This project introduces the Sequential Threshold Least Squares (STLSQ) algorithm, a computational technique for identifying governing equations of complex dynamical systems. By leveraging machine learning and data-driven modeling, the study applied the Sparse Identification of Nonlinear Dynamics (SINDy) algorithm to identify patterns and behaviors in nonlinear systems. The project emphasizes the growing role of computational methods in scientific discovery and demonstrates how sparse regression techniques can reveal fundamental insights into the evolution of complex systems.