Sbir phase II: real-time computer automated identification and quantification of insects entering the solarid insect control device (ICD)

The National Science Foundation (NSF) awarded a $981,168 Cooperative Agreement under its Technology, Innovation, and Partnerships (CFDA 47.084) program to Solarid Ar LLC, a minority-owned, veteran-owned, Asian-Pacific American-owned limited liability company. This 2-year project aims to develop an artificial intelligence (AI)-driven insect trapping and identification system that can detect, identify, and quantify insects entering insect control devices in real-time. The primary objective is to create an integrated pest management tool that attracts, captures, and images pest insects, identifies and counts them, and delivers data and management decisions to farmers. This technology is expected to enable more efficient and precise insect monitoring, leading to reduced chemical insecticide use and increased crop yields. The project will involve deploying the system in agricultural settings and using the collected insect data to train the AI-based insect identification system.

Abstract

The broader impacts of this small business innovation research (SBIR) phase II project include an artificial intelligence technology designed to detect, identify, and determine levels of insect infestations in fields, providing a comprehensive decision support system in real-time. More efficient and precise insect monitoring would result in reduced chemical insecticide use by increasing the specificity and timeliness of the applied input. Successful completion of the project could serve to increase the economic competitiveness of the U.S. In the world agricultural market, positively impact the health and welfare of the american public through reduced pesticide use, and introduce rural populations to technology highlighting the benefits of investment in science, technology, engineering and math (STEM) education. This technology could result in significant savings per acre through decreased expenditures on pesticides and decreased damage done by pests. Considering pests cause $45 billion per year in crop damage annually, and US farms spend more than $25 billion per year on pesticides, the savings to the industry could be substantial. The project provides an artificial intelligence (AI)-driven insect trapping system that can identify a broad diversity of insects in real-time. The primary objective of the project is to finish development of an integrated pest management tool that attracts, captures, and images pest insects, identifies and counts them in real-time, and delivers data and management decisions in a user-friendly format to internet-accessible devices. In order to achieve this objective, the technology will be deployed in several agricultural systems where they will continuously obtain data in the form of insect images. The insects in these images will be identified by experts and the data will be used to train the AI insect identification system. During the project, the system will learn to identify a diversity of important and commonly encountered insects in agricultural fields and orchards and a user-friendly interface for delivering results to users will be developed. The end goal is an all-in-one pest management tool that can be deployed in any agricultural system in the united states where IT can aid farmers in the management of pest problems while minimizing pesticide use and increasing yields. 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.- subawards are planned for this award.