In this talk, we introduce our novel digital tools to predict chemical/mechanical & physical performance loss of adhesives due to aging in extreme environments. Our physics-informed machine-learned tools need very few accelerated aging tests andcan predict the long-term performance of adhesives under multiple environmental loads with high accuracy. The study also presents a comprehensive characterization of the mechanical and chemical properties of adhesives before and after exposure to extreme temperatures, humidity, and UV radiation. The proposed approach enables the prediction of adhesive performance over extended periods of time, allowing for better design of adhesive-based materials and structures. The results of this study demonstrate the effectiveness of informed machine-learned tools in predicting the performance of adhesives in extreme environments, providing a valuable tool for engineers and researchers in the field of materials science and engineering.