Artificial intelligence designs advanced materials
Scientists of the Max-Planck-Institut für Eisenforschung pioneer new machine learning model for corrosion-resistant alloy design
2023-08-11
(Press-News.org)
In a world where annual economic losses from corrosion surpass 2.5 trillion US Dollars, the quest for corrosion-resistant alloys and protective coatings is unbroken. Artificial intelligence (AI) is playing an increasingly pivotal role in designing new alloys. Yet, the predictive power of AI models in foreseeing corrosion behaviour and suggesting optimal alloy formulas has remained elusive. Scientists of the Max-Planck-Institut für Eisenforschung (MPIE) have now developed a machine learning model that enhances the predictive accuracy by up to 15% compared to existing frameworks. This model uncovers new, but realistic corrosion-resistant alloy compositions. Its distinct power arises from fusing both numerical and textual data. Initially developed for the critical realm of resisting pitting corrosion in high-strength alloys, this model's versatility can be extended to all alloy properties. The researchers published their latest results in the journal Science Advances.
Merging texts and numbers
“Every alloy has unique properties concerning its corrosion resistance. These properties do not only depend on the alloy composition itself, but also on the alloy’s manufacturing process. Current machine learning models are only able to benefit from numerical data. However, processing methodologies and experimental testing protocols, which are mostly documented by textual descriptors, are crucial to explain corrosion,”, explains Kasturi Narasimha Sasidhar, lead author of the publication and former postdoctoral researcher at MPIE. The researcher team used language processing methods, akin to ChatGPT, in combination with machine learning (ML) techniques for numerical data and developed a fully automated natural language processing framework. Moreover, involving textual data into the ML framework allows to identify enhanced alloy compositions resistant to pitting corrosion. “We trained the deep-learning model with intrinsic data that contain information about corrosion properties and composition. Now the model is capable of identifying alloy compositions that are critical for corrosion-resistance even if the individual elements were not fed initially into the model”, says Michael Rohwerder, co-author of the publication and head of the group Corrosion at MPIE.
Pushing boundaries: automated data mining and image processing
In the recently devised framework, Sasidhar and his team harnessed manually gathered data as textual descriptors. Presently, their objective lies in automating the process of data mining and seamlessly integrating it into the existing framework. The incorporation of microscopy images marks another milestone, envisioning the next generation of AI frameworks that converge textual, numerical, and image-based data.
END
ELSE PRESS RELEASES FROM THIS DATE:
2023-08-11
Effluents from wastewater treatment plants have a dual effect: Some species disappear, while others benefit. Especially certain insect orders, such as stonefly and caddisfly larvae, are decimated. Certain worms and crustaceans, by contrast, can increase in number. A team from Goethe University Frankfurt led by Daniel Enns and Dr. Jonas Jourdan has corroborated this in a comprehensive study, which has now been published in the journal Water Research. They examined 170 wastewater treatment plants in Hesse in relation to species composition.
Wastewater treatment plants are ...
2023-08-11
URBANA, Ill. – Producers of infant formula employ comprehensive food safety systems, including product testing to ensure those systems are working. A new study from the University of Illinois Urbana-Champaign finds that some testing methods are more powerful at catching contaminants than others.
Spacing out samples over time in a stratified sampling pattern is better at catching risky pathogens like Cronobacter than randomly sampling from the product as it is being produced, the researchers found. Furthermore, while taking more samples of product generally increases the chance to catch the pathogen, there is a point after which it ...
2023-08-11
EL PASO, Texas (Aug. 11, 2023) – How are our region’s pecan farms affected by drought? Is there a better way to address domestic violence in Ciudad Juárez? These are a few of the big questions scientists are asking as they prepare to embark on a new cross-border research collaboration.
Created by The University of Texas at El Paso, the U.S.-Mexico Faculty Collaboration Fellowship program will support research projects with higher education institutions in the State of Chihuahua to spur studies on issues ...
2023-08-11
Watermelon is a globally significant agricultural product, both in terms of the total amount produced and the total economic value generated.
Scientists at the Boyce Thompson Institute have constructed a comprehensive "super-pangenome" for watermelon and its wild relatives, uncovering beneficial genes lost during domestication that could improve disease resistance and fruit quality of this vital fruit crop.
"We aimed to delve deeper into the genetic variations that make watermelons so diverse and unique," stated ...
2023-08-11
Historically, the Arctic was considered a pristine region, but scientific research spanning the last three decades has revealed the harsh reality of long-range transported pollutants reaching the Arctic from different corners of the world. In response to this alarming discovery, AMAP was created with the mission to monitor pollution and its effects on the Arctic environment and human health.
In a new article published on 26 July 2023, in the journal Environmental Science and Ecotechnology, researchers from Arctic Knowledge Ltd, presents the initiation and implementation of a systematic scientific and political cooperation in the Arctic related to environmental ...
2023-08-11
Directing light from place to the place is the backbone of our modern world. Beneath the oceans and across continents, fiber optic cables carry light that encodes everything from YouTube videos to banking transmissions—all inside strands about the size of a hair.
University of Chicago Prof. Jiwoong Park, however, wondered what would happen if you made even thinner and flatter strands—in effect, so thin that they’re actually 2D instead of 3D. What would happen to the light?
Through a series of innovative experiments, he and his team found ...
2023-08-11
An experimental malaria vaccine appears safe and promotes an immune response in African infants, one of the groups most vulnerable to severe malaria disease. There is currently only one malaria vaccine, “RTS,S” that is approved by the World Health Organization and offers partial disease protection. However, in the results of the early-stage phase Ib trial conducted in Tanzania and published on August 11th in the journal Med, researchers find that targeting RH5 – a protein that the malaria pathogen Plasmodium falciparum uses to invade red blood cells – can generate a promising immune response ...
2023-08-11
From text-generating ChatGPT to voice-activated Siri, artificial intelligence-powered tools are designed to aid our everyday life — as long as you speak a language they support. These technologies are out of reach for billions of people who don’t use English, French, Spanish or other mainstream languages, but researchers in Africa are looking to change that. In a study published August 11 in the journal Patterns, scientists draw a roadmap to develop better AI-driven tools for African languages.
“It doesn’t ...
2023-08-11
Scientists have developed a synthetic extracellular matrix (ECM) that can support the growth of a mini endometrium in a dish for at least two weeks. The endometrium—the mucosal lining of the uterus—has been historically hard to model in the lab, which has limited scientists’ ability to study its role in healthy and diseased states like endometriosis. The matrix, described on August 11 in the journal Med, allows cells to interact in an environment that recapitulates human physiology which could help researchers better simulate the healthy and pathological response to menstrual cycles.
“With this matrix, we can begin to extrapolate and utilize ...
2023-08-11
LA JOLLA (August 11, 2023)—Glioblastoma, the most common and deadly form of brain cancer, grows rapidly to invade and destroy healthy brain tissue. The tumor sends out cancerous tendrils into the brain that make surgical tumor removal extremely difficult or impossible.
Now, Salk scientists have found the immunotherapy treatment anti-CTLA-4 leads to considerably greater survival of mice with glioblastoma. Furthermore, they discovered that this therapy was dependent on immune cells called CD4+ T cells infiltrating the brain and triggering the tumor-destructive activities of other immune cells ...
LAST 30 PRESS RELEASES:
[Press-News.org] Artificial intelligence designs advanced materials
Scientists of the Max-Planck-Institut für Eisenforschung pioneer new machine learning model for corrosion-resistant alloy design
