AI-driven optimization for sustainable landscape design has so far mostly concentrated on site analysis, plant selection, and design automation. Recycled waste materials have not received much attention as a central component of this approach. The area that needs more research is the application of AI algorithms specifically for selecting, processing, and using these recycled materials in a way that maximizes sustainability and minimizes waste. Our research is valuable because it closes this gap by creating AI-driven processes that prioritize the usage of recovered waste materials and improve landscape design, supporting both creative design and environmental sustainability. The goal of this study was to optimize recycled waste materials using artificial intelligence for sustainable landscape design. Direct data collection from the case study plant was done for the three recycled materials. To make sure the gathered data is appropriate for AI model training and analysis, Z-score uses preprocessing. Using AI-driven planning and operation, genetic programming (GP) is used to evaluate the characteristics of recycled materials and match them with the specifications of energy system landscape design optimization. We examined the operational data from energy producing machinery in real time. In order to ensure sustainability and durability, MLP used predictive modeling to simulate the long-term performance of various materials in varied environmental situations. CNN will develop a range of design alternatives that integrate recycled materials, considering aspects including environmental impact, cost-effectiveness, and resource efficiency. As a result, recycled waste materials demonstrated by the suggested superior performance over other similar models in terms of AUC, accuracy (training has 83% and validation has 90%), energy consumption (38J), precision (98%), RMSE (3.24), MAE (2.73) and R2 (0.88). Through the result overcoming sustainable design principles, this effort hopes to open up new avenues for ecologically conscious landscape architecture.