Soybeans, weeds, and cover crop performance vary spatially across farm fields as a function of management, soils, and drainage. Therefore, maps of in-field performance (species, biomass, density) can aid farmers in planning their crop, soil, and pest management. These maps are particularly impactful when combined with precision variable rate applicators. The Precision Sustainable Agriculture (PSA) and Getting Rid of Weeds (GROW) networks are delivering low-cost technologies for sensing cover crop species and biomass, weed dynamics, and soybean health (e.g., WeedMap3D, SoyMap3D, CCMap3D, now packaged together and rebranded as PlantMap3D). These networks have a large, mature research and development team that is fine-tuning the technology, its applications, and the user experience. They also represent established research networks with demonstrated capacity to carry out on-farm and on-station research at a national scale. This project is a component of larger efforts to build technology and establish transfer pathways to enable commercialization of low-cost precision agriculture technologies that automate monitoring, analysis, and mapping of soybeans, cover crops, and weeds in U.S. soybean production for farmers and researchers. Computer vision tools for data collection developed by the GROW and PSA networks must have a user-interface that provides an intuitive and easy-to-use experience that consistently performs high quality data collection. Throughout the product development process, cycles of testing, feedback, and improvement are carried out with collaborating farmers to ensure that these tools are highly functional and easy to operate. This user-testing process facilitates iterative improvement of the individual hardware and software components and their integration into a seamless data collection platform. The ultimate determinant of how well this technology will be adopted is the user experience. Therefore, the specific goal of this project is to build a user-experience testing pipeline to farm-tune the technology with farmers and agricultural service providers, the primary target audience. Over the course of this project our team prepared for and began conducting user testing of the PlantMap3D system by: -Finalizing hardware and software integration for on-farm testing, -Training technical staff on installation of the hardware and configuration of the software, and providing technical support to agricultural service providers and farmers, -Finalizing survey instruments and protocols for in-person focus groups for collecting user feedback, -Deploying equipment to initial testing sites in North Carolina, Maryland, Texas, and Virginia, and -Holding a three day in-person training session at North Carolina State University in Raleigh, NC in mid-March 2024.

This project report represents the successful completion of the proposed work. Our goal is to build technology and establish transfer pathways to enable commercialization of low-cost precision agriculture technologies that automate monitoring, analysis, and mapping of soybeans, cover crops, and weeds in US soybean production for farmers and researchers. A computer vision tool for data collection must have a user-interface that provides an intuitive and easy-to-use experience that consistently performs high quality data collection. The user-experience testing pipeline developed by this project will now be used to farm-tune the technology with farmers and agricultural service providers. By the end of the larger project of which this work is a part we will translate our findings into refined tools that can be released to farmers and private industry, supporting the sustainability of US soybean production. Stakeholder engagement and accelerated adoption of the technology will be supported by the Getting Rid of Weeds (GROW) team’s outreach and extension specialists.