1 of 33

Drone Data Bottlenecks

And How to Fix Them

Jeffrey K. Gillan

Research Data Scientist

jgillan@arizona.edu

Tyson L. Swetnam

Director of Open Science

tswetnam@cyverse.org

Tech & Research Initiative Fund (TRIF)

2 of 33

Animal Agriculture

Plant Agriculture

Construction

Infrastructure

Geology

Mining

Wildfire/Forestry

Ecosystem Monitoring

Disaster Management

3 of 33

Large Data Requirements

Meta-analysis of 204 peer-reviewed studies in Environmental Management

(Walker et al. 2023)

Top Barrier to Drone Use?

4 of 33

UAS data provide unique high spatiotemporal resolutions

UAS data is BIG

UAS Data Management is often ad hoc for each group

Wyngaard et al. 2019

Characteristics of Drone Data

5 of 33

Remote Sensing

Optical

MultiSpectral

Full motion video

Thermal

LiDAR

Hyperspectral

Synth. Aperture Radar

Drone Data Types

Other Data

Methane

Aerosol

Drone telemetry

Flight metadata

Digital Surface Model

Digital Terrain Model

Orthomosaic

Canopy Height Model

Derivative Products

Point Cloud

6 of 33

Drone Data LifeCycle

Data Collection

1

Data Sharing

5

Data Storage

4

Data Processing

2

Data Analysis

3

7 of 33

2024

A Survey of Drone Data Management - 55 Respondents

What is your most pressing UAS Data Need?

8 of 33

2024

Data Processing

Where do you Process your UAS Data?

9 of 33

2024

Data Processing

Current Processing Bottlenecks?

10 of 33

Data Processing

Processing Fixes

  1. Larger Computers

Expertise to help you use HPC and Cloud Computing

UofA HPC

11 of 33

2. Scripting

Data Processing

Processing Fixes

Metashape Scripting from Open Forest Observatory https://github.com/open-forest-observatory/automate-metashape

Free Metashape Licenses for Non-Commerical use https://github.com/jeffgillan/agisoft-metashape

Containerized Automation with OpenDroneMap

https://opendronemap.org/odm/

12 of 33

2024

Data Storage

Where do you store your UAS data?

13 of 33

Data Storage

Bottlenecks for Storing UAS Data?

Storage Volume - Not enough space

Storage Costs - Too expensive to host online

Input | Output - Too slow to read/write data

14 of 33

Storage Fixes

Drone Data Cloud Storage

Data Storage

15 of 33

To Give your Data a 2nd Life

So Colleagues can:

Reproduce, Build on, and Synthesize

Federal Policy1

1 https://www.whitehouse.gov/wp-content/uploads/2022/08/08-2022-OSTP-Public-Access-Memo.pdf

Data Sharing

Why Share Drone Data?

16 of 33

  • USGS Sciencebase
  • Ag Data Commons
  • USGS Earth Explorer
  • Environmental Data Initiative
  • Pangaea
  • Figshare
  • Zenodo
  • Oak Ridge Laboratory

Drone Data Repositories

Data Sharing

17 of 33

Stream Data from Cloud Storage to Any App

View and Analyze without Downloading

Serverless!

Data Sharing

Cloud Native Formats

18 of 33

Cloud Native Formats

FlatGeobuff

GeoParquet

Data Sharing

19 of 33

Building a Federated Global Catalog

of Open Geospatial Data

Data Sharing

MetaData

20 of 33

Standard JSON Format

Standard API

Data Sharing

MetaData

21 of 33

Data Sharing

MetaData

22 of 33

Data Analysis

rasterio

Free to Use Tools

23 of 33

Data Analysis

Deep Learning Tools

DeepForest - Tree crown object-detection

Restor Foundation - Tree Crown instance & semantic segmentation

Detectree2 - Instance segmentation of tree crowns

Detecto - Object detection of many things (need to fine-tune)

24 of 33

Data Analysis

Reproducible Pipelines

Photogrammetry

Fir

Pine

Spruce

ML Species Identification

Individual Tree Detection

25 of 33

Python Library: https://py.d2s.org/ available in PyPI

QGIS Plugin: D2S Browser

Github Repository: https://github.com/gdslab/data-to-science

Developed by: Jinha Jung & Ben Hancock (Purdue University)

Open-source Web Platform for Drone Data

Store | SfM Process | Visualize | Share

ps2.d2s.org

26 of 33

27 of 33

28 of 33

29 of 33

Python Library

https://py.d2s.org

30 of 33

QGIS Plugin: D2S Browser

31 of 33

Questions?

Comments?

Please Contact Me for Advice on Drone Data Management

Jeffrey K. Gillan

Data Science Institute

jgillan@arizona.edu

32 of 33

R. P. Abernathey et al., "Cloud-Native Repositories for Big Scientific Data," in Computing in Science & Engineering, vol. 23, no. 2, pp. 26-35, 1 March-April 2021, doi: 10.1109/MCSE.2021.3059437.

