I-Corps: Market research for unmanned aircraft system imaging of agricultural fields

Purdue University, West Lafayette IN

Investigators

Abstract

The broader impact of this I-Corps project is to promote the use of drones in agriculture and natural resource commercial endeavors and research. Due to scale, logistics, and lack of rural broadband internet access, there is a surprising lack of data in agriculture and agronomic research. At the same time, farmers and agronomists are in one way or another adapting to precision agriculture crop management and need high-resolution data at the landscape scale. This project will drastically reduce the time needed to generate accurate crop growth metrics from drone imagery, and then act on the information. Development of this project will improve data-driven decision-making in agriculture and agronomic research, including plant breeding and sustainable crop management. Data from our technology can be used for drone-based yield prediction for economic and value-chain applications, with information provided sooner than is available from current methods. This I-Corps project will reduce the cost and time to analyze unmanned aircraft system imagery of crop fields for quantification of metrics describing crop health, growth, and development, proactively during the season. The technology is software and workflows that use techniques from remote sensing, photogrammetry, and computer vision to automatically extract replicate images of research plots and management zones from raw drone imagery of crop fields, instead of relying on expensive and massive image ortho-mosaics and high-grade GPS measurements for plot extraction and analysis. The innovation can be applied in the field by eliminating the need for internet access or high-performance computers. The innovation also provides custom zoning of metrics, and quality control of the data generated. The innovation is an inexpensive method of high-throughput field phenotyping in the plant sciences. The innovation can contribute significantly to early-season yield prediction for a range of decision-making and forecasting applications. Implementation of regular consideration of growth analysis using inexpensive aerial imagery in the seed industry will improve genetic gain and product placement in precision agriculture management zones. Precision agriculture management will be facilitated by real-time, responsive, high-resolution assessments of crop health. Improved crop modeling and yield predictions are economically valuable to many sectors. 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.