Digital Agriculture Laboratory

There has been a significant expansion of UAS-based remote sensing in various industries, including agriculture and environmental research. However, the outcomes of remote sensing models are not generalizable because the ability to translate them to another time and space has been constrained by the lack of an efficient and trustworthy quantitative approach independent of the experiment circumstance. The sun-camera geometry is one of the most significant error factors degrading the UAS-based remote sensing data.

Selecting Optimal Multispectral Bands for Remote Sensing of Grapevine Nitrogen Using Hyperspectral Data

By Alireza Pourreza, and Ryan Omidi (Digital Agriculture Lab, UC Davis)

 Reference: Omidi, R., Moghimi, A., Pourreza, A., El-Hadedy, M., & Eddin, A. S. (2020). Ensemble Hyperspectral Band Selection for Detecting Nitrogen Status in Grape Leaves. arXiv preprint arXiv:2010.04225.

Moghimi, A., Pourreza, A., Zuniga-Ramirez, G., Williams, L. E., & Fidelibus, M. W. (2020). A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery. Remote Sensing, 12(21), 3515.