{"id":100806,"date":"2025-03-28T11:20:20","date_gmt":"2025-03-28T11:20:20","guid":{"rendered":"https:\/\/www.simscale.com\/?page_id=100806"},"modified":"2026-01-22T18:28:25","modified_gmt":"2026-01-22T18:28:25","slug":"ai-model-training","status":"publish","type":"page","link":"https:\/\/www.simscale.com\/docs\/ai-model-training\/","title":{"rendered":"Artificial Intelligence (AI) Model Training in SimScale"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">SimScale leverages Physics AI in a cloud-native simulation environment to accelerate computational engineering. This documentation explains how to train simulation models using Artificial Intelligence &#8211; AI and how it could benefit users and engineering organizations with faster result prediction in seconds instead of actually simulating.<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-simscale wp-block-embed-simscale\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"kLeNfJMhzi\"><a href=\"https:\/\/www.simscale.com\/blog\/shaping-the-future-of-automotive-engineering-with-ai-powered-simulation\/\">Shaping the Future of Automotive Engineering with AI-Powered Simulation<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; clip: rect(1px, 1px, 1px, 1px);\" title=\"&#8220;Shaping the Future of Automotive Engineering with AI-Powered Simulation&#8221; &#8212; SimScale\" src=\"https:\/\/www.simscale.com\/blog\/shaping-the-future-of-automotive-engineering-with-ai-powered-simulation\/embed\/#?secret=dYpIaN9gEy#?secret=kLeNfJMhzi\" data-secret=\"kLeNfJMhzi\" width=\"500\" height=\"282\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Consider the following AI trained example model of a Centrifugal pump. Running over hundreds of parallel simulations with geometry variations in the number of blades, blade thickness, etc. and variable inlet flow rates predicted CFD results within seconds for new user inputs with accuracy up to 99% and above.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump.jpg\"><img loading=\"lazy\" decoding=\"async\" width=\"1042\" height=\"597\" src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump.jpg\" alt=\"ai model training schematic\" class=\"wp-image-101475\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump.jpg 1042w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump-300x172.jpg 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump-1024x587.jpg 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-pump-768x440.jpg 768w\" sizes=\"auto, (max-width: 1042px) 100vw, 1042px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 1: AI model training can help reduce the result output to seconds.<\/figcaption><\/figure>\n<\/div>\n\n\n<h2 id='simscale-ai-integration' class=\"wp-block-heading\" id=\"simscale-ai-integration\">SimScale AI Integration<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">To do engineering simulations with AI, you need quick and easy access to models and data. SimScale&#8217;s cloud-based setup and well-organized simulation data storage make it super easy to use powerful AI tools whenever you need them. There are four major steps involved:<\/p>\n\n\n\n<h2 id='step-1-activation' class=\"wp-block-heading\" id=\"step-1-activation\">Step 1: Activation<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">If your organization has a license for AI training then as an <a href=\"https:\/\/www.simscale.com\/knowledge-base\/organization-account-admin\/\">organization admin<\/a> you can activate <strong>AI training permission<\/strong> for your users. This can be done by first accessing the <strong>&#8216;Manage users&#8217;<\/strong> item on your Dashboard and then enabling the feature <strong>&#8216;AI training permission&#8217;<\/strong> for each user individually.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Once the feature is activated, a new item <em>AI Model Training<\/em> can be seen in the left panel in the Dashboard.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"781\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98.png\" alt=\"ai training permission dashboard manage users\" class=\"wp-image-101587\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98.png 1920w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98-300x122.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98-1024x417.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98-768x312.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-98-1536x625.png 1536w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 2: Steps for the organization admin to activate the AI training permission for the users<\/figcaption><\/figure>\n<\/div>\n\n\n<p class=\"wp-block-paragraph\">As an organization admin, you can access all the AI models created within your organization. This includes seeing them on the <em>AI Models Training<\/em> overview page as well as opening and editing each model individually.<\/p>\n\n\n\n<h2 id='step-2-ai-model-training' id='step-2-ai-model-training' class=\"wp-block-heading\" id=\"step-2-ai-model-training\">Step 2: AI Model Training<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">In order to train a new AI model, go to the <em>AI model training<\/em> page (see left menu in Figure 2) and click on the top right button <strong>&#8216;+ New model&#8217;<\/strong>.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"670\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85.png\" alt=\"new ai training model\" class=\"wp-image-101514\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85.png 1920w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85-300x105.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85-1024x357.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85-768x268.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-85-1536x536.png 1536w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 3: Creating a new model for AI training<\/figcaption><\/figure>\n<\/div>\n\n\n<h3 id='create-a-new-model' id='create-a-new-model' class=\"wp-block-heading\" id=\"create-a-new-model\">Create a New Model<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Set a model name and description.