Development potential of nanoenabled agriculture projected using machine learning
The models quantify the synergistic effects among the surface charge, size, temperature, and NP exposure dose on plant growth and NP uptake and provide ideas for the design of environmentally friendly nanoenabled pesticides and fertilizers.
Abstract
Significance The development of nanotechnology has enabled precision and sustainable agriculture. The controllability and targeting of nanoparticles (NPs) will accelerate the development of modern agriculture. However, the development potential of nanoenabled agriculture remains unknown. Here, we built models of plant responses and uptake/transport of NPs using machine learning. Feature interaction and covariance analysis provide ideas for the design of environmentally friendly nanoenabled pesticides and fertilizers. The models quantify the synergistic effects among the surface charge, size, temperature, and NP exposure dose on plant growth and NP uptake. According to the prediction, Africa is a suitable area for nanoenabled agriculture, where a moderate temperature increase (approximately 6.0°) in the future may reduce the oxidative stress of bean induced by NPs.