Materials Informatics 2022-2032
Data-centric approaches for design and discovery within materials science R&D. Notable advancements in data infrastructures and machine learning. Player profiles, technology progression, market outlook, business models, and case studies.
Materials Informatics is an R&D paradigm shift, enabling discoveries and cutting the time to market.
Materials Informatics represents an R&D paradigm shift by fundamentally accelerating the time from innovation to market. There are multiple strategic approaches and already some notable success stories; missing this transition will be very costly.
This report provides key insights and outlooks on the market. Through technical primary interviews, readers will get a detailed understanding of the players, business models, technology, and the application areas.
Materials informatics (MI) involves using data-centric approaches for materials science R&D. There are multiple strategic approaches and already some notable success stories; the adoption is happening now and missing this transition will be very costly.
This report provides key insights and commercial outlooks for this emerging field. Built upon technical primary interviews, readers will get a detailed understanding of the players, business models, technology, and the application areas.
What is materials informatics?
Materials informatics is the use of data-centric approaches for the advancement of materials science. This can take numerous forms and influence all parts of R&D (hypothesis - data handling & acquisition - data analysis - knowledge extraction).
Primarily, MI is based on using data infrastructures and leveraging machine learning solutions for the design of new materials, discovery of materials for a given application, and optimisation of how they are processed.
MI can accelerate the "forward" direction of innovation (properties are realised for an input material) but the idealised solution is to enable the "inverse" direction (materials are designed given desired properties).
This is not straight-forward and is still at a nascent stage. In many cases, the data infrastructure is not comprehensive and MI algorithms are often too immature for the given experimental data. The challenge is not the same as in other AI-led areas (such as autonomous cars or social media), the players are often dealing with sparse, high-dimensional, biased, and noisy data; leveraging domain knowledge is an essential part of most approaches.
Contrary to what some may believe, this is not something that will displace research scientists; if integrated correctly, MI will become a set of enabling technologies accelerating their R&D process. For many, the dream end-goal is for humans to oversee an autonomous self-driving laboratory; although still at an early-stage there have been key improvements, spin-out companies formed, and success stories all facilitated by MI developments.
This is not a new approach, many sectors have adopted similar design approaches for decades. But there are three main reasons why this transformative technology is impacting the materials science space right now:
- Improvements in AI-driven solutions leveraged from other sectors.
- Improvements in data infrastructures, from open-access data repositories to cloud-based research platforms.
- Awareness, education, and a need to keep up with the underlying pace of innovation.
IDTechEx have classified the projects undertaken into eight main categories outlined in detail within the report. Within that, there are three repeated advantages to employing advanced machine learning techniques into your R&D process: enhanced screening of candidates & scoping research areas, reducing the number of experiments to develop a new material (and therefore time to market), and finding new materials or relationships. The training data can be based on internal experimental, computational simulation and/or from external data repositories; enhanced laboratory informatics and high throughput experimentation or computation can be integral to many projects.
This report looks at the key progressions in machine learning for MI, the success stories, and how end-users are actively engaging with this.
What are the strategic approaches?
Ignoring this R&D transition is a major oversight for any company that designs materials or designs with materials. The impact will not be seen immediately, but in the mid- to long-term the missed opportunity will be significant. This could be when bringing competitive products to market, developing versatility in the supply chain, finding next-generation opportunities, or generating the ability to diversify a business unit or material portfolio.
Numerous players have already begun this adoption with three core approaches: operate fully in-house, work with an external company, or join forces as part of a consortium.
Each of these approaches is appraised in detail in the report; choosing to start the adoption of MI is important, choosing the right path is essential.
The external MI players can come from numerous starting points, as outlined in the figure below. There is also the option for MI players to become a licencing company with a strong advanced material portfolio and also for end-users to offer MI as a service. Geographically, many of the end-users embracing this technology are Japanese companies, many of the emerging external companies are from USA, and the most notable consortia and academic labs are split across Japan and the USA.
Interview based profiles of all the key companies are included within this IDTechEx report.
Summary of different MI players. Source: Material Informatics 2022-2032.
What application areas are successfully using this?