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-86.png\"><img loading=\"lazy\" decoding=\"async\" width=\"578\" height=\"299\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-86.png\" alt=\"new model ai dialog box\" class=\"wp-image-101519\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-86.png 578w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-86-300x155.png 300w\" sizes=\"auto, (max-width: 578px) 100vw, 578px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 4: Dialog box for new AI model<\/figcaption><\/figure>\n<\/div>\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Model name:<\/strong> Model name is what will be seen later by users of the AI model when they are applying it within the Workbench for fast result prediction. <\/li>\n\n\n\n<li><strong>Short description:<\/strong> Short description will later be shown on the model details page and should give a brief overview of the purpose of the model.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Proceed using the <strong>&#8216;Select Training Data&#8217;<\/strong> button.<\/p>\n\n\n\n<h3 id='select-training-data' id='select-training-data' class=\"wp-block-heading\" id=\"select-training-data\">Select Training Data<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Select projects whose simulation data shall be used for AI training.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">You need at least 20 simulation runs performed in a single project or across multiple projects, however, more data usually leads to higher AI model prediction accuracy.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Currently, the following analysis types are available for the AI model training:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.simscale.com\/docs\/analysis-types\/incompressible-fluid-flow-analysis\/\">Incompressible<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.simscale.com\/docs\/analysis-types\/static\/\">Static (linear)<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.simscale.com\/docs\/analysis-types\/conjugate-heat-transfer-analysis\/\">Conjugate heat transfer<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.simscale.com\/docs\/analysis-types\/conjugate-heat-transfer-ibm\/\">Conjugate heat transfer (IBM)<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.simscale.com\/docs\/analysis-types\/multi-purpose-analysis\/\">Multi-purpose<\/a><\/li>\n<\/ul>\n\n\n\n<h3 id='analysis-type' id='analysis-type' class=\"wp-block-heading\" id=\"analysis-type\">Analysis Type<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">The AI training is&nbsp;restricted to using simulation runs from only a single analysis type. If simulation runs from multiple analysis types have been completed in the selected projects, one has to be chosen.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1602\" height=\"780\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87.png\" alt=\"ai model training data selection\" class=\"wp-image-101520\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87.png 1602w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87-300x146.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87-1024x499.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87-768x374.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-87-1536x748.png 1536w\" sizes=\"auto, (max-width: 1602px) 100vw, 1602px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 5: AI model training data selection. At least 20 runs are required.<\/figcaption><\/figure>\n<\/div>\n\n\n<p class=\"wp-block-paragraph\">Select <strong>&#8216;Next&#8217;<\/strong> to choose an analysis type.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-analysis-type-choose.jpg\"><img loading=\"lazy\" decoding=\"async\" width=\"577\" height=\"425\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-analysis-type-choose.jpg\" alt=\"choose analysis type dialog box ai model\" class=\"wp-image-101596\" style=\"width:422px;height:auto\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-analysis-type-choose.jpg 577w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/ai-analysis-type-choose-300x221.jpg 300w\" sizes=\"auto, (max-width: 577px) 100vw, 577px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 6: Select the analysis type of interest to display the corresponding projects and confirm.<\/figcaption><\/figure>\n<\/div>\n\n\n<p class=\"wp-block-paragraph\">Select the analysis type of interest to display the corresponding projects. Click <strong>&#8216;Confirm&#8217;<\/strong> to proceed.<\/p>\n\n\n\n<div class=\"hw-block hw-note hw-note--success hw-note\">\n    <div class=\"hw-note__title\">\n        <p class=\"hw-note__titleText\"><i class=\"fa fa-exclamation-circle\" aria-hidden=\"true\"><\/i>Best Practices on How to Choose a Model for AI Training<\/p>\n    <\/div>\n    <div class=\"hw-note__body\">\n        <p><p>There are mainly two parameters that can be varied:<\/p> <li><strong>Geometry:<\/strong> This can include dimensions such as inlet length, outlet diameter, number of holes, thickness and number of turbine blades, etc.<\/li> <li><strong>Boundary conditions:<\/strong> This can include parameterization of simulation quantities such as a range of flowrate velocity, pressure, temperature, angular velocity, force, etc.<\/li><\/p>\n    <\/div>\n<\/div>\n\n\n\n<h2 id='step-3-ai-training-data-settings' id='step-3-ai-training-data-settings' class=\"wp-block-heading\" id=\"step-3-training-data-settings\">Step 3: AI Training Data Settings<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">In this step, some information related to the AI model training needs to be provided before it can be started.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1603\" height=\"780\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89.png\" alt=\"ai mode training data settings\" class=\"wp-image-101522\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89.png 1603w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89-300x146.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89-1024x498.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89-768x374.