The original data (emulated HHDCs) presented in the study entitled "Generative Diffusion Models for Compressed Sensing of Satellite LiDAR Data: Evaluating Image Quality Metrics in Forest Landscape Reconstruction" - Open Research Data - Bridge of Knowledge

Your account

login

Search

The original data (emulated HHDCs) presented in the study entitled "Generative Diffusion Models for Compressed Sensing of Satellite LiDAR Data: Evaluating Image Quality Metrics in Forest Landscape Reconstruction"

Description

The dataset contains four subsets of original data (emulated HHDCs) presented in the study entitled "Generative Diffusion Models for Compressed Sensing of Satellite LiDAR Data: Evaluating Image Quality Metrics in Forest Landscape Reconstruction" submitted to the journal "Remote Sensing".

The raw LiDAR data, being the source for the emulated HHDCs, centered on the Smithsonian Environmental Research Center
(SERC) in the state of Maryland (Latitude 38.88° N, Longitude 76.56° W) are available at NEON (National Ecological Observatory Network) website: Discrete return LiDAR point cloud (DP1.30003.001), RELEASE-2024. https://doi.org/10.48443/hj77-kf64.

A dataset of emulated HHDCs was created using high-resolution point clouds from the SERC region. The input low-resolution HHDC footprints were modeled with a uniform diameter of 10 meters, spaced 3 meters apart along the swath and 6 meters across the swath, with a vertical resolution of 0.5 meters (these values were chosen to match the LiDAR instrument currently under development as part of NASA’s CASALS project). These HHDCs were standardized to a fixed size of 16 × 32 × 128 (footprints across the swath × footprints along the swath × height), corresponding to a forest tile covering 96 × 96 meters with a height of 64 meters. For super-resolution to 3 meters, the high-resolution output HHDC footprints were designed to increase the resolution while maintaining the same coverage area. Specifically, the footprints were assigned a radius of 3 meters, with a 3-meter separation both along and across the swath, and a vertical resolution of 0.5 meters. This configuration resulted in a tensor size of 32 × 32 × 128 while preserving the original 96 × 96 meters area. Using the approach described above, four subsets were created using different sizes of reconstructed areas defined by the lengths of square sides equal to 576 m, 288 m, 144 m, and 96 m.

The dataset was created within the joint IMPRESS-U project entitled ”EAGER IMPRESS-U: Exploratory Research on Generative Compression for Compressive Lidar” co-funded by U.S. National Science Foundation NSF under Grant No. 2404740, Science & Technology Center in Ukraine (STCU) Agreement No. 7116, and National Science Centre, Poland (NCN), Grant no. 2023/05/Y/ST6/00197.

Dataset file

HHDC_Dataset.zip
4.8 GB, S3 ETag ceef611c973bfeee3654ee62a4a64dac-10, downloads: 0
The file hash is calculated from the formula
hexmd5(md5(part1)+md5(part2)+...)-{parts_count} where a single part of the file is 512 MB in size.

Example script for calculation:
https://github.com/antespi/s3md5

File details

License:
Creative Commons: by 4.0 open in new tab
CC BY
Attribution
File embargo:
2025-03-14

Details

Year of publication:
2025
Verification date:
2025-03-13
Creation date:
2024
Dataset language:
English
Fields of science:
  • information and communication technology (Engineering and Technology)
DOI:
DOI ID 10.34808/3dk4-ah25 open in new tab
Funding:
Verified by:
West Pomeranian University of Technology in Szczecin

Keywords

Cite as

Authors

seen 18 times