Video | Agriculture | Confidence | Economy | Energy | Employment | Finance | Media | Property | RBNZ | Science | SOEs | Tax | Technology | Telecoms | Tourism | Transport | Search

 

Improving Machine Learning For Materials Design

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.

"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.

© Scoop Media

 
 
 
Business Headlines | Sci-Tech Headlines

 



Electricity Authority: Review Of Competition In The Wholesale Electricity Market Raises Questions

In March 2021 the Electricity Authority announced it would conduct a review into competition in the wholesale electricity market. The period of the review covers the sustained elevated electricity prices since an unplanned outage at the Pohokura gas facility in Spring 2018... More>>


Government: RSI ‘State Of The Nation’ Report Published
latest research, science and innovation system report card is now available, and outlines how the system is performing, Research, Science and Innovation Minister Megan Woods has announced. “The report seeks to increase transparency, act as a reliable data source and stimulate discussion... More>>




Fonterra: Increases 2021/22 Forecast Farmgate Milk Price

Fonterra Co-operative Group Limited today increased and narrowed its forecast Farmgate Milk Price range to NZD $7.90 - $8.90 per kgMS, from NZD $7.25 - $8.75 per kgMS. The midpoint of the range, which farmers are paid off, has increased to NZD $8.40 per kgMS, from NZD $8.00 per kgMS... More>>




Pamu & Westpac: Market-leading Sustainability-Linked Loan

Westpac NZ and Pāmu have signed New Zealand’s most comprehensive Sustainability-Linked Loan to date, also the largest in the agricultural sector, and the first involving a state-owned enterprise. Pāmu, also known as Landcorp, is New Zealand’s biggest farming business. It will borrow $85m from Westpac NZ over three years... More>>


Retail NZ: Some Good News In COVID Announcements, But Firm Dates Needed

Retail NZ is welcoming news that the Government is increasing financial support for businesses in light of the ongoing COVID-19 lockdown, and that retail will be able to open at all stages of the new “Covid Protection Framework... More>>

ComCom: Companies In Hot Water For Selling Unsafe Hot Water Bottles And Toys

A wholesaler and a retailer have been fined a total of $140,000 under the Fair Trading Act for selling hot water bottles and toys that did not comply with mandatory safety requirements. Paramount Merchandise Company Limited (Paramount) was fined $104,000 after pleading guilty in the Manukau District Court... More>>