Forest ecosystems play a fundamental role in natural balances and climate mechanisms through their contribution to global carbon storage. Their sustainable management and conservation is crucial in the current context of global warming and biodiversity conservation. To tackle such challenges, Earth observation data has been identified as a valuable source of information capable to provide stakeholders with informative indicators to support the decision making process related to forest ecosystems management. While Earth observation data constitutes an unprecedented opportunity to monitor forest ecosystems, its effective exploitation still poses serious challenges since multimodal (i.e. multi-scale and multi-source) information need to be combined in order to describe complex natural phenomena. To deal with this particular issue in the context of structure and biophysical variables estimation for forest characterization, we propose a new deep learning based fusion strategy to combine together high density 3D-point clouds acquired by airborne laser scanning (ALS) with high resolution optical imagery freely accessible via the Sentinel-2 mission. In order to manage and fully exploit the available multi-modal information, we implement a two-branch late fusion deep learning architecture taking advantage of the specificity of each modality: on the one hand, a 2D-CNN branch is devoted to the analysis of Sentinel-2 time series data and, on the other hand, a Multi-Layer Perceptron branch is dedicated to the processing of LiDAR-derived information. The whole framework is learnt end-to-end in order to effectively exploit the complementarity between the two sources of information. The performance of our framework is evaluated on two forest variables of interest: total volume and basal area at stand level. The obtained results underline that the availability of multi-modal remote sensing data is not a direct synonym of performance improvements but, the way in which they are combined together is of paramount importance to leverage the complex interplay among the different input sources.
The Global Ecosystem Dynamics Investigation (GEDI), specifically designed to measure vertical forest structures, has acquired, since April 2019, more than 35 billion waveforms of Earth’s surface on a nearly global scale. GEDI is equipped with 3 identical 1064 nm lasers with a power of 10 mJ per shot, where 1 laser is split into 2 lasers, resulting in 2 5 mJ coverage lasers and 2 10 mJ full-power lasers. In this study, we evaluate the potential of GEDI’s four lasers to penetrate through canopies and detect the ground, and their capabilities to detect the top of the canopies over a tropical forest (in French Guiana) characterized by a dense canopy cover and tall trees. The accurate detection of both of these surfaces is the first step in characterizing vertical forest structures. The SRTM Digital Elevation Model (DEM) is used as a reference point for elevations while a canopy height model (CHM), derived from airborne and spaceborne LiDAR data, is used as a reference for canopy heights. In addition, the ground and canopy-top elevations estimated from NASA’s Land, Vegetation, and Ice Sensor (LVIS, 1064 nm full-waveform LiDAR, 5 mJ per shot, ~8 km altitude) are used as a benchmark for comparison with GEDI’s lasers. Results indicate that GEDI’s coverage and full-power lasers, even after the application of a preliminary filter that removes around 50% of acquisitions, tend to underestimate tree heights in densely vegetated, tall forests. Moreover, GEDI’s coverage lasers also exhibited a lower level of performance in comparison to both the full-power lasers and LVIS. Overall, the average estimated maximum canopy heights (RH100) for a CHM greater than 30 m was 24.4 m with the coverage lasers, 32.1 m with the full-power lasers, and 36.7 m with LVIS. The analysis of shots with high-beam sensitivity (sensitivity ≥ 98%) showed that they tend to have a better probability of reaching the ground and have better detection of canopy tops for both GEDI laser types. Nonetheless, GEDI’s coverage lasers still showed an underestimation of canopy heights with an average RH100 of 29.8 m, while for GEDI’s full-power lasers and LVIS, the average RH100 was 35.2 m and 37.7 m, respectively. Finally, the assessment of the acquisition time on the detection of the ground return and the top of the canopies showed that, for the coverage lasers, solar noise could affect the detection of the ground return as acquisitions made during early mornings or late afternoons have more penetration than shots acquired between 8 a.m. and 4 p.m. The effect of acquisition time on the detection of the tops of canopies showed that solar noise slightly affected the coverage lasers. Regarding the full-power lasers, the acquisition time of the shots seem to affect neither the penetration of the lasers, nor the detection of the tops of canopies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.