Walnut rootstocks are commonly used in California orchards to provide resistance to soil-borne pests and diseases. However, little information exists about the impact of commercial rootstock on the common scion's physiological response under drought. This is becoming increasingly important since walnuts are commonly cultivated in semi-arid regions where frequent and severe droughts require efficient water use. We previously reported that own-rooted walnut rootstocks (RX1, VX211 and Vlach) differ in their physiological performance under drought. Here, we evaluated whether similar water relations and performance are conferred to a common English walnut scion (Juglans regia cv. Cisco). To do so, we used a mini-lysimeter platform to continuously track soil moisture and transpirational water loss from trees. Along with the canopy's estimated leaf area, changes in canopy shape and texture were evaluated using deep learning as an independent method to analyze canopy response to water stress. In support of our recent findings, the scion grafted onto rootstock RX1 exhibited subtle improvements in physiological performance associated with higher transpiration and canopy conductance under well-watered condition compared to Vlach and VX211 rootstocks. Canopy conductance, texture, and shape were not significantly affected by rootstock under water stress. However, Cisco grafted onto RX1 exhibited higher leaf turgor and water use efficiency, and lower osmotic potentials under water stress. Our results suggest some subtle differences in water relations between the rootstock genotypes, and propose an efficient deep-learning method to screen canopies for water stress-induced response through image processing.