Machine Learning to Predict the Interfacial Behavior of Pesticide Droplets on Hydrophobic Surfaces for Minimizing Environmental Risk
Authors:
Ridan Song, Yanling Wu, Zhenping Bao, Yuxia Gao
Publisher:
ACS Sustainable Chem. Eng.
Abstract:
Achieving accurate and efficient target deposition of pesticide droplets is the principal factor in minimizing environmental risk. For hydrophobic surfaces, adding tank-mix adjuvants containing surfactants to modulate interfacial behavior is warranted, which lacks common laws to guide practical applications directly. Machine learning is developing rapidly and makes many data-based decisions in various industrial processes. Hence, according to machine learning-based analysis of fundamental physical quantities, proposing quantitative sustainability metrics to improve interface behavior is essential. Comparing the interfacial behavior of five adjuvants, the common denominator is that droplets in the Wenzel state with higher adhesion tension and lower contact angles can generate the pinning force that causes energy dissipation, reduces pesticide losses, and weakens environmental pollution. Simultaneously, the interfacial behavior of pesticide droplets including adjuvants on citrus leaves is verified, while the phytotoxicity experiment under high temperature and the laboratory bioassay are carried out. The results show that the eco-friendly alkyl polyglycoside (APG) as the glycosidic surfactant has nontarget biosafety and better mite control, which can be exploited as a commercial tank-mix adjuvant for promotion. This study provides a new insight into guiding adjuvants added to pesticides on account of quantitative sustainability metrics, which has important implications for food safety and agricultural green development.
