News
News
Apply Machine Learning Algorithms for Optimizing Lettuce Production, Ensuring Food Safety, and Mitigating Environmental Impact
August, 2024
The proposal aims to apply machine learning algorithms to develop robust classification, estimation, and prediction models for lettuce crops thus enhancing production efficiency and food safety while minimizing the environmental impact. The project has four specific objectives: (1) To develop mathematical models to assess plant nutritional and water status from spectral data; (2) To irrigate lettuce plants using egg-washing wastewater as sustainable water and natural fertilizer sources; (3) To investigate the challenges and opportunities of using egg-washing wastewater for lettuce irrigation; (4) To analyze and model the spatio-temporal dynamics of mineral element composition in lettuce leaves during plant development.
Societal implications of Clean Energy Tractors for Farming
May, 2024
The project aims to implement a cohesive methodology and strategy to assess the societal implications of introducing and easing the acceptance of clean energy tractors by engaging all potential interested parties (producers, engineers, business and industry representatives, educators, policymakers, and consumers) from the beginning of the innovation processes while considering social, cultural, economic, legal, educational, and environmental aspects.
Fully Automated Controlled Environment Agriculture at NDSU.
September, 2024
The project focuses on automating drip irrigation systems for lettuce production using soil sensors and machine learning to conserve water and nutrients while maintaining plant health. Water and nutrient balances are quantified to enhance conservation in controlled environments. Energy efficiency is addressed through innovative solar modules for greenhouses, maximizing solar radiation, generating electricity, and boosting crop yields. Additionally, the team conducts outreach and educational activities, integrating these advancements into coursework and training programs for students.
Farm Weed Control Solution Based on Edge-AI and UGV Systems
March, 2024
Weed control is critically important to farm operations. Farmers need effective solutions for weed control with less herbicide and more environmentally friendly techniques. This project will develop a cooperative UGV weed recognition and spraying system with advanced Edge-AI technology. A multi-tank target spraying UGV system will be designed and developed based on existing multifunctional UGVs, which will use its onboard computer vision system to precisely spray all targeted weeds in the field. This project has assembled an interdisciplinary team of experts that includes a weed scientist, an autonomous vehicle engineer, and an artificial intelligence engineer. This precision agriculture research project will make an impact on the North Dakota farming industry and beyond.
Fusion of Machine Learning and Electromagnetic Sensors for Real-Time Local Decisions in Agriculture
August, 2024
The overall goal of this multi-year project is to bring together personnel from both USDA and NDSU to develop novel DC-to-Light electromagnetic sensors, and unique field-ready platforms to bring sensors to the grower and fuse them with Machine Learning for real-time decision-making. The project will focus on the following objectives: (1) Partner with USDA and various constituents to conduct fundamental research on new electromagnetic sensor technologies for agriculture; (2) Carry out an extensive technology readiness level study of existing sensor technologies and apply them to agriculture; (3) Develop Machine Learning (ML) theory specific for edge computing, electromagnetic sensors and applications in agriculture; (4) Implement secure Information Technology (IT) platforms for this initiative; and (5) Align and deploy these new technologies in the field for grower needs.