Materials Informatics: Augmenting Materials Research with Data-driven Design and Machine Learning

Lauri Himanen

Materials Informatics: Augmenting Materials Research with Data-driven Design and Machine Learning

Julkaisun otsikon käännös: Materiaali-informatiikka: datalähtöinen suunnittelu ja koneoppiminen materiaalitieteen tukena

Lauri Himanen

Tutkimustuotos: Doctoral Thesis › Collection of Articles

Abstrakti

Materiaalitiede pyrkii ymmärtämään ja mallintamaan materiaalien ominaisuuksia ja valjastamaan näitä ominaisuuksia erilaisiin sovelluksiin. Materiaali-informatiikka ja datalähtöinen materiaalitiede ovat yläkäsitteitä käytännöille, joissa olemassaolevia tietomassoja hyödynnetään tehokkaasti materiaalituntemuksen edistämiseksi. Tämä eroaa perinteisistä tieteellisistä lähestymistavoista, sillä prosessoidun tiedon määrä on suurempi vaatien lähes täysin automatisoituja menetelmiä. Tätä datalähtöistä lähestymistapaa on myös kutsuttu tieteen neljänneksi paradigmaksi. Se syntyyn ovat vaikuttaneet kyky tuottaa ja tallentaa suuria tietomääriä modernin tietokonelaitteiston ja -ohjelmiston avulla, avoimen tieteen periaatteiden käyttöönotto sekä tiedon louhintaan ja koneoppimiseen käytettyjen menetelmien kehitys. Tässä väitöskirjassa tarkastellaan kuinka materiaali-informatiikkaa voidaan tehokkaasti soveltaa materiaalitieteen nopeuttamiseen keskittyen laskennalliseen, atomistiseen materiaalien mallintamiseen. Aihe on jaettu kahteen eri osa-alueeseen: miten datalähtöistä suunnittelua ja siihen liittyviä työkaluja käytetään materiaalitiedon elinkaaren uudelleenjärjestämiseen ja kuinka erityisesti koneoppimista voidaan käyttää olemassa olevien tutkimusmenetelmien täydentämiseksi. Näitä aiheita lähestytään tutkimalla materiaali-informatiikan historiallista kehitystä ja nostamalla esiin nykyaikaisia työkaluja ja tekniikoita. Tämä yhteenveto tarjoaa oppaan kaikille, jotka ovat kiinnostuneita näiden menetelmien käyttöönotosta tutkimuksessaan tuoden samalla esiin materiaali-informatiikan keskeisimpiä haasteita.Tämän yleiskatsauksen jälkeen esitellään opintojen aikana suoritettu alkuperäinen materiaalitutkimus. Aluksi käydään läpi materiaali-informaatiikkaa varten kehitetyt avoimen lähdekoodin ohjelmistokirjastot. Nämä kirjastot käsittelevät monimutkaisten atomististen geometrioiden automaattista rakenteellista luokittelua ja materiaaleja kuvaavan syötteen tehokasta muodostamista koneoppimista varten. Seuraavaksi esitellään tutkimukset, joissa tiedon louhintaa ja koneoppista käytetään uusien materiaalien etsimiseen kahdessa eri sovelluskohteessa. Ensimmäisessä tutkimuksessa hyödynnetään materiaalitietokantoja etsittäessä optimaalisia pinnoitemateriaaleja perovskiittipohjaisille aurinkokennoille, kun taas toisessa tutkimuksessa käytetään koneoppimista katalyyttisesti aktiivisten sijaintien tunnistamiseen nanoklustereissa.

Julkaisun otsikon käännös	Materiaali-informatiikka: datalähtöinen suunnittelu ja koneoppiminen materiaalitieteen tukena
Alkuperäiskieli	Englanti
Pätevyys	Tohtorintutkinto
Myöntävä instituutio	Aalto-yliopisto
Valvoja/neuvonantaja	Rinke, Patrick, Vastuuprofessori Foster, Adam, Ohjaaja
Kustantaja	Aalto University
Painoksen ISBN	978-952-60-8950-8
Sähköinen ISBN	978-952-60-8951-5
Tila	Julkaistu - 2020
OKM-julkaisutyyppi	G5 Tohtorinväitöskirja (artikkeli)

Tutkimusalat

materiaali-informatiikka
materiaalitiede
koneoppiminen
datalähtöinen tiede

Pääsy asiakirjaan

http://urn.fi/URN:ISBN:978-952-60-8951-5

OpenUrl-saatavuus

Koko teksti

Siteeraa tätä

@phdthesis{19bb44ba0a924e9f914551170fe19314,

title = "Materials Informatics: Augmenting Materials Research with Data-driven Design and Machine Learning",

