Data-driven Simulations For Training AI-Based Segmentation of Neutron Images

Source of the Refl1d program for modeling and analyzing neutron and X-ray reflectometry data, with the addition of distributed roughness capability.

The open dataset, software, and other files accompanying the manuscript "An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models," submitted for publication to Integrated Materials and Manufacturing Innovations.Machine learning and autonomy are increasingly prevalent in materials science, but existing models are often trained or tuned using idealized data as absolute ground truths. In actual materials science, "ground truth" is often a matter of interpretation and is more readily determined by consensus. Here we present the data, software, and other files for a study using as-obtained diffraction data as a test case for evaluating the performance of machine learning models in the presence of differing expert opinions. We demonstrate that experts with similar backgrounds can disagree greatly even for something as intuitive as using diffraction to identify the start and end of a phase transformation. We then use a logarithmic likelihood method to evaluate the performance of machine learning models in relation to the consensus expert labels and their variance. We further illustrate this method's efficacy in ranking a number of state-of-the-art phase mapping algorithms. We propose a materials data challenge centered around the problem of evaluating models based on consensus with uncertainty. The data, labels, and code used in this study are all available online at data.gov, and the interested reader is encouraged to replicate and improve the existing models or to propose alternative methods for evaluating algorithmic performance.

A Wolfram Demonstration Template has been specialized to a model of a semiclassical model of photon echoes. An incident Gaussian pulse propagates through a material with a dielectric function in the form of a model Atomic Frequency Comb. The output pulse is calculated for seven values of the finesse of the comb.

The National Institute of Standards and Technology and the International Centre for Diffraction Data co-hosted a workshop on 17-18 October 2023 to identify and prioritize the goals, challenges, and opportunities for critical and emerging technology needs within industry, with an emphasis on leveraging artificial intelligence, data-driven methodologies, and high-throughput and automated workflows for accelerating x-ray-based structural analysis for materials development and manufacturing. Participants, predominantly from industry, gathered in-person at ICDD headquarters in Newtown Square, Pennsylvania. The data collected during this workshop is published in this data publication. This data is interpreted in the workshop report, which cites this dataset.Certain equipment, instruments, software, or materials, commercial or non-commercial, are identified in this dataset. Such identification does not imply recommendation or endorsement of any product or service by NIST, nor does it imply that the materials or equipment identified are necessarily the best available for the purpose.

프라 엣지에서 주변 동적객체를 2차원 Bounding Box 형태로 검출하기 위한 인공지능 학습 데이터 셋입니다.아래 링크에서 세부 정보를 확인하실 수 있으며 전체 데이터를 다운로드 받을 수 있습니다.https://nanum.etri.re.kr/share/teslasystem/Infra2DObjectDetection?lang=ko_KR

자율주행 차량에서 주변 동적객체를 3차원 Bounding Box 형태로 검출/추적하기 위한 인공지능 학습 데이터 셋입니다.카메라 및 레이더, 라이다 등의 다중 센서 기반으로 3차원 동적객체 검출 모델 학습에 활용할 수 있습니다.아래 링크에서 세부 정보를 확인하실 수 있으며 전제 데이터를 다운로드 받을 수 있습니다.https://nanum.etri.re.kr/share/sanmin0312/AD3OD?lang=ko_KR상기 데이터는 한국전자통신연구원, 카카오 모빌리티, 테슬라 시스템, 한국전자기술연구원, 한국과학기술원 등이 공동으로 협력하여 수행하는 자율주행혁신사업을 통해 구축한 데이터로 한국전자통신연구원에서 운영하는 ETRI AI 나눔 사이트를 통해 전체 데이터를 공개함담당자: 김산민 / 042-350-1286 / 한국과학기술원

시각 정보에 대한 이해를 위해 이미지의 유사성 이외에도 논리적 관계, 즉 성질의 유사성, 시각적 상식, 카테고리 등의 관계를 추론할 수 있는 인공지능 모델을 개발하기 위한 대규모 시각 추론 학습 데이터

Software to predict the optical sorting of particles in a standing-wave laser interference field