Mehmet Akif Özgül’s recent research focuses on strengthening cybersecurity in Supervisory Control and Data Acquisition (SCADA) systems used in critical energy infrastructure, with a particular emphasis on hydroelectric power plants. In the paper “A Hybrid Machine Learning Approach for Cyberattack Detection and Classification in SCADA Systems: A Hydroelectric Power Plant Application,” he and his co-authors propose an intelligent security model that integrates multiple machine learning techniques to detect and classify cyberattacks with high accuracy. Recognizing that conventional signature-based systems are often limited in identifying evolving and sophisticated threats, the study develops a hybrid model capable of learning complex behavioral patterns from operational data. Real-world SCADA data from a hydroelectric facility is used to train and evaluate the system, ensuring that the model reflects authentic power plant operating conditions. The proposed approach demonstrates improved performance in distinguishing between normal activities and various cyberattack categories, contributing to better situational awareness, operational continuity, and risk mitigation in industrial control environments. This research is particularly significant as cyber threats targeting energy systems continue to rise, and hydroelectric plants represent essential components of national energy grids. By advancing intelligent intrusion detection tailored to SCADA environments, Özgül’s work bridges the gap between electrical engineering practice and cybersecurity innovation, supporting safer, more resilient, and more reliable power generation systems.