deploy: 5ad44f7

_sources/pypolymlp.md

@@ -15,13 +15,15 @@ The training process involves using a dataset consisting of supercell
 displacements, forces, and energies. The trained MLPs are then employed to
 compute forces for supercells with specific displacements.
 
-For more details on the methodology, refer to <u>A. Togo and A. Seko, J. Chem. Phys.
-**160**, 211001 (2024)</u> [[doi](https://doi.org/10.1063/5.0211296)].
+For further details on combining phono3py calculations with pypolymlp, refer to
+<u>A. Togo and A. Seko, J. Chem. Phys. **160**, 211001 (2024)</u>
+[[doi](https://doi.org/10.1063/5.0211296)]
+[[arxiv](https://arxiv.org/abs/2401.17531)].
 
 An example of its usage can be found in the `example/NaCl-pypolymlp` directory
 in the distribution from GitHub or PyPI.
 
-## Requirement
+## Requirements
 
 - [pypolymlp](https://github.com/sekocha/pypolymlp)
 - [symfc](https://github.com/symfc/symfc)
@@ -228,7 +230,7 @@ displacement distance of 0.001 Angstrom. The forces for these supercells are
 then evaluated using pypolymlp. Both the generated displacements and the
 corresponding forces are stored in the `phono3py_mlp_eval_dataset` file.
 
-### Steps 4-6: Force constants calculation (random displacements in step 5)
+### Steps 4-7: Force constants calculation (random displacements in step 5)
 
 After developing MLPs, random displacements are generated by specifying
 {ref}`--rd <random_displacements_option>` option. To compute force constants
@@ -329,6 +331,14 @@ an additional 200 supercells. In total, 400 supercells are created. The forces
 for these supercells are then evaluated. Finally, the force constants are
 calculated using symfc.
 
+## Convergence with respect to dataset size
+
+In general, increasing the amount of data improves the accuracy of representing
+force constants. Therefore, it is recommended to check the convergence of the
+target property with respect to the number of supercells in the training
+dataset. Lattice thermal conductivity may be a convenient property to monitor
+when assessing convergence.
+
 ## Parameters for developing MLPs
 
