The DAISy Lab @ USU

The DAISy (Digital Agro-environment and Intelligent Systems) Lab aims to advance our understanding of the natural environment by developing new use cases for mobile and optical sensor systems to monitor environmental and agricultural processes.

The lab currently has two major thrusts:

(1) non-destructive, optical sensing to model and predict characteristics of biological materials, and

(2) integrating sensing and sampling technologies with mobile aerial and aquatic vehicles for informative environmental monitoring.

Current applications of interest and pursuit include evaluating water quality using UAS, measuring earth surface processes with ground-based instrumentation, and monitoring crops across various production systems with optical sensors.

Selected Recently Completed and Ongoing Projects

Advancing camera-based monitoring for operational hydrologic applications

To address the challenges of implementing low-cost cameras into hydrologic monitoring, this project funded by the U.S. Geological Survey focuses on integrating existing and cutting-edge computer vision algorithms, AI models, and computational tools into a camera-based monitoring system. These systems will be deployed at selected sites, and the images and video, along with advanced processing algorithms, will generate data on water levels and surface velocity.

Stay tuned for publications currently in progress!

Surface and aerial vehicles to advance water quality monitoring for aquaculture

Our ongoing project through the National Robotics Initiative aims to develop surface and aerial vehicles for smart sampling of coliform bacteria. In collaboration with faculty from NC State, we are currently integrating water quality models with sampling and planning strategies for shellfish production areas along the coast of NC. Field studies are ongoing -- stay tuned for more publications in progress!

Publications:

Nguyen, A., Ore, J.P., Castro-Bolinaga, C., Hall, S., Young, S. (2024). Towards autonomous, optimal water sampling with aerial and surface vehicles for rapid water quality assessment. Journal of the ASABE. doi.org/10.13031/ja.15796

Hyperspectral imaging for managing industrial hemp

Through a project funded by the NC Ag Foundation, we developed methods using hyperspectral imagery to evaluate the growth stage, cultivar, and cannabinoid content in industrial hemp flowers and leaves. This project also aimed at understanding the effects of harvest date and transplant date on biomass and cannabinoid production.

Publications:

Lu, Li, Young, Li, Linder, Suchoff (2022). Hyperspectral imaging with chemometrics for non-destructive determination of cannabinoids in floral and leaf materials of industrial hemp (Cannabis sativa L.). Computers and Electronics in Agriculture, doi.org/10.1016/j.compag.2022.107387.

Linder, Young, Li, Henriquez-Inoa, Suchoff (2022). The Effect of Harvest Date on Temporal Cannabinoid and Biomass Production in the Floral Hemp (Cannabis sativa L.) Cultivars BaOx and Cherry Wine. Horticulturae, 8(10), 959, doi.org/10.3390/horticulturae8100959.

Lu, Young, Linder, Whipker, Suchoff. (2022). Hyperspectral imaging with machine learning to differentiate cultivars, growth stages, flowers and leaves of industrial hemp (Cannabis sativa). Frontiers in Plant Science, doi.org/10.3389/fpls.2021.810113.

Linder, Young, Li, Henriquez-Inoa, Suchoff (2022). The Effect of Transplant Date and Plant Spacing on Biomass Production for Floral Hemp (Cannabis sativa L.). Agronomy, doi.org/10.3390/agronomy12081856.

Hyperspectral imaging to advance breeding of Loblolly pine

In collaboration with the NC Tree Improvement Program, we developed methods for high-throughput screening of loblolly pine seedlings for disease and cold tolerance. Notably, this work found that the top half of the stem contains the most information for identifying rust disease post-inoculation. Further, we were able to predict the mean minimum winter temperature of the seed source using hyperspectral images of seedlings prior to exposure to freezing events.

Publications:

Lu, Walker, Payn, Acosta, Young, Pandey, Heine (2021). Prediction of freeze damage and minimum winter temperature of the seed source of loblolly pine seedlings using hyperspectral imaging. Forest Science, doi:10.1093/forsci/fxab003.

Lu, Payn, Pandey, Acosta, Heine, Walker, Young (2021). Hyperspectral imaging with cost-sensitive learning for high-throughput screening of loblolly pine (Pinus taeda L.) seedlings for freeze tolerance. Transactions of the ASABE, doi.org/10.13031/trans.14708.

Pandey, Payn, Lu, Heine, Walker, Acosta, Young (2021). Hyperspectral Imaging Combined with Machine Learning for the Detection of Fusiform Rust Disease Incidence in Loblolly Pine Seedlings. Remote Sensing, doi.org/10.3390/rs13183595

See this download [links to .zip file] for details on how to build our low-cost, motorized belt for hyperspectral scanning in a greenhouse

Exploring new applications for aerial vehicles

Our group is interested in exploring new ways to expand the capabilities of and find new uses for aerial platforms for agricultural and environmental applications. Recently, we've developed a lightweight payload for performing controlled pollinations in loblolly pine orchards. Other areas of ongoing exploration include soil moisture measurement, water quality monitoring, and water sampling.

Publications:

Pandey*, Acosta, Payn, and Young, Towards autonomous, aerial pollination: Design of a robotic pollinator payload for controlled crosses in loblolly pine. Applied Engineering in Agriculture, vol. 40, no. 6, 2024. doi.org/10.13031/aea.15916.

Young, Lanciloti, Peschel (2022). The Effects of Interface Views on Performing Aerial Telemanipulation Tasks using Small UAVs. International Journal of Social Robotics. doi.org/10.1007/s12369-021-00783-9.

Page updated

Google Sites

Report abuse