Organic electronics, battery compositions, additive manufacturing alloys, polyurethane formulations, and nanomaterial development are all examples of areas that MI is having an immediate impact on. The broad range of material use-cases means industrial adoption is being seen from electronics manufacturers to chemical companies.
There are universal challenges, but each application area will have certain considerations, be it in the availability of existing data, the domain knowledge, the complexity of the structure-property relationships, and more.
The final part of this report goes into detail on each applications area in turn, highlighting key developments, commercial use-cases, and notable publications. This provides end-users the opportunity to focus on case studies in their specific areas of interest, and informs MI players on what areas to explore.
What will I learn from the report?
This market report is released at a point in time where the 10-year outlook is prime for rapid adoption. This report goes far beyond what is available on the internet, providing key commercial outlooks based on primary-interviews coupled with expertise on both this topic and numerous of the relevant application areas.
In recent years there has been significant progression in external companies providing MI solutions, more key partnerships and end-user engagements, new consortium and academic advancements, and new companies emerging. All of this is tracked, explained and analysed throughout this industry-leading report on the topic.
Market forecasts, player profiles, investments, roadmaps, and comprehensive company lists are all provided, making this essential reading for anyone wanting to get ahead in this field.
Analyst access from IDTechEx
All report purchases include up to 30 minutes telephone time with an expert analyst who will help you link key findings in the report to the business issues you're addressing. This needs to be used within three months of purchasing the report.
TABLE OF CONTENTS
1. EXECUTIVE SUMMARY AND CONCLUSIONS
- 1.1. What is materials informatics?
- 1.2. Overview of significant industry activity
- 1.3. Latest key news and developments
- 1.4. AI opportunities at every stage of materials design and development
- 1.5. Problems with materials science data
- 1.6. Key areas of algorithm advancements
- 1.7. Materials informatics players - categories
- 1.8. Conclusions and outlook for strategic approaches
- 1.9. Main players
- 1.10. Key partners and customers of external providers
- 1.11. Notable MI consortia
- 1.12. Project categories
- 1.13. Company Profiles - links to 24 IDTechEx company profiles
- 2.1. Common abbreviations
- 2.2. What is materials informatics?
- 2.3. Materials informatics - why now?
- 2.4. What can ML/AI do in materials science?
- 2.5. Materials Informatics - category definitions
- 2.6. The broader informatics space in science and engineering
- 2.7. The broader informatics space in science and engineering
- 2.8. Key challenges for MI across the full materials spectrum
- 2.9. Closing-the-loop on traditional synthetic approaches
- 2.10. High Throughput Virtual Screening (HTVS)
- 2.11. Advantages of ML for chemistry and materials science - Acceleration
- 2.12. Advantages of ML for chemistry and materials science - Scoping and screening
- 2.13. Advantages of ML for chemistry and materials science - New species and relationships
- 2.14. Data infrastructures for chemistry and materials science
3. TECHNOLOGY ASSESSMENT
- 3.1. Overview
- 3.1.1. Inputs and outputs of materials informatics algorithms
- 3.1.2. What is needed for materials informatics?