 A few parameters can be specified using the `--mlp-params` option for the

pypolymlp.html

@@ -324,13 +324,14 @@ <h2> Contents </h2>
             </div>
             <nav aria-label="Page">
                 <ul class="visible nav section-nav flex-column">
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#requirement">Requirement</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#requirements">Requirements</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#workflow">Workflow</a><ul class="nav section-nav flex-column">
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-1-3-dataset-preparation">Steps 1-3: Dataset preparation</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-7-force-constants-calculation-systematic-displacements-in-step-5">Steps 4-7: Force constants calculation (systematic displacements in step 5)</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-6-force-constants-calculation-random-displacements-in-step-5">Steps 4-6: Force constants calculation (random displacements in step 5)</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-7-force-constants-calculation-random-displacements-in-step-5">Steps 4-7: Force constants calculation (random displacements in step 5)</a></li>
 </ul>
 </li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#convergence-with-respect-to-dataset-size">Convergence with respect to dataset size</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#parameters-for-developing-mlps">Parameters for developing MLPs</a><ul class="nav section-nav flex-column">
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#ntrain-and-ntest"><code class="docutils literal notranslate"><span class="pre">ntrain</span></code> and <code class="docutils literal notranslate"><span class="pre">ntest</span></code></a></li>
 </ul>
@@ -358,12 +359,14 @@ <h2> Contents </h2>
 <p>The training process involves using a dataset consisting of supercell
 displacements, forces, and energies. The trained MLPs are then employed to
 compute forces for supercells with specific displacements.</p>
-<p>For more details on the methodology, refer to <u>A. Togo and A. Seko, J. Chem. Phys.
-<strong>160</strong>, 211001 (2024)</u> [<a class="reference external" href="https://doi.org/10.1063/5.0211296">doi</a>].</p>
+<p>For further details on combining phono3py calculations with pypolymlp, refer to
+<u>A. Togo and A. Seko, J. Chem. Phys. <strong>160</strong>, 211001 (2024)</u>
+[<a class="reference external" href="https://doi.org/10.1063/5.0211296">doi</a>]
+[<a class="reference external" href="https://arxiv.org/abs/2401.17531">arxiv</a>].</p>
 <p>An example of its usage can be found in the <code class="docutils literal notranslate"><span class="pre">example/NaCl-pypolymlp</span></code> directory
 in the distribution from GitHub or PyPI.</p>
-<section id="requirement">
-<h2>Requirement<a class="headerlink" href="#requirement" title="Link to this heading">#</a></h2>
+<section id="requirements">
+<h2>Requirements<a class="headerlink" href="#requirements" title="Link to this heading">#</a></h2>
 <ul class="simple">
 <li><p><a class="reference external" href="https://github.com/sekocha/pypolymlp">pypolymlp</a></p></li>
 <li><p><a class="reference external" href="https://github.com/symfc/symfc">symfc</a></p></li>
@@ -558,8 +561,8 @@ <h3>Steps 4-7: Force constants calculation (systematic displacements in step 5)<
 then evaluated using pypolymlp. Both the generated displacements and the
 corresponding forces are stored in the <code class="docutils literal notranslate"><span class="pre">phono3py_mlp_eval_dataset</span></code> file.</p>
 </section>
-<section id="steps-4-6-force-constants-calculation-random-displacements-in-step-5">
-<h3>Steps 4-6: Force constants calculation (random displacements in step 5)<a class="headerlink" href="#steps-4-6-force-constants-calculation-random-displacements-in-step-5" title="Link to this heading">#</a></h3>
+<section id="steps-4-7-force-constants-calculation-random-displacements-in-step-5">
+<h3>Steps 4-7: Force constants calculation (random displacements in step 5)<a class="headerlink" href="#steps-4-7-force-constants-calculation-random-displacements-in-step-5" title="Link to this heading">#</a></h3>
 <p>After developing MLPs, random displacements are generated by specifying
 <a class="reference internal" href="command-options.html#random-displacements-option"><span class="std std-ref">–rd</span></a> option. To compute force constants
 with random displacements, an external force constants calculator is necessary.
@@ -656,6 +659,14 @@ <h3>Steps 4-6: Force constants calculation (random displacements in step 5)<a cl
 calculated using symfc.</p>
 </section>
 </section>
+<section id="convergence-with-respect-to-dataset-size">
+<h2>Convergence with respect to dataset size<a class="headerlink" href="#convergence-with-respect-to-dataset-size" title="Link to this heading">#</a></h2>
+<p>In general, increasing the amount of data improves the accuracy of representing
+force constants. Therefore, it is recommended to check the convergence of the
+target property with respect to the number of supercells in the training
+dataset. Lattice thermal conductivity may be a convenient property to monitor
+when assessing convergence.</p>
+</section>
 <section id="parameters-for-developing-mlps">
 <h2>Parameters for developing MLPs<a class="headerlink" href="#parameters-for-developing-mlps" title="Link to this heading">#</a></h2>
 <p>A few parameters can be specified using the <code class="docutils literal notranslate"><span class="pre">--mlp-params</span></code> option for the
@@ -735,13 +746,14 @@ <h3><code class="docutils literal notranslate"><span class="pre">ntrain</span></
   </div>
   <nav class="bd-toc-nav page-toc">
     <ul class="visible nav section-nav flex-column">
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#requirement">Requirement</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#requirements">Requirements</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#workflow">Workflow</a><ul class="nav section-nav flex-column">
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-1-3-dataset-preparation">Steps 1-3: Dataset preparation</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-7-force-constants-calculation-systematic-displacements-in-step-5">Steps 4-7: Force constants calculation (systematic displacements in step 5)</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-6-force-constants-calculation-random-displacements-in-step-5">Steps 4-6: Force constants calculation (random displacements in step 5)</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#steps-4-7-force-constants-calculation-random-displacements-in-step-5">Steps 4-7: Force constants calculation (random displacements in step 5)</a></li>
 </ul>
 </li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#convergence-with-respect-to-dataset-size">Convergence with respect to dataset size</a></li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#parameters-for-developing-mlps">Parameters for developing MLPs</a><ul class="nav section-nav flex-column">
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#ntrain-and-ntest"><code class="docutils literal notranslate"><span class="pre">ntrain</span></code> and <code class="docutils literal notranslate"><span class="pre">ntest</span></code></a></li>
 </ul>