Poached eggs

How to boil an egg

Today I asked ChatGPT to explain to a robot how to boil an egg. After a brief pause, the Natural Language Processing model replied.

Here is a step-by-step explanation for a robot on how to boil an egg:

  1. Fill a saucepan with enough water to cover the eggs by about one inch.
  2. Place the saucepan on a stove and turn on the heat to high.
  3.  Use a temperature sensor to monitor the water temperature.
  4. Once the water reaches a boiling point (212°F or 100°C), carefully place the eggs in the boiling water using a mechanical arm or gripper.
  5. Set a timer for 4-9 minutes depending on the desired level of doneness (soft-boiled 4-5 minutes, medium-boiled 6-7 minutes, hard-boiled 8-9 minutes).
  6. Once the timer goes off, use a mechanical arm or gripper to remove the eggs from the boiling water and place them into a bowl filled with cold water.
  7. Use a timer to let the eggs sit in the cold water for a few minutes, then remove the eggs from the water.
  8. Gently crack the shells and peel them off, starting from the large end.

Note: It is important for the robot to have a mechanism for handling hot objects, such as heat-resistant gloves or tongs, to ensure the safety of the eggs and the robot.

Impressive as it certainly sounds, the description above is still too vague. Suppose we had a robot sophisticated enough to handle the operations described before. Will it be able to boil an egg? As humans, we understand perfectly the context and materials involved in the process. But what exactly is an egg? We have no doubt that a chicken’s egg will do the job, but so would a duck’s or goose’s egg. What about turtle’s eggs? They are indeed collected and eaten in certain parts of the world. Also, how does the stove operate? Depending on whether it uses gas, electricity or wood, there are additional constraints on the material the saucepan is made of. For instance, one made of aluminium won’t work on a modern induction stovetop.

These may sound like unnecessary complications to an otherwise simple and straightforward process. But even if these robots are not yet among us, something similar already exists. They are swarms of programs sieving the internet for content and meaning. We call them by the somewhat sinister name of “agents”. These agents interact with the Semantic Web, a technology that represents information in a manner that makes it easier for computers to understand and process.
One of the most apparent and defining services built on top of semantic web technologies is recommendation systems, such as those used by Netflix or Amazon, which make accurate recommendations based on the relationships between users, items, and context.

Ontologies are a crucial component of the semantic web, providing a common vocabulary and a shared understanding of concepts and relationships in a particular knowledge domain. In the semantic web context, an ontology is a machine-readable representation of knowledge expressed as a set of classes (or concepts) with relations operating between them. Ontologies have been used to unify the representation of gene and gene product attributes in molecular biology (Gene Ontology / GO); to describe things that are of interest in financial business applications and the ways that those things can relate to one another (Financial Industry Business Ontology / FIBO); or to enable interoperability between devices from different providers and among various activity sectors in the Internet of Things (Smart Applications REFerence ontology / SAREF), just to name a few examples.

In the field of applied sciences, the Elementary Multiperspective Material Ontology (EMMO) is a foundation (or top-level) ontology providing a common starting point for defining domain-specific and application ontologies. The EMMO is based on analytical philosophy and scientific principles. In particular, real world objects are represented in EMMO by different ways (perspectives) of understanding them. Perspectives are an expression of reductionism (i.e. objects are made of sub-objects) and epistemological pluralism (i.e. objects are always defined according to the perspective of an interpreter).  Furthermore, the way in which objects relate to each other is founded on principles of mereology (parthood) and causality.

To demonstrate the flexibility and expressivity of the EMMO, let us try to describe the process of boiling an egg using two different perspectives. From a strict process engineering point of view, it makes sense to use the Reductionistic perspective to decompose the process of boiling an egg (the “whole”) into steps that are causally connected in space and time. The process can be expressed as a workflow of causally-connected events (tiles), thus defining a beginning, the intermediate steps, and an end. At the same time, properties can be attached to each of the objects by using the Semiotic perspective. That way, the process can be fully characterised in terms of any known or observed physical quantities such as the mass of the objects, their temperature throughout the process, the inertia moment of the egg before and after being boiled, etc. To describe the materials involved, the Physicalistic perspective allows looking at the egg as a complex material. The egg is encased in a solid crust made of an inorganic salt embedded in an organic matrix. Boiling the egg then transforms the microscopic structure of the proteins in the egg’s white and yolk, turning them from a gel to a solid. These descriptions fulfil different purposes and are by no means the only possible ones. For example, another (Holistic) perspective would be to consider the egg’s role as food.

The power of ontologies resides in their ability to capture different requirements and levels of detail. On top of that, EMMO offers foundational rules based on physical principles and aims to provide a unified framework that supports the pluralisms of our observations and understanding and enables interoperability between the many different applications of material science.

Goldbeck Consulting is part of the development team of the EMMO. It is working on European projects ranging from connecting data sources to manufacturing processes to describing and deploying materials modelling workflows into open platforms.


What is a Translator in Knowledge Management

Current divisions in disciplines and data silos mean that there is a huge untapped value not just in terms of ‘lost’ data but also stakeholder knowledge, which currently is not well captured. The role of the Knowledge Management Translator is to work with materials and manufacturing domain experts as well as data scientists and knowledge engineers to shape data in order to express knowledge. The job of the Knowledge Management Translator is to bring together and orchestrate people, tools, and processes to achieve this.

Supported by the European H2020 OntoCommons project, a range of authors, representing the knowledge management translation ecosystem, got together and discussed the role in workshops and produced a paper outlining the role, including a structured approach to Knowledge Management Translation, as a process broken down into six steps.

Three priorities of data-driven development of advanced materials: Generate, Dcoument, Access and interrogate data and knowledge

Materials 2030 Roadmap draft published

A wide range of stakeholders in Europe are elaborating a roadmap for “a strong European Materials ecosystem driving the green and digital transition”. We are pleased to have contributed together with EMMC to Part I – Advanced materials – from vision to mission and action and the cross-cutting challenges. In particular, the roadmap proposes future actions to accelerate digitalisation of materials and product innovation highlighting three priorities:
1) Generating new data and knowledge: Develop digital and innovative methodologies for generating materials data and knowledge, including modelling, characterisation, production and testing technologies
2) Documenting data and knowledge: Develop and disseminate a common (standardized) language (ontology) for data exchange and knowledge management
3) Accessing and interogating data and knowledge: Provide reliable and easy access to and interrogation of generated data/information/knowledge
for all stakeholders

Goldbeck Consulting is involved in a range of projects supporting these actions, in particular in the areas of modelling, characterisation and ontologies.

Open Innovation Environments and their Importance in Materials Modelling and Materials Characterisation

Together with partners from the European H2020 OYSTER Open Innovation Environment (OIE) project, we put together a White Paper with some historical context to the development of Open Innovation and make the case that OIE and similar platform technologies are key enablers of open innovation in complex research fields such as materials science. They provide possibilities for participating in a wider Innovation Network Ecosystem involving all stakeholders from citizen to corporation. Thanks to Cambridge Nanomaterials Technology for their contribution.

Digital Marketplaces and their value for the Materials Modelling Ecosystem

We just published an overview paper of the emergence of digital marketplaces in the area of science driven industries, with a particular focus on materials modelling. Complex science and technology requires a wide range of tools and expertise, and benefits from assembling a network of skills and capabilities in an open innovation approach. Digital marketplaces are becoming crucial in