- 3.1.3. Summary of technology approaches
- 3.1.4. Uncertainty in Experimental Data Undermines Analysis
- 3.1.5. QSAR and QSPR: The role of regression analysis
- 3.2. MI algorithms
- 3.2.1. Overview of MI algorithms
- 3.2.2. Descriptors and training a model
- 3.2.3. Automated feature selection
- 3.2.4. Exploitation vs Exploration
- 3.2.5. Types of MI algorithms - supervised vs unsupervised
- 3.2.6. Types of MI algorithms - typical supervised models
- 3.2.7. Types of MI algorithms - Bayesian optimization
- 3.2.8. Types of MI algorithms - unsupervised case study
- 3.2.9. Types of MI algorithms - generative vs discriminative
- 3.2.10. Types of MI algorithms - deep learning
- 3.2.11. Generative Models for Inorganic Compounds
- 3.2.12. How to work with small material datasets
- 3.2.13. Deep learning with small material datasets
- 3.2.14. Key areas of algorithm advancements
- 3.3. Establishing a data infrastructure
- 3.3.1. A data infrastructure is critical for MI
- 3.3.2. Developments targeted for chemical and materials science
- 3.4. External databases
- 3.4.1. Data repositories - organisations
- 3.4.2. Data repositories - trends
- 3.4.3. Leveraging data repositories
- 3.4.4. Text Extraction and Analysis
- 3.4.5. Data mining publications and patents
- 3.4.6. Annotating and extracting the relevant information
- 3.5. MI with physical experiments and characterisation
- 3.5.1. Achieving high-volumes of physical experimental data
- 3.5.2. High-throughput spectroscopy
- 3.5.3. In-situ spectroscopy developments
- 3.6. MI with computational materials science
- 3.6.1. Simulations for chemistry and materials science R&D
- 3.6.2. ICME and the role of machine learning
- 3.6.3. Generating and Using the Largest Computational Materials Science Database
- 3.6.4. Explorative Design Utilising Cloud-Based Simulation
- 3.6.5. The potential in leveraging quantum computing
- 3.6.6. Computation Autonomy for Materials Discovery
- 3.7. Autonomous labs
- 3.7.1. The future - fully autonomous labs
- 3.7.2. The future - "Chemputer"
- 3.7.3. A Chemputer to explore chemical space
- 3.7.4. Workflow management for laboratory automation
- 3.7.5. Autonomous High Throughput Experimentation
- 3.7.6. Commercial self-driving-laboratories
- 3.7.7. Mobile Autonomous Robot
- 3.7.8. Retrosynthesis through to robot execution
- 3.7.9. Three technology pillars to chemical autonomy
4. COMPANY ANALYSIS
- 4.1. Overview of significant industry activity
- 4.2. Latest key news and developments
- 4.3. Materials informatics players - categories
- 4.4. Conclusions and outlook for strategic approaches
- 4.5. Materials Informatics players - Overview
- 4.6. Key partners and customers of external providers
- 4.7. Partnerships with engineering simulation software
- 4.8. Funding raised by private companies
- 4.9. Significant market growth
- 4.10. Full player list - private companies
- 4.11. Main players
- 4.12. Full player list - public organisations
- 4.13. Support in building in-house capability
- 4.14. Taking the operation in-house
- 4.15. Commercial retrosynthesis predictors
- 4.16. Notable MI consortia
- 4.17. Public-private collaborations
- 4.18. Materials Genome Initiative (MGI)
- 4.19. Materials Genome Engineering (MGE)
- 4.20. Additional key initiatives and research centres around the world
- 4.21. Materials development via synthetic biology
- 4.22. COVID-19 and materials informatics (MI)
- 4.23. Sector-by-sector impact
5. APPLICATIONS AND CASE STUDIES
- 5.1. Case studies - overview
- 5.2. Market forecast
- 5.3. Materials informatics roadmap
- 5.4. Project categories
- 5.5. Materials informatics - market penetration by maturity
- 5.6. Microscopy: Accelerating process and synthetic uses
- 5.7. Improving the use of Synchrotron Light Sources
- 5.8. Aluminium and titanium alloys
- 5.9. Metallic glass alloys
- 5.10. Nickel-base superalloys
- 5.11. High-entropy alloys
- 5.12. Intermetallics
- 5.13. Coatings
- 5.14. Organic electronics - OLED
- 5.15. Organic electronics - RFID
- 5.16. Organic electronics - OPV
- 5.17. Organic electronics - beyond
- 5.18. Catalysts
- 5.19. Ionic Liquids
- 5.20. Superconductors
- 5.21. Toxic chemicals
- 5.22. Energy storage: Lithium-ion batteries
- 5.23. Polymers and composites
- 5.24. Polymer Informatics
- 5.25. Lubricants
- 5.26. Thermoelectrics
- 5.27. Organometallics
- 5.28. 2D materials
- 5.29. Nanofabrication
- 5.30. Quantum Dots
- 5.31. Other nanomaterials
- 5.32. Metal-insulator transition compounds
- 5.33. Light absorbers and solar cells
- 5.34. Perovskite photovoltaics
- 5.35. Self-assembled monolayers
- 5.36. Metamaterials
6. COMPANY PROFILES
- 6.1. Company Profiles - links to 24 IDTechEx company profiles