Bringing Big Data to Clean Energy Materials Discovery

将大数据引入清洁能源材料发现

• 批准号: 502052-2016
• 负责人: BERLINGUETTE, CURTIS
• 金额: $ 40.68万
• 依托单位: University of British Columbia
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=619394
• 关键词: Bringing; Big; Data; Clean; Energy

The Berlinguette research program focuses on developing advanced materials for clean energy production and storage. Google research is seeking to revolutionize materials science by using machine learning techniques to help researchers solve major research questions in new ways inaccessible to humans alone. A limitation to both these research programs is the lack of a capability to rapidly generate detailed characterization data for wide ranges of novel materials.This collaborative research program seeks to develop a microfabricated platform technology for performing simultaneous high-throughput materials fabrication, characterization and screening. The resulting microfabricated devices will use a multiplexed architecture to address large numbers of thin film samples with in situ electrochemical, electrical and thermal measurements. Microscopic and spectroscopic characterization tools will also be employed. These tools will provide both practical and fundamental insights into the characteristics of the studied materials.The Berlinguette research group is a pioneer in photochemical film growth methods that result in highly active electrocatalytic films. For this reason thin film samples will be grown photochemically as well as by electrosynthesis and through vapor deposition techniques. Dispensing film growth precursors and electrolytes via a microarray printer will allow a high throughput of systematically varied compositions of both films and electrolytes to be investigated. In collaboration with Google Inc, we will develop and deploy state-of-the-art big data analysis methodologies to make optimal use of the high volume of data this platform will produce. These technologies will enable the Berlinguette group to elucidate fundamental composition- and structure-property relationships and thus identify commercially viable clean energy materials at an unrivalled pace.

Berlinguette研究项目的重点是开发用于清洁能源生产和储存的先进材料。谷歌research正在寻求通过使用机器学习技术来帮助研究人员以人类无法单独实现的新方式解决重大研究问题，从而彻底改变材料科学。这两个研究项目的一个限制是缺乏快速生成广泛新材料的详细表征数据的能力。该合作研究项目旨在开发一种微加工平台技术，用于同时进行高通量材料制造、表征和筛选。由此产生的微制造器件将使用多路复用架构，通过原位电化学、电学和热测量来处理大量薄膜样品。显微镜和光谱表征工具也将被使用。这些工具将为所研究材料的特性提供实用和基本的见解。Berlinguette研究小组是光化学薄膜生长方法的先驱，这种方法可以产生高活性的电催化薄膜。由于这个原因，薄膜样品将通过光化学、电合成和气相沉积技术来生长。通过微阵列打印机分配薄膜生长前体和电解质将允许高通量系统地研究薄膜和电解质的不同组成。通过与谷歌公司合作，我们将开发和部署最先进的大数据分析方法，以最佳利用该平台将产生的大量数据。这些技术将使Berlinguette团队能够阐明基本的成分和结构-性质关系，从而以无与伦比的速度确定商业上可行的清洁能源材料。