup> of 0.78 and RMSE of 4.38. Furthermore, applying ARFCNet, we mapped 1-m resolution forest canopy heights in Guangzhou, revealing a citywide mean vegetation height of 12.45 m with a standard deviation of 4.26 m. Comparative validation against four existing canopy height products and field measurements in Guangzhou demonstrated our model's robustness, with <italic>R</italic><sup>2</sup> values ranging from 0.45 to 0.72 and RMSE from 3.93 to 6.04. Our ultra-high resolution (1 m) forest canopy height mapping offers detailed insights, particularly in urban areas, promising significant advancements in national or global vegetation monitoring, biomass mapping accuracy, and contributions toward carbon neutrality objectives. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |