SBIR Phase II: AI-based automated, portable, and high-throughput platform for early identification and characterization of potentially harmful microorganisms in aquaculture

点击翻译按钮获取中文摘要

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is the development of a cost-effective, high-performance platform to monitor and characterize plankton and other microorganisms in water. Some of these aquatic microorganisms may be harmful or even fatal resulting in significant public health concerns and economic consequences, such as billions lost annually in the aquaculture industry due to harmful algal blooms and sea lice. The current state of the art in monitoring technology includes laborious and expensive manual sample collections and evaluation. In contrast, the proposed platform may enable low-cost, portable and fast monitoring, as well as automated characterization of harmful aquatic microorganisms. Furthermore, this platform will enable a much wider application of the technology to other markets such as marine biology science and STEM education, general monitoring of particles and pathogens at the water treatment facilities, and production algae monitoring. The proposed technology is envisioned to have a significant societal impact and commercial potential.This project may result in a versatile, cost-effective, and high-throughput aquatic microobjects monitoring instrument. The instrument will have a wide spectrum of applications and initial focus on aquaculture market. The technology will initially focus on early identification of specific microorganisms, such as sea lice and harmful algae as they are detrimental to the wellbeing of aquaculture animals. This demonstration will provide high quality data at an affordable price to ensure confidence and credibility to aquaculture farmers, marine scientists, and other users interested in aquatic microobjects characterization. To accomplish this plan, several operating regimes will be implemented enabling the device to switch from high-resolution (monitoring harmful algae) to high-throughput (identifying sea lice). An autofluorescent camera module will be developed to further assist with differentiating microorganisms. Next, an innovative neural network framework will be developed and tested for identification of different types of sea lice and harmful algae. Finally, the system will be integrated into an environmentally protected enclosure and rigorously tested in laboratory, as well as in-field in realistic conditions. At the end of the Phase II program a prototype will be completed that will be designed in coordination with aquaculture partners and prospective users.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.