New Pest Identification App is Available

Have you ever wondered what a particular plant or insect is in your field, yard, or garden? We have all been there, and we have great news: a new tool is available for farmers everywhere! Iowa State University's Pest ID App is now available. Developed by ISU researchers, the Pest ID app uses deep learning models trained on millions of images to recognize weeds and insects directly from your photo.

Simply take a photo of an unknown insect or weed, upload it to the app, and it will identify it and provide additional background information. This tool could bring meaningful changes to farmers everywhere with its unique local-to-global model design. A regional model is trained on the weeds and insects common to an area, providing fast, accurate identifications, while the global model covers thousands of species and can flag a pest new to the region. Identifying pest issues sooner helps those who have fewer local resources. Users can learn about issues as they arise, allowing farmers to respond faster and correct problems earlier, protecting crop yields from potential loss. Each time users use the app, its accuracy improves, helping more crop producers. Researchers are also working to add a disease identification feature. You can access Iowa State University's Pest ID app from your browser on most devices.

For more information on the Pest ID App, reach out to Arti Singh, Associate Professor of Agronomy, at arti@iastate.edu or Wesley Everman, Extension Weed Science Specialist and Assistant Professor, at weverman@iastate.edu.

Links to this article are strongly encouraged, and this article may be republished without further permission if published as written and if credit is given to the author, Integrated Crop Management News, and Iowa State University Extension and Outreach. If this article is to be used in any other manner, permission from the author is required. This article was originally published on September 3, 2026. The information contained within may not be the most current and accurate depending on when it is accessed.