Optimizing Soybean Planting Date to Develop Yield and Protein Prediction Model using Uncrewed Aerial Vehicles (UAVs) and Machine Learning Techniques across Kansas Agroclimatic Zones

This research project aims at optimizing early planting dates for soybeans in major growing regions of Kansas focusing on yield under diverse soil, climate, and environmental conditions. Building on previous research, the first objective investigates the correlation between different attributes to predict the yield by using different machine learning models and crop simulation modelling. The research will be carried out at multiple sites in Kansas, employing diverse planting dates, populations, and soybean cultivars. The second objective explores the potential of Uncrewed Aerial Vehicles (UAVs) in predicting soybean yield and quality through canopy spectra, structure, thermal and texture information based on planting dates. The justification for the study lies in the wide climatic variations across Kansas and the potential impact of early planting dates on soybean development. Optimizing planting dates can extend the growing season, enhance photosynthesis, and potentially increase yields, benefiting farmers economically. Node formation analysis is crucial for understanding soybean growth and maturity, aiding growers in making informed decisions. Additionally, investigating the influence of planting dates on soybean quality, including protein content and oil composition, is essential for meeting market standards. The project recognizes the challenges posed by climate change and positions early planting as a strategy to mitigate adverse effects, such as late-season frosts or heat stress. By optimizing planting dates, farmers can reduce vulnerability to extreme weather events, safeguarding their crops and investments. The integration of UAVs with various sensors offers a novel approach to capturing spatial and structural information about crop canopies, enhancing the accuracy of yield predictions, and providing valuable insights into crop growth dynamics.