This research examines how agricultural sprays are formed at the moment of atomization, where nozzle geometry, operating pressure, and liquid formulation determine the droplet population that enters the surrounding flow. Using shadowgraph imaging and data-driven interpretation, the work studies how sprays from standard ASABE nozzle classes change across coarse-to-fine atomization regimes and how those changes can be recognized from the spray structure itself. A central contribution is showing that image-based methods can recover meaningful information about atomization state, including nozzle class and pressure condition, without relying exclusively on expensive laboratory droplet-sizing systems.
Infographic
Research infographic
NotebookLM-generated infographic and video assets for this research subcategory. Click any image to open the full-size file, or play videos directly on the page.
Ag Spray & Deep LearningDeep Learning for Spray Drift
Contributors
Students who contributed to this work
Students connected to the publications and projects represented on this page.
B. N. Narayanan, Joseph Ivarson, Lars Maneck, Sidaard Gunasekaran , “Deep Learning Algorithm for Atomization Characterization using Shadowgraph Images”, 2021 IEEE National Aerospace and Electronics Conference (NAECON), Dayton, OH, USA, 2021. 10.1109/NAECON49338.2021.9696443
