Understanding the movement of ions through a material is crucial to understanding important properties such as radiation, stress cracking, and ion conductivity. Fundamentally, these dynamics are determined by the relevant energy barriers to ion motion. As such, in order to advance our understanding of the mechanisms of materials processes for complex systems, there is a need to determine the energy landscapes for such ionic motion. However, determining complete maps of high-dimensional landscapes is currently not computationally feasible for systems with a large number of atoms or defects, mainly because of the challenge of finding all of the energy transition states (TSs). Without all of the TSs for a system, the simulator may not be able to uncover important mechanisms that govern the dynamics of material processes. While there exist efficient methods for finding a single TS, the problem of finding all TSs in a high-dimensional phase space is currently computationally intractable. Thus, there is an urgent need for an efficient and scalable method for finding all of the TSs in a high-dimensional energy landscape. Until this need is met, we will be unable to predict many important mechanisms that govern long-term dynamics of materials processes under exposure to thermal/radiative environments will remain unknown. To overcome these challenges, this project seeks to design a machine-learning based surrogate model, namely a treed Gaussian process classification model, to predict the existence of saddle points of a landscape. Gaussian processes are well-suited for global modeling of non-convex functions, and the tree-based configuration will help enable the modeling of high-dimensional spaces.