Real-Time Adaptive Optimization of Deep-Space Missions Using Lightweight Machine Learning Models

– Deep-space missions involve complex challenges such as communication delays, resource limitations, and unpredictable environmental conditions. This paper presents a real-time adaptive optimization system using lightweight machine learning models to improve mission planning and efficiency. Unlike traditional approaches that rely on computationally intensive deep learning models, the proposed system utilizes efficient algorithms such as Random Forest and Support Vector Machines to predict mission success, optimize resource allocation, and enhance communication reliability. The system integrates historical NASA datasets and processes them through a web-based interface built using Flask and React for real-time prediction and visualization. Experimental results demonstrate improved accuracy, reduced computational cost, and enhanced decision-making capability. The proposed approach provides a practical and scalable solution for intelligent deep-space mission optimization.