In the face of global warming and the pressing need for sustainable energy solutions, efficient energy storage devices have become paramount. Developing such systems requires exploring their parameter space and assessing durability. Traditionally, exploration has often been done randomly and inefficiently and proved to be time-consuming, resource-intensive, and limited in its ability to quantify failure probabilities. Here we introduce a novel approach that leverages statistical and machine learning techniques, specifically Gaussian Process regression and expected information gain of future experiments, to navigate the parameter space of energy storage systems efficiently. By integrating experts' domain knowledge, our methodology minimizes the number of experiments while accurately quantifying probability failure distributions. Experimental results demonstrate the effectiveness and efficiency of our approach in optimizing parameter space exploration and durability testing. This work holds promise for expediting the development and optimization of energy storage, facilitating renewable energy integration, and contributing to a more sustainable future.