Dataset for Machine Learning-based Surrogate Model for Melt Pool Control in Laser-based Direct Energy Deposition

This repository provides the dataset supporting the manuscript “Machine Learning‑based Surrogate Model for Melt Pool Control in Laser‑based Direct Energy Deposition.” It includes the synthetic high‑fidelity (HF) training data generated using an experimentally calibrated Finite Element (FE) thermal model for surrogate model development. It also includes data from the statistical analysis of the input features, a representative dataset for the hyperparameter tuning process of the regression model, and validation data on an independent test case. Additionally, the repository contains test results comprising the optimized laser power profiles and the corresponding thermal and melt pool geometric process indicators used for performance evaluation and analysis for three test cases. Two of which are not part of the training dataset.These files correspond to the results presented in the manuscript and enable full reproduction of the figures, analysis, and regression workflow. A structured folder layout and accompanying README describe the dataset contents and intended usage.