The study and measurement of optical nonlinearities, particularly the nonlinear refractive index and absorption coefficient, are critical for advancing a wide range of applications, from spectroscopy and material processing to biophysics, atmospheric sensing, and metrology [1]. These nonlinear properties are essential for developing innovative technologies and predicting material responses in specific applications. For example, materials exhibiting significant two-photon absorption are vital in fields such as microfabrication, optical data storage, bio-imaging, and optical power limiting, while those with a pronounced nonlinear refractive index are crucial for optical switching and soliton generation [2]. Central to our project is the implementation of an automated Z-scan technique, enhanced with machine learning algorithms, on an FPGA (Field Programmable Gate Array). The Z-scan technique is renowned for its effectiveness in determining nonlinear optical properties. The use of FPGA technology allows the complete automation of this technique without the need for a traditional computer, thereby significantly improving the efficiency and accuracy of the measurements. The development of computational methods in the field of photonics and electromagnetic wave propagation is of great importance. Analytical solutions are only feasible in specific cases where simple geometries prevail. The application of computational methods in photonics extends far beyond the design phase. For instance, in the study by Baik et al. (2022) [3], the use of FPGA technology to implement the Finite Difference Time Domain (FDTD) method is proposed to estimate real-time thermal lesions caused by surgical techniques based on electromagnetic wave propagation. This highlights the potential of FPGA in real-time processing applications. In another study [4], the implementation of nonlinear optical propagation algorithms using FPGA for demodulating information is demonstrated. The FDTD method also has significant applications in biology, given that much of the evolution of life forms on Earth has been influenced by interactions with light. In this project, we aim to implement a fully automated Z-scan technique with minimal human intervention, using an FPGA as the central processing unit. The FPGA will not only replace the traditional computer but will also be the platform where machine learning algorithms are implemented. These algorithms will enhance the prediction of nonlinear optical characteristics of materials, leading to more accurate and reliable measurements. By integrating machine learning with the FPGA, we expect to achieve a higher level of precision and automation, pushing the boundaries of current Z-scan methodologies. Additionally, we are collaborating with the Nonlinear Optics group at The College of Optics and Photonics, University of Central Florida—the originators of the Z-scan technique—to further refine and optimize its implementation.