A supervised neural network algorithm is used to categorize near-global satellite retrievals into three mesoscale cellular convective (MCC) cloud morphology patterns. At constant cloud amount, morphology patterns differ in brightness associated with the amount of optically-thin cloud features present. Environmentally-driven transitions from closed MCC to other morphology patterns, typically accompanied by a shift to more optically-thin cloud features, are used as a framework to quantify the morphology contribution to shortwave cloud feedback. Shifts in closed MCC occurrence associated with a marine heat wave were predicted as an out-of-sample test. Morphology shifts in optical-depth under projected environmental changes assuming constant cloud cover contributes between 0.05-0.09 W/m2/K (aggregate of 0.07) to the global mean cloud feedback.