Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ARIM-mdx Data System: Towards a Nationwide Data Platform for Materials Science

Masatoshi Hanai, Ryo Ishikawa, Mitsuaki Kawamura, Masato Ohnishi, Norio Takenaka, Kou Nakamura, Daiju Matsumura, Seiji Fujikawa, Hiroki Sakamoto, Yukinori Ochiai, Tetsuo Okane, Shin-Ichiro Kuroki, Atsuo Yamada, Toyotaro Suzumura, Junichiro Shiomi, Kenjiro Taura, Yoshio Mita, Naoya Shibata, Yuichi Ikuhara

TL;DR

The paper addresses the lack of scalable nationwide data platforms for materials science that integrate experimental and computational data. It presents ARIM-mdx, a hybrid architecture combining petascale storage with cloud compute, direct IoT-based data transfer from standalone facilities, and high-speed national networks (SINET6) to support interactive analysis and HPC workflows. Key contributions include a complete system design, containerized compute via Jupyter and MateriApps LIVE!, cloud–storage integration, IoT data-transfer, and an evaluation demonstrating low latency and high throughput across a year of operation with hundreds of users. The work demonstrates the feasibility and potential impact of nationwide, cross-institutional data infrastructure for accelerating materials research.

Abstract

In modern materials science, effective and high-volume data management across leading-edge experimental facilities and world-class supercomputers is indispensable for cutting-edge research. However, existing integrated systems that handle data from these resources have primarily focused just on smaller-scale cross-institutional or single-domain operations. As a result, they often lack the scalability, efficiency, agility, and interdisciplinarity, needed for handling substantial volumes of data from various researchers. In this paper, we introduce ARIM-mdx data system, aiming at a nationwide data platform for materials science in Japan. Currently in its trial phase, the platform has been involving 11 universities and institutes all over Japan, and it is utilized by over 800 researchers from around 140 organizations in academia and industry, being intended to gradually expand its reach. The ARIM-mdx data system, as a pioneering nationwide data platform, has the potential to contribute to the creation of new research communities and accelerate innovations.

ARIM-mdx Data System: Towards a Nationwide Data Platform for Materials Science

TL;DR

The paper addresses the lack of scalable nationwide data platforms for materials science that integrate experimental and computational data. It presents ARIM-mdx, a hybrid architecture combining petascale storage with cloud compute, direct IoT-based data transfer from standalone facilities, and high-speed national networks (SINET6) to support interactive analysis and HPC workflows. Key contributions include a complete system design, containerized compute via Jupyter and MateriApps LIVE!, cloud–storage integration, IoT data-transfer, and an evaluation demonstrating low latency and high throughput across a year of operation with hundreds of users. The work demonstrates the feasibility and potential impact of nationwide, cross-institutional data infrastructure for accelerating materials research.

Abstract

In modern materials science, effective and high-volume data management across leading-edge experimental facilities and world-class supercomputers is indispensable for cutting-edge research. However, existing integrated systems that handle data from these resources have primarily focused just on smaller-scale cross-institutional or single-domain operations. As a result, they often lack the scalability, efficiency, agility, and interdisciplinarity, needed for handling substantial volumes of data from various researchers. In this paper, we introduce ARIM-mdx data system, aiming at a nationwide data platform for materials science in Japan. Currently in its trial phase, the platform has been involving 11 universities and institutes all over Japan, and it is utilized by over 800 researchers from around 140 organizations in academia and industry, being intended to gradually expand its reach. The ARIM-mdx data system, as a pioneering nationwide data platform, has the potential to contribute to the creation of new research communities and accelerate innovations.
Paper Structure (24 sections, 11 figures, 1 table)

This paper contains 24 sections, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background: MEXT ARIM Japan Project
  3. ARIM-mdx Data System: Overview
  4. Key Design Principles
  5. Usability
  6. Mixture of Interactive and Batch Workload
  7. Secure Data Transfer
  8. System Overview
  9. As a research data storage and analysis service
  10. For data analysis within experimental facilities
  11. As a service for managing and analyzing supercomputer-generated data
  12. Universities and Institutions Involved
  13. Implementation
  14. Cloud Internal Direct Connection
  15. IoT-based Networking of Standalone Material Facilities
  16. ...and 9 more sections

Figures (11)

  • Figure 1: Collaboration between experimental and theoretical materials science. The example shows a typical nanostructure analysis, where the atomic-scale image of the targeting material is obtained from the electron microscope whereas it is analyzed via computation-intensive theoretical simulation using the supercomputer to detect its structure. The raw image is obtained from ishikawa2022direct.
  • Figure 2: System overview.
  • Figure 3: System implementation.
  • Figure 4: Latency to the storage.
  • Figure 5: Throughput to the storage.
  • ...and 6 more figures