A Non-invasive Stem Water Potential Monitoring Method Using Proximate Sensor and Machine Learning Classification Algorithms

This chapter introduces a novel method for non-invasive monitoring of stem water potential using proximate sensors and machine learning classification algorithms. The chapter begins with an overview, emphasizing the significance of non-invasive techniques in understanding plant water status for effective agricultural management. The Materials and Methods section provides a detailed description of the walnut study area, the utilization of a radio frequency sensor for reflectance measurements, and the data collection and processing procedures. The implementation of scikit-learn classification algorithms is elucidated as a key component of the monitoring method. The Results and Discussion section presents findings and insights derived from the application of the proposed method. The chapter concludes with a summary, highlighting the potential of this non-invasive approach for stem water potential monitoring. This research opens avenues for advancing digital agriculture through enhanced water management practices. References are provided for further exploration of the methodologies and concepts discussed in this chapter.