A unique NNP with high versatility and accuracy.
"Matlantis" is a general-purpose atomic-level simulator that incorporates deep learning models into traditional atomic simulators, based on Neural Network Potential (NNP), enabling the reproduction of material behavior at the atomic scale and facilitating large-scale material exploration. By significantly reducing computational costs while maintaining versatility, it allows for the rapid and extensive computation of complex systems that closely resemble reality. Please feel free to contact us if you have any inquiries. 【Features】 ■ Supports a wide range of elements and structures ■ Over 10,000 times faster than traditional methods ■ Simulation can be started simply by opening a browser *For more details, please download the PDF or contact us.
Inquire About This Product
basic information
【Recommended for the following individuals】 ■ Those who are troubled by the constraints of computation time and resources when using methods such as DFT (Density Functional Theory) or DFTB (Density Functional based Tight Binding). ■ Those who are utilizing MD (Molecular Dynamics) but are struggling due to a lack of good interatomic potentials. ■ Those who wish to advance their research by simulating and following experimental results while conducting theoretical discussions. ■ Those who are working on DX (Digital Transformation) in research and development departments and aim to promote the use of simulations within their company. *For more details, please download the PDF or contact us.
Price range
Delivery Time
Applications/Examples of results
【Calculation Examples】 ■ TMA-OSA System: Reaction analysis of TMA in a system mimicking the surface of silicon oxide film ■ Battery: Molecular dynamics calculation of magnesium ion conductive oxide ■ Battery: Evaluation of lithium ion conductivity in garnet-type oxide materials ■ Catalyst: Activation energy of CO dissociation reaction in cobalt catalysts ■ Adsorbent: Adsorption and diffusion behavior of H2O molecules in MOF-74Ni ■ Lubricating Oil: Prediction of liquid viscosity through reverse nonequilibrium molecular dynamics simulation ■ Battery: Li diffusion in sulfide solid electrolytes *For more details, please download the PDF or contact us.
catalog（1）
Download All Catalogs
Company information
Our company is dedicated to realizing a sustainable world by enabling the creation of innovative materials and substances. To achieve this, we are developing services by combining AI technologies such as deep learning from Preferred Networks, computational infrastructure, and the expertise and knowledge in the chemical field from ENEOS. We will support researchers around the world involved in material development by providing powerful tools to help them discover innovative materials that can change the future of the world for the better. Please feel free to contact us if you have any inquiries.
![[Simulator Utilization Case] Behavior Analysis of Sorters](https://image.mono.ipros.com/public/product/image/f29/2000737697/IPROS10528584251328593190.png?w=280&h=280)
![[Case Study] Successful Example of an Automatic Inspection Device for Battery Management Systems (BMS)](https://image.mono.ipros.com/public/product/image/5af/2001217735/IPROS11938869017554156144.jpg?w=280&h=280)
![[Case Study] Biomedical Testing Lab "Spinal Wear Simulator"](https://image.mono.ipros.com/public/product/image/dec/2000019552/IPROS2897255303564026484.jpg?w=280&h=280)
