PhaseSplit-FH3: A dataset of ternary separation per Flory-Huggins theory.

<p>This dataset holds 1036 ternary phase diagrams and how points on the diagram phase separate if they do. The data is provided as a serialized object using the `pickle' Python module. The data was compiled using Python version 3.8.&nbsp;</p> <p><strong>References<br></strong>The specific applications and analyses of the data are described in&nbsp;<br>1.&nbsp; Dhamankar, S.; Jiang, S.; Webb, M.A. "Accelerating Multicomponent Phase-Coexistence Calculations with Physics-informed Neural Networks"</p> <p><strong>Usage</strong><br>To access the data in the .pickle file, users can execute the following:</p> <blockquote> <p><br># LOAD SIMULATION DATA<br>DATA_DIR = "your/custom/dir/"</p> <p>filename = os.path.join(DATA_DIR, f"data_clean.pickle")<br>with open(filename, "rb") as handle:<br>&nbsp; &nbsp; (x, y_c, y_r, phase_idx, num_phase, max_phase) = pickle.load(handle)</p> </blockquote> <ul> <li>x: Input x = (&chi;_AB, &chi;_BC, &chi;_AC, v_A, v_B, v_C, &phi;_A, &phi;_B) &isin; ℝ^8.</li> <li>y_c: Output one-hot encoded classification vector y_c &isin; ℝ^3.</li> <li>y_r: Output equilibrium composition and abundance vector y_r = (&phi;_A^&alpha;, &phi;_B^&alpha;, &phi;_A^&beta;, &phi;_B^&beta;, &phi;_A^&gamma;, &phi;_B^&gamma;, w^&alpha;, w^&beta;, w^&gamma;) &isin; ℝ^9.</li> <li>phase_idx: A single integer indicating which unique phase system it belongs to.</li> <li>num_phase: A single integer indicates the number of equilibrium phases the input splits into.</li> <li>max_phase: A single integer indicates the maximum number of equilibrium phases the system splits into.</li> </ul> <p><strong>Help, Suggestions, Corrections?</strong><br>If you need help, have suggestions, identify issues, or have corrections, please send your comments to Shengli Jiang at sj0161@princeton.edu</p> <p><strong>GitHub</strong><br>Additional data and code relevant for this study is additionally accessible at&nbsp;<a href="https://github.com/webbtheosim/gcgnn">ht</a><a href="https://github.com/webbtheosim/ml-ternary-phase">https://github.com/webbtheosim/ml-ternary-phase</a></p>