<![CDATA[The rapid expansion of wind power plants has increased their exposure to lightning-related hazards, which pose significant risks to turbine integrity, operational reliability, and economic performance. Conventional lightning protection systems are often limited by their reliance on single-source data and reactive approaches, reducing their effectiveness in detecting and mitigating complex lightning phenomena. This study aims to develop a real-time, multi-source meteorological data integration framework to enhance lightning risk detection and protection in wind power plants. The proposed system integrates satellite observations, ground-based sensor networks, vertical atmospheric profiling technologies such as light detection and ranging and radar, lightning detection systems, and historical meteorological datasets within a unified architecture. Data are processed using embedded computing platforms and analyzed through machine learning techniques, including logistic regression and Extreme Gradient Boosting (XGBoost), to classify lightning types and compute a composite risk index for decision-making. The system enables automated alerts and protective responses, such as turbine shutdown or repositioning, when risk thresholds are exceeded. Results demonstrate that the framework achieves high predictive accuracy with a response latency of less than three seconds, allowing timely identification of lightning precursors and effective mitigation of potential damage. The modular, cost-effective design supports scalable deployment across varying wind farm capacities and operational environments. Thus, the findings indicate that integrating multi-source meteorological data significantly improves the performance and reliability of lightning protection systems, providing a practical, adaptable solution to enhance the safety and resilience of wind energy infrastructure under increasingly volatile climatic conditions.]]>
