LatticeML: a data-driven application for predicting the effective Young Modulus of high temperature graph based architected materials

Architected materials with their unique topology and geometry offer the potential to modify physical and mechanical properties. Machine learning can accelerate the design and optimization of these materials by identifying optimal designs and forecasting performance. This work presents LatticeML, a data-driven application for predicting the effective Young's Modulus of high-temperature graph-based architected materials. The study considers eleven graph-based lattice structures (e.g., octet truss, honeycomb, Kelvin cell) with two high-temperature alloys, Ti–6Al–4V and Inconel 625. Finite element simulations were used to compute the effective Young's Modulus of the 2 × 2 × 2 unit cell configurations, generating a dataset of 110 samples. A machine learning framework was developed, implementing five supervised regression algorithms: decision trees, XGBoost, CatBoost, extra trees, and gradient boosting. The XGBoost Regressor achieved the highest accuracy with an MSE of 2.7993, MAE of 1.1521, and R-squared of 0.9875. The LatticeML application, built using the Streamlit framework, creates an interactive web interface where users can input material and geometric parameters to obtain predicted Young's Modulus values. The integration of finite element analysis, machine learning models, and a user-friendly interface enables rapid prediction of material properties, accelerating the design and optimization of high-performance architected materials.