**5. Conclusions**

This study presents a novel remote sensing-machine learning framework for modelling water stress in a Shiraz vineyard using terrestrial hyperspectral imaging. Based on the results of our study, we can draw the following conclusions:


Given the results obtained in the present study, we recommend the employment of RF, rather than XGBoost, for the classification of hyperspectral data to discriminate stressed from non-stressed Shiraz vines.

**Acknowledgments:** Winetech funded the research. The authors sincerely thank the SIMERA Technology Group for providing the hyperspectral sensor.

**Author Contributions:** Kyle Loggenberg, Nitesh Poona, and Albert Strever conceptualised the research; Kyle Loggenberg conducted the field work, carried out the main analysis, and wrote the paper; Nitesh Poona and Berno Greyling assisted in data analysis and field work; Nitesh Poona contributed to the interpretation of the results. Nitesh Poona, Albert Strever, and Berno Greyling contributed to the editing of the manuscript.

**Conflicts of Interest:** The authors declare no conflict of interest.