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-89-1536x747.png 1536w\" sizes=\"auto, (max-width: 1603px) 100vw, 1603px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 7: Provide AI model training data before beginning the training.<\/figcaption><\/figure>\n<\/div>\n\n\n<p class=\"wp-block-paragraph\">The required information is as follows:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Version Name:<\/strong> Provide a version name to distinguish between different AI model trainings. <\/li>\n\n\n\n<li><strong>Confidence Score: <\/strong>A<strong> <\/strong>Confidence score from 0-100 shows the trust level users can have with the result prediction. It is recommended to turn it on.<\/li>\n\n\n\n<li><strong>Max runtime:<\/strong> Select the time limit beyond which the AI training time will not be exceeded.<\/li>\n\n\n\n<li><strong>Start Training:<\/strong> Click here to start the AI model training.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">The training status is displayed as follows:<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1603\" height=\"778\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91.png\" alt=\"ai model training status display\" class=\"wp-image-101526\" style=\"width:768px;height:auto\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91.png 1603w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91-300x146.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91-1024x497.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91-768x373.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-91-1536x745.png 1536w\" sizes=\"auto, (max-width: 1603px) 100vw, 1603px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 8: Users can see the status of their AI model training until it is completed. <\/figcaption><\/figure>\n<\/div>\n\n\n<div class=\"hw-block hw-note hw-note--info hw-note\">\n    <div class=\"hw-note__title\">\n        <p class=\"hw-note__titleText\"><i class=\"fa fa-exclamation-circle\" aria-hidden=\"true\"><\/i>Note<\/p>\n    <\/div>\n    <div class=\"hw-note__body\">\n        <p>Currently, SimScale AI models can provide result predictions for all surfaces of the CAD, for e.g. pressure and velocity at inlet outlet and also on walls. If you want to  train an AI model to predict also scalar values (like averaged pressures across a surface, drag coefficients, reaction forces, etc.) or restrict the training only to specific regions of the CAD  please <a href=\"mailto:support@simscale.com\">contact our support for assistance<\/a>.<\/p>\n    <\/div>\n<\/div>\n\n\n\n<h2 id='step-4-review-the-ai-model-accuracy' class=\"wp-block-heading\" id=\"step-4-review-the-ai-model-accuracy\">Step 4: Review the AI Model Accuracy<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Before the AI model can be released for use by the organization, the following parameters should be thoroughly investigated.<\/p>\n\n\n\n<h3 id='model-accuracy' id='model-accuracy' class=\"wp-block-heading\" id=\"model-accuracy\">Model Accuracy<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Here, quality metrics for the quantities involved in the simulation, like velocity, pressure, etc., can be explored. <\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1478\" height=\"726\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93.png\" alt=\"model accuracy ai training loss validation loss\" class=\"wp-image-101533\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93.png 1478w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93-300x147.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93-1024x503.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-93-768x377.png 768w\" sizes=\"auto, (max-width: 1478px) 100vw, 1478px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 9: Model accuracy and loss parameters should be thoroughly reviewed to check AI model accuracy.<\/figcaption><\/figure>\n<\/div>\n\n\n<h4 id='mapemax' id='mapemax' class=\"wp-block-heading\" id=\"mapemax\">MAPEMax<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Mean absolute percentage error maximum. This should be close to zero.<\/p>\n\n\n\n<h4 id='mae' id='mae' class=\"wp-block-heading\" id=\"mae\">MAE<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Mean absolute error. This should ideally be zero. These are absolute values with units of the physical quantity involved.<\/p>\n\n\n\n<h4 id='r2' id='r2' class=\"wp-block-heading\" id=\"r2\">R2<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">R-squared coefficient. A value close to 1 indicates perfect accuracy.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Let&#8217;s understand the metrics using the figure above. The MAEPMax for pressure is 93.63 %; however, for velocity it is under 24.33 %. This means the AI model can be used for predicting velocity values with a lower degree of error.<\/p>\n\n\n\n<h3 id='training-loss' id='training-loss' class=\"wp-block-heading\" id=\"training-loss\">Training Loss<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">The graph shows how relatable the data is. The loss should tend to zero and be significantly reduced on the last iterations compared to the initial value of the residual at iteration 0. One must be cautious not to run the AI training across too many iterations as this could bear the risk of overfitting the model to the training data. This means it would be difficult for the model to generalize beyond the given training data points, even for input data that is not too far from the training data.<\/p>\n\n\n\n<h3 id='validation-loss' id='validation-loss' class=\"wp-block-heading\" id=\"validation-loss\">Validation Loss<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">In order to check that the model is not over-fitting to the training data, one must ensure that the training loss and the validation loss are in the same ranges &#8211; so the value of the validation loss over the last iterations should be close to the training loss. If the validation loss is much higher than the training loss, this is a strong sign of over-fitting, and a new training should be started with either more training data or training for fewer iterations.