Grant: Alliance Grants

Food security is a global concern due to the ever-increasing population and limited agricultural land resources. Farmers use fertilizers and herbicides to ensure consistent crop establishment. However, overuse of fertilizers and other treatments leads to negative consequences resulting in soil depletion, environmental contamination, and pollution. An effective way to reduce these toxic chemicals is to apply the optimal amount based on crop/weed distribution. Uneven crop distribution adversely impacts crop production, and it is important to identify inconsistent areas within a field. Once inconsistent regions are identified, site-specific treatments can be prescribed. Site-specific farm management practices require high-resolution quantification of crop establishment like plant stand counting, leaf area estimation, inter-row spacing, inter-plant spacing, plants per crop row and plants per acre. Traditionally, manual scouting is performed to estimate these parameters, which is subjective, time-consuming, costly and not fully representative of the whole field. This research proposal aims to develop methods for quantifying crop establishment and biotic stress mapping using AI methods. Recently, highly accurate deep learning-based object detection methods have been developed. These methods are widely applied for non-agriculture applications like autonomous vehicles and medical imaging. However, in agriculture, plant features are not very distinctive, and field conditions are highly varied, which demands tailoring deep learning methods for agriculture data. In this research partnership, we are tailoring deep learning object detection and semantic segmentation models and image processing techniques to achieve the following objectives: 1) perform plant stand count for sparsely populated crops, 2) perform plant stand counting for densely populated cereal crops, 3) improve crop and weed density estimation models and 4) detect and quantify wild oats weed in narrow leaf cereal crops. The methods will automate the challenging task of ascertaining consistency of crop establishment at a large scale with higher spatiotemporal resolution.