Cyber-Collaborative Learning Protocol for Precision Agriculture (CCLP)

This chapter mainly introduces the Cyber-Collaborative Learning Protocol for Precision Agriculture (CCLP). CCLP is the Cyber-Collaborative Protocol (CCP) integrated with Machine Learning and Artificial Intelligence (ML&AI) techniques, enhancing CCP capabilities to indicate directions of stress propagation. Using an agriculture setting as an example, CCLP improves Agricultural Robotic System (ARS) performance by indicating the potential greenhouse stress propagation directions. The stress propagation is modeled as a disruption propagation network, providing a better understanding of the emergence and propagation of crop plant stress. The model provides the foundation for developing an innovative protocol for scanning crop plants. Five different scanning algorithms are developed in this chapter, including one algorithm based on Bayesian network inference analysis, which is used in CCLP as an ML&AI technique, three algorithms derived from disruption propagation network analytics, and a final algorithm that serves as the baseline. The protocol and algorithms have been implemented in agricultural settings, and computer simulation experiments have been conducted. The experiment results indicate that the CCLP outperforms other options and can indicate the potential directions in which stress propagates in a greenhouse.