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If you are not satisfied with the training or if the current version did not finish successfully a new version can be trained. Additionally, a document can be created to provide key information for the users of this AI model. These two options are depicted in Figure 10.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1592\" height=\"743\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94.png\" alt=\"ai demo new version create documentation\" class=\"wp-image-101534\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94.png 1592w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94-300x140.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94-1024x478.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94-768x358.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-94-1536x717.png 1536w\" sizes=\"auto, (max-width: 1592px) 100vw, 1592px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 10: Begin a new version or create a log of steps involved in the current AI model version.<\/figcaption><\/figure>\n<\/div>\n\n\n<h2 id='step-5-release-the-ai-trained-model' class=\"wp-block-heading\" id=\"step-5-release-the-ai-trained-model\">Step 5: Release the AI Trained Model<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Once you are satisfied with the AI model training parameters, you have the option to release the trained model to users within your organization.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1210\" height=\"711\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95.png\" alt=\"release ai trained model\" class=\"wp-image-101537\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95.png 1210w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95-300x176.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95-1024x602.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-95-768x451.png 768w\" sizes=\"auto, (max-width: 1210px) 100vw, 1210px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 11: Release the AI trained model.<\/figcaption><\/figure>\n<\/div>\n\n\n<p class=\"wp-block-paragraph\">Click on <strong>&#8216;Release&#8217;<\/strong>. This opens a dialog box as shown below:<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-96.png\"><img loading=\"lazy\" decoding=\"async\" width=\"576\" height=\"491\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-96.png\" alt=\"Dialog box for the release version settings\" class=\"wp-image-101538\" style=\"width:388px;height:auto\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-96.png 576w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-96-300x256.png 300w\" sizes=\"auto, (max-width: 576px) 100vw, 576px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 12: Dialog box for the release version settings<\/figcaption><\/figure>\n<\/div>\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Description of changes:<\/strong> Mention the changes performed for this version of AI training.<\/li>\n\n\n\n<li><strong>Internal Distribution:<\/strong> Decide who should have access to the trained model. There are two options: <em>yourself<\/em> or <em>your organization<\/em>. Access to your organization means every user of your organization will have access to the model from the Workbench and can use it to predict simulation results.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Click <strong>&#8216;Release&#8217;<\/strong> again and a message that the version has been successfully released will be displayed. <\/p>\n\n\n\n<h2 id='after-the-release' id='after-the-release' class=\"wp-block-heading\" id=\"after-the-release\">After the Release<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Once the trained model version is released to Workbench the <em>AI Model Training<\/em> page shows the release status and the type of internal distribution.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1592\" height=\"762\" nonce='1586236032bff83da2cb4e3b21365787' src=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97.png\" alt=\"release history ai\" class=\"wp-image-101539\" srcset=\"https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97.png 1592w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97-300x144.png 300w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97-1024x490.png 1024w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97-768x368.png 768w, https:\/\/frontend-assets.simscale.com\/media\/2025\/03\/image-97-1536x735.png 1536w\" sizes=\"auto, (max-width: 1592px) 100vw, 1592px\" \/><\/a><figcaption class=\"wp-element-caption\">Figure 13: AI model training page after the release. All the related history is available.<\/figcaption><\/figure>\n<\/div>\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Released to Workbench:<\/strong> This shows versions released to Workbench.<\/li>\n\n\n\n<li><strong>All versions: <\/strong>This shows all unreleased versions.<\/li>\n\n\n\n<li><strong>Release history:<\/strong> It displays past information related to version releases such as time of release, name, and description of changes.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>SimScale leverages Physics AI in a cloud-native simulation environment to accelerate computational engineering....","protected":false},"author":118,"featured_media":101475,"parent":14048,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"templates\/template-documentation.php","meta":{"_acf_changed":false,"_crdt_document":"","inline_featured_image":false,"footnotes":""},"class_list":["post-100806","page","type-page","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/pages\/100806","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/users\/118"}],"replies":[{"embeddable":true,"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/comments?post=100806"}],"version-history":[{"count":0,"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/pages\/100806\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/pages\/14048"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/media\/101475"}],"wp:attachment":[{"href":"https:\/\/www.simscale.com\/wp-json\/wp\/v2\/media?parent=100806"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}