ENGLISH
|
JAPANESE
|
CONNECT WITH US:
Home
About
Contact
Log in
Home
Press release
Sep 30, 2021 07:00 JST
Source:
Science and Technology of Advanced Materials
Improving machine learning for materials design
A quick, cost-effective approach improves the accuracy with which machine learning models can predict the properties of new materials.
TSUKUBA, Japan, Sep 30, 2021 - (ACN Newswire) - A new approach can train a machine learning model to predict the properties of a material using only data obtained through simple measurements, saving time and money compared with those currently used. It was designed by researchers at Japan's National Institute for Materials Science (NIMS), Asahi KASEI Corporation, Mitsubishi Chemical Corporation, Mitsui Chemicals, and Sumitomo Chemical Co and reported in the journal Science and Technology of Advanced Materials: Methods.
The new approach can predict difficult-to-measure experimental data such as tensile modulus using easy-to-measure experimental data like X-ray diffraction. It further helps design new materials or repurpose already known ones.
"Machine learning is a powerful tool for predicting the composition of elements and process needed to fabricate a material with specific properties," explains Ryo Tamura, a senior researcher at NIMS who specializes in the field of materials informatics.
A tremendous amount of data is usually needed to train machine learning models for this purpose. Two kinds of data are used. Controllable descriptors are data that can be chosen without making a material, such as the chemical elements and processes used to synthesize it. But uncontrollable descriptors, like X-ray diffraction data, can only be obtained by making the material and conducting experiments on it.
"We developed an effective experimental design method to more accurately predict material properties using descriptors that cannot be controlled," says Tamura.
The approach involves the examination of a dataset of controllable descriptors to choose the best material with the target properties to use for improving the model's accuracy. In this case, the scientists interrogated a database of 75 types of polypropylenes to select a candidate with specific mechanical properties.
They then selected the material and extracted some of its uncontrollable descriptors, for example, its X-ray diffraction data and mechanical properties.
This data was added to the present dataset to better train a machine learning model employing special algorithms to predict a material's properties using only uncontrollable descriptors.
"Our experimental design can be used to predict difficult-to-measure experimental data using easy-to-measure data, accelerating our ability to design new materials or to repurpose already known ones, while reducing the costs," says Tamura. The prediction method can also help improve understanding of how a material's structure affects specific properties.
The team is currently working on further optimizing their approach in collaboration with chemical manufacturers in Japan.
Further information
Ryo Tamura
National Institute for Materials Science (NIMS)
Email:
tamura.ryo@nims.go.jp
About Science and Technology of Advanced Materials: Methods (STAM Methods)
STAM Methods is an open access sister journal of Science and Technology of Advanced Materials (STAM), and focuses on emergent methods and tools for improving and/or accelerating materials developments, such as methodology, apparatus, instrumentation, modeling, high-through put data collection, materials/process informatics, databases, and programming.
https://www.tandfonline.com/STAM-M
Dr. Yoshikazu Shinohara
STAM Methods Publishing Director
Email:
SHINOHARA.Yoshikazu@nims.go.jp
Press release distributed by Asia Research News for Science and Technology of Advanced Materials.
Source: Science and Technology of Advanced Materials
Sectors: Science & Nanotech
Copyright ©2024 ACN Newswire. All rights reserved. A division of Asia Corporate News Network.
Latest Release
Hitachi: Established the Open Source Program Office (OSPO) to Globally Lead the Strategic Utilization of OSS
Nov 11, 2024 10:31 JST
Transgene and NEC Present New Data Confirming Clinical Proof of Principle for Neoantigen Cancer Vaccine, TG4050, in Head & Neck Cancer at SITC 2024
Nov 08, 2024 10:31 JST
Hitachi High-Tech and University of Tokyo Promote Joint Research for the Practical Application of High-resolution Laser-PEEM in the Semiconductor Field
Nov 07, 2024 18:19 JST
Mitsubishi Motors Acquires Its Own Shares from Nissan
Nov 07, 2024 17:20 JST
Honda Signs Sponsorship Agreement to Provide Electrified Vehicles at World Athletics Championships Tokyo 25
Nov 07, 2024 17:10 JST
Home of Fujitsu joint conservation project designated as first Nationally Certified Sustainably Managed Natural Site in Okinawa
Nov 07, 2024 14:51 JST
NEC and NEC Bio publish foundational work on T Cell Receptor engineering using proprietary generative AI at the Society for Immunotherapy of Cancer annual meeting
Nov 07, 2024 11:40 JST
Anime Tokyo Station 1st Anniversary Event: Celebrating one year since the opening of the new hub for sharing Japanese anime
Nov 07, 2024 11:00 JST
57% of Banking Executives Struggle with Data Silos, Blocking AI-Driven Personalization, CleverTap's New Report Highlights
Nov 06, 2024 15:30 JST
Honda Unveils Electric Motorcycle Concept Models "EV Fun Concept" and "EV Urban Concept" at EICMA 2024
Nov 06, 2024 14:15 JST
Yoshimoto Kogyo and Mitsubishi Corporation have signed a business partnership agreement for co-creation of business using "laughter"
Nov 06, 2024 11:51 JST
Honda to Begin European Verification Test of Battery Sharing Service with GoCimo
Nov 06, 2024 10:39 JST
Honda Unveils World's First and New V3 Engine with Electrical- Compressor at EICMA 2024
Nov 06, 2024 09:03 JST
Victory and world title for TOYOTA GAZOO Racing
Nov 05, 2024 17:59 JST
Tokyo Stock Exchange and Fujitsu announce renewal of cash equity trading system 'arrowhead4.0'
Nov 05, 2024 17:13 JST
Mitsubishi Heavy Industries Continues Order Intake, Revenue, and Profit Growth in Strong First Half, Raises Full-Year Order Intake Guidance
Nov 05, 2024 14:37 JST
Eisai's Corporate Venture Capital Subsidiary, Eisai Innovation, Inc., Selected for AMED's 'Strengthening Program for Pharmaceutical Startup Ecosystem"
Nov 05, 2024 11:35 JST
Asahi Kasei and Honda Sign Shareholders' Agreement to Convert Existing Asahi Kasei Subsidiary into Joint Venture for Production of Lithium-ion Battery Separators in Canada
Nov 04, 2024 14:12 JST
Joby Aviation and Toyota Accelerate Efforts to Realize Air Mobility
Nov 04, 2024 09:36 JST
Eisai Completes Rolling Submission to US FDA for LEQEMBI(R) (lecanemab-irmb) Biologics License Application for Subcutaneous Maintenance Dosing for the Treatment of Early Alzheimer's Disease Under the Fast Track Status
Nov 01, 2024 13:56 JST
More Latest Release >>
Related Release
Machine learning can predict the mechanical properties of polymers
October 25 2024 23:00 JST
Dual-action therapy shows promise against aggressive oral cancer
July 30 2024 20:00 JST
A new spin on materials analysis
April 17 2024 22:00 JST
Kirigami hydrogels rise from cellulose film
April 12 2024 18:00 JST
Sensing structure without touching
February 27 2024 08:00 JST
Nano-sized probes reveal how cellular structure responds to pressure
November 21 2023 07:00 JST
Machine learning techniques improve X-ray materials analysis
November 17 2023 10:00 JST
A bio-inspired twist on robotic handling
November 14 2023 20:00 JST
GPT-4 artificial intelligence shows some competence in chemistry
October 17 2023 08:00 JST
Closing the loop between artificial intelligence and robotic experiments
August 24 2023 09:00 JST
More Press release >>