abstract = "Materials science is the systematic study and development of materials and their properties. Materials informatics and data-driven materials science are umbrella terms for the scientific practice of systematically extracting knowledge from data produced in materials science. This practice differs from traditional scientific approaches in materials research by the volume of processed data and the more automated way information is extracted. This data-driven approach — sometimes referred to as the 4th paradigm of science — is largely driven by the use of modern hardware and software for data production and storage, the Open Science movement and the methodological developments in data mining and machine learning. This dissertation reviews how materials informatics can be effectively applied to accelerate materials science, focusing on computational, atomistic materials modelling. The topic is divided into two different areas: how the data-driven design and tools are being used to re-imagine the life-cycle of materials data and how machine learning, in particular, can be used to complement existing research methodologies in materials science. These topics are explored by investigating the historical development of materials informatics and by highlighting the modern tools and techniques. This discussion provides a guide for anyone interested in deploying these methods in their research and also covers some of the key challenges that the field of materials informatics still faces. After this overview, the original materials informatics research performed during the studies is summarized. First, the open-source software libraries developed for materials informatics are introduced. These libraries deal specifically with tasks related to the automated structural classification of complex atomistic geometries and the efficient description of materials for machine learning. Next, the studies related to materials discovery using data mining and machine learning are discussed. The first study leverages materials databases in the search for optimal coating materials for perovskite-based photovoltaics while the second study focuses on using machine learning for identifying catalytically active sites on nanoclusters.",

keywords = "materials informatics, materials science, machine learning, data-driven science, materiaali-informatiikka, materiaalitiede, koneoppiminen, datal{\"a}ht{\"o}inen tiede, materials informatics, materials science, machine learning, data-driven science",

author = "Lauri Himanen",

year = "2020",

language = "English",

isbn = "978-952-60-8950-8",

series = "Aalto University publication series DOCTORAL DISSERTATIONS",

publisher = "Aalto University",

number = "26",

address = "Finland",

school = "Aalto University",

}

TY - THES

T1 - Materials Informatics

T2 - Augmenting Materials Research with Data-driven Design and Machine Learning

AU - Himanen, Lauri

PY - 2020

Y1 - 2020

N2 - Materials science is the systematic study and development of materials and their properties. Materials informatics and data-driven materials science are umbrella terms for the scientific practice of systematically extracting knowledge from data produced in materials science. This practice differs from traditional scientific approaches in materials research by the volume of processed data and the more automated way information is extracted. This data-driven approach — sometimes referred to as the 4th paradigm of science — is largely driven by the use of modern hardware and software for data production and storage, the Open Science movement and the methodological developments in data mining and machine learning. This dissertation reviews how materials informatics can be effectively applied to accelerate materials science, focusing on computational, atomistic materials modelling. The topic is divided into two different areas: how the data-driven design and tools are being used to re-imagine the life-cycle of materials data and how machine learning, in particular, can be used to complement existing research methodologies in materials science. These topics are explored by investigating the historical development of materials informatics and by highlighting the modern tools and techniques. This discussion provides a guide for anyone interested in deploying these methods in their research and also covers some of the key challenges that the field of materials informatics still faces. After this overview, the original materials informatics research performed during the studies is summarized. First, the open-source software libraries developed for materials informatics are introduced. These libraries deal specifically with tasks related to the automated structural classification of complex atomistic geometries and the efficient description of materials for machine learning. Next, the studies related to materials discovery using data mining and machine learning are discussed. The first study leverages materials databases in the search for optimal coating materials for perovskite-based photovoltaics while the second study focuses on using machine learning for identifying catalytically active sites on nanoclusters.

AB - Materials science is the systematic study and development of materials and their properties. Materials informatics and data-driven materials science are umbrella terms for the scientific practice of systematically extracting knowledge from data produced in materials science. This practice differs from traditional scientific approaches in materials research by the volume of processed data and the more automated way information is extracted. This data-driven approach — sometimes referred to as the 4th paradigm of science — is largely driven by the use of modern hardware and software for data production and storage, the Open Science movement and the methodological developments in data mining and machine learning. This dissertation reviews how materials informatics can be effectively applied to accelerate materials science, focusing on computational, atomistic materials modelling. The topic is divided into two different areas: how the data-driven design and tools are being used to re-imagine the life-cycle of materials data and how machine learning, in particular, can be used to complement existing research methodologies in materials science. These topics are explored by investigating the historical development of materials informatics and by highlighting the modern tools and techniques. This discussion provides a guide for anyone interested in deploying these methods in their research and also covers some of the key challenges that the field of materials informatics still faces. After this overview, the original materials informatics research performed during the studies is summarized. First, the open-source software libraries developed for materials informatics are introduced. These libraries deal specifically with tasks related to the automated structural classification of complex atomistic geometries and the efficient description of materials for machine learning. Next, the studies related to materials discovery using data mining and machine learning are discussed. The first study leverages materials databases in the search for optimal coating materials for perovskite-based photovoltaics while the second study focuses on using machine learning for identifying catalytically active sites on nanoclusters.

KW - materials informatics

KW - materials science

KW - machine learning

KW - data-driven science

KW - materiaali-informatiikka

KW - materiaalitiede

KW - koneoppiminen

KW - datalähtöinen tiede

KW - materials informatics

KW - materials science

KW - machine learning

KW - data-driven science

M3 - Doctoral Thesis

SN - 978-952-60-8950-8

T3 - Aalto University publication series DOCTORAL DISSERTATIONS

PB - Aalto University

ER -

Materials Informatics: Augmenting Materials Research with Data-driven Design and Machine Learning

Abstrakti

Tutkimusalat

Pääsy asiakirjaan

OpenUrl-saatavuus

Sormenjälki

Siteeraa tätä