Digital Hub Karlsruhe | EDIH-AICS’ Post

Cenovus Energy is making a groundbreaking move in Quantum Causal Inference! They've partnered with Perimeter to support innovative research in this field with immense possibilities. 🌌 Quantum causal inference transforms machine learning, moving artificial intelligence beyond pattern-finding to revealing and predicting complex networks of cause and effect. Research can lead to algorithms that extract cause-and-effect insights from large statistical datasets, more powerfully and authoritatively than any existing technology. This collaboration between Cenovus and Perimeter is poised to support a high-impact research area that could shape tomorrow’s technologies. Check out the full article on this exciting initiative here: https://hubs.ly/Q0236xKp0 #quantum #quantumcanada #quantumresearch

Cenovus Energy is partnering with Perimeter Institute in the exciting and promising field of Quantum Causal Inference - moving AI beyond pattern recognition into the prediction and gaining insights of complex cause and effect from large statistical data sets. This is an exciting and promising area of research. Learn more of the implications of this area at this link https://lnkd.in/gHXgj3n5 #quantum #causalinference #quantumresearch

If you are at the #ACCGE Conference from August 13-18 in Tucson, Arizona make sure you attend G-Space, Inc., Chief Product Officer Christianna Taylor, PhD's presentation to learn more about how #microgravity #research #analytics, applied to #microgravity R&D investigations or #inspace manufacturing, could help save time, money and derisk data! The presentation "An AI Predictive Platform for Microgravity Innovation" will take place Monday, Aug 14th, from 2:20PM - 2:40PM in the "Reduced Crystal Growth Symposium" session. In this talk, G-Space, Inc. will provide an overview of its specialized Microgravity R&D algorithms as applied to a variety of microgravity science problems. By leveraging such tools, customers can perform valuable microgravity analytics at the blink of an eye and exponentially expand the extraction of key scientific information. As the G-SPACE microgravity data set keeps growing so does the ability of these physics models and ML algorithms to turn into powerful predictive tools. Contact us at info_at_g-space.com for a demo. We’d love to hear the challenges you have with your microgravity data sets and see how we can help. Hope to see you at the presentation! Reach out to Christianna Taylor, PhD Taylor to connect at the conference.

Simulating 2.2 million crystal structures with 80% accuracy and creating 41 new materials in just 17 days – This is an AI breakthrough! 🌐 👏 To navigate industry shifts and avoid the pitfalls of past giants like Kodak and Blockbuster, agility is crucial. 🚀 #AIInnovation #MaterialScience

With his forward-thinking approach to monitoring data of the #PowderBedFusion process with #AI, Simon Oster was able to show that defects, such as lack of fusion and keyhole porosities, can be predicted successfully at a layer-by-layer basis. We are delighted to share that his scientific paper “Potentials and challenges of deep-learning-assisted porosity prediction based on thermographic in situ monitoring in laser powder bed fusion” won the “paper of the month award” in the field of analytical science at Bundesanstalt für Materialforschung und -prüfung🎉 📣For the AI and PBF-LB/M community: Check out the paper (link below) to learn more about the exciting subject of defect prediction using thermographic in-situ monitoring data, a door opener for real-time quality assurance during the #PowderBedFusion process. 🤖 Objective: AI-supported prediction of defects (porosities) based on thermographic features collected during the AM process (e.g., melt pool geometry and temperature). 🚀 Opportunity: Accurate prediction of layer-by-layer porosities in PBF-LB/M parts 🙏 Many thanks to the co-authors Nils Scheuschner, Keerthana Chand and Simon Altenburg from #BAM as well as Gerald Gerlach from Technische Universität Dresden!  Find out more here 👇 https://lnkd.in/enYXChyS

FAQ #7: What are the short-term and long-term business goals? In the short term, the goal is to create a sustainable global environment through the global dissemination and adoption of AI smart electronic generator technology. In the long term, the foundation aims to operate as a global aerospace research institute through future innovative technologies, contributing to the development of Earth science on a global scale.

Our #SISPAD #2023 papers are now published in IEEE Xplore. If you want to know more about our work in #ML, #AI and #devicemodelling and #devicesimulation, please have a look at Preslav Aleksandrov's great work : 1. Fully Convolutional Generative Machine Learning Method for Accelerating Non-Equilibrium Green’s Function Simulations (https://lnkd.in/dNgeb4Sj). If you want to know more about #ISFETs #biosensors #simulator #modelling, have a look at Naveen Kumar excellent job: 2. Electrolyte-Gated FET-based Sensing of Immobilized Amphoteric Molecules Including the Variability in Affinity of the Reactive Sites (https://lnkd.in/dSiqaDS5) James Watt School of Engineering, University of Glasgow

Lithium-ion batteries are vital for providing energy as either the primary or backup power source. However, assessing their state of health (SoH) is challenging due to the lack of real-world discharge data. To address this, accelerated aging is used to estimate SoH by simulating degradation. Yet, accelerated aging creates complex deterioration patterns due to harsh conditions and nonlinearity. In this context, we proposed a predictive model that addresses incomplete data problems in two ways. Firstly, it introduces a robust collaborative feature extractor (RCFE) by combining improved restricted Boltzmann machines (I-RBMs) to create a more generalized global extraction model, overcoming the lack of patterns. Secondly, a set of RCFEs is evolved through a neural network with an augmented hidden layer (NAHL) to enhance predictive ability and tackle pattern complexity. This proposal is described in a paper titled “Lithium-ion battery state of health prediction with a robust collaborative augmented hidden layer feedforward neural network approach,” IEEE Transactions on Transportation Electrification, vol. 9, n°3, pp. 4492–4502, September 2023. It is co-authored by Tarek Berghout, Mohamed Benbouzid, Yassine AMIRAT, and Gang Yao. This was a collaboration between the Université de Batna 2, the Université de Bretagne Occidentale, ISEN Yncréa Ouest Brest, and the Shanghai Maritime University.   Link to the paper: https://lnkd.in/eK64gxp7   IRDL - UMR CNRS 6027/UBS/ENSTA-Bretagne/ENIB/UBO