Barbieri, L, Wyngaard, J, Swanz, S and Thomer, AK. 2023. Making Drone Data FAIR Through a Community-Developed Information Framework. Data Science Journal, 22: 1, pp. 1–9. DOI: https://doi.org/10.5334/ dsj-2023-001. https://account.datascience.codata.org/index.php/up-j-dsj/article/download/dsj-2023-001/1154

Barnas, AF, Chabot, D, Hodgson, AJ, Johnston, DW, Bird, DM and Ellis-Felege, SN. 2020. A standardized protocol for reporting methods when using drones for wildlife research. Journal of Unmanned Vehicle Systems. Publisher: NRC Research Press. DOI: https://doi.org/10.1139/juvs-2019-0011

Eskandari R, Mahdianpari M, Mohammadimanesh F, Salehi B, Brisco B, Homayouni S. Meta-analysis of Unmanned Aerial Vehicle (UAV) Imagery for Agro-environmental Monitoring Using Machine Learning and Statistical Models. Remote Sens. 2020;12(21):3511

Fremand, Alice. Towards a data commons: Imagery and derived data from autonomous and remotely piloted aerial vehicles. UK Polar Data Centre, British Antarctic Survey This report is an output of Work Package 4 of the Environmental Data Service (EDS) UKRI DRI Phase 1b grant. November 2023 https://nora.nerc.ac.uk/id/eprint/536398/1/UAV_NERC_report.pdf

Guo J, Huang C, Hou J. A Scalable Computing Resources System for Remote Sensing Big Data Processing Using GeoPySpark Based on Spark on K8s. Remote Sensing. 2022; 14(3):521. https://doi.org/10.3390/rs14030521

James, MR, JH Chandler, A. Eltner, C. Fraser, PE Miller, JP Mills, T. Noble, S. Robson, and SN Lane. 2019. Guidelines on the use of structure-from-motion photogrammetry in geomorphic research. Earth Surface Processes and Landforms 44 (10), 2081-2084. https://doi.org/10.1002/esp.4637

Lachowiec, J., Feldman, M. J., Matias, F. I., LeBauer, D., & Gregory, A. (2024). Adoption of unoccupied aerial systems in agricultural research. The Plant Phenome Journal, 7(1), e20098.

La Salandra, M., Miniello, G., Nicotri, S., Italiano, A., Donvito, G., Maggi, G., ... & Capolongo, D. (2021). Generating UAV high-resolution topographic data within a FOSS photogrammetric workflow using high-performance computing clusters. International Journal of Applied Earth Observation and Geoinformation, 105, 102600.

Pereyra Irujo G, Bernaldo P, Velázquez L, Pérez A, Molina Favero C, Egozcue A (2023) Open Science Drone Toolkit: Open source hardware and software for aerial data capture. PLoS ONE 18(4): e0284184. https://doi.org/10.1371/journal.pone.0284184

Vithlani, H. N., Dogotari, M., Lam, O. H. Y., Prüm, M., Melville, B., Zimmer, F., & Becker, R. (2020, May). Scale Drone Mapping on K8S: Auto-scale Drone Imagery Processing on Kubernetes-orchestrated On-premise Cloud-computing Platform. In GISTAM (pp. 318-325).

Walker, S. E., Sheaves, M., & Waltham, N. J. (2023). Barriers to Using UAVs in Conservation and Environmental Management: A Systematic Review. Environmental Management, 71(5), 1052-1064. https://doi.org/10.1007/s00267-022-01768-8

Wilkinson, MD, Dumontier, M, Aalbersberg, IJ, Appleton, G, Axton, M, Baak, A, Blomberg, N, Boiten, J-W, da Silva Santos, LB, Bourne, PE, Bouwman, J, Brookes, AJ, Clark, T, Crosas, M, Dillo, I, Dumon, O, Edmunds, S, Evelo, CT, Finkers, R, Gonzalez-Beltran, A, Gray, AJG, Groth, P, Goble, C, Grethe, JS, Heringa, J, Hoen, PACT, Hooft, R, Kuhn, T, Kok, R, Kok, J, Lusher, SJ, Martone, ME, Mons, A, Packer, AL, Persson, B, Rocca-Serra, P, Roos, M, van Schaik, R, Sansone, S-A, Schultes, E, Sengstag, T, Slater, T, Strawn, G, Swertz, MA, Thompson, M, van der Lei, J, van Mulligen, E, Velterop, J, Waagmeester, A, Wittenburg, P, Wolstencroft, K, Zhao, J and Mons, B. 2016. The FAIR guiding principles for scientific data management and stewardship. Scientific Data, 3; 160018. DOI: https:// doi.org/10.1038/sdata.2016.18

Wyngaard, J.; Barbieri, L.; Thomer, A.; Adams, J.; Sullivan, D.; Crosby, C.; Parr, C.; Klump, J.; Raj Shrestha, S.; Bell, T. Emergent Challenges for Science sUAS Data Management: Fairness through Community Engagement and Best Practices Development. Remote Sens. 2019, 11, 1797. https://doi.org/10.3390/rs11151797

References

33 of 33

Open-source Web Platform for Drone Data

Store | SfM Process | Visualize | Share

ps2.d2s.org