Project Number: 6064-21660-001-046-S
Project Type: Non-Assistance Cooperative Agreement
Start Date: Jun 1, 2023
End Date: May 31, 2028
1. Develop, expand, and deploy high throughput data acquisition and analytics systems and platforms for multi-faceted data streams to improve the sustainability and relevancy of agricultural production systems and ecosystem services with an emphasis on soil health, production inputs, water conservation, water quality, and GHG emissions. 1.A. Develop and evaluate a multi-sensor platform technology for within-the-canopy data collection and machine learning models for high throughput approaches to soybean, pea, and dry bean crop development. 2. Advance engineering and computational technologies for cropping system best management practices and ecosystem services through innovations in precision agriculture, digital transformations, advanced hardware and software technologies, autonomous systems, computer vision, and artificial intelligence. 2.A. Develop and evaluate AI-enabled techniques and systems for in-field monitoring of crop growth status by multisource remote/proximal sensing and meteorological observations to provide data and information to regulate the performance of the cropping and animal production systems 2.B. Determine the ‘essential data resolution’ needed to develop effective models to quantitatively estimate crop resiliency at the genotype, environment, management, and its interactions by utilizing statistical analytics, machine learning and artificial intelligence methods. 2.C. Create the next-generation predictive and prescriptive tools for selection and deployment of climate-resilient cultivars adapted to the region.
Experimental Design 2.C.1: “Multi-sensor platform for UGV”. (NDSU). Hypothesis: Automated pod count technology can improve field trial efficiency and outcomes. This project proposes to research and develop a multi-sensor platform mounted to an autonomous UGV that will cover three plots wide and allow for route and automated mission planning for data collection. In addition, this proposed project will develop algorithms to automate data collection, catalogue and organize images, test machine learning models, and identify the most accurate process that detects and counts pods in soybeans, peas, and dry beans. Models will also be developed to predict plot yield prior to harvest. Experimental Design 3.A.1: “Novel approaches to remote sensing in cropping systems”. (NDSU & ARS). Goal: Integrate proximal imaging, AI, and robotic technologies to provide effective site-specific weed management and soil health assessment for improved cropping systems xperiment 3.A.2: “Precision agricultural technology for livestock production practices”. (NDSU). Goal: Using sensors, computer vision, and AI technologies, determine correlations between beef quality and pre-harvest factors (behavior and health) to improve livestock production practices. Experimental Design 3.B.2: “Develop regional row crop modeling system integrated with remote sensing and ML” (ARS & NDSU). Goal: Use AI, big data, ML, and other statistical methods as important drivers to understand complex agricultural ecosystems which will impact crop variety development and management. Experimental Design 3.D.1: “Genomic selection predictive models for breeding programs”. (NDSU). Goal: Identify and develop Genomic Selection (GS) predictive models to be applied to breeding programs to predict genomic estimated breeding values (GEBVs) of individuals in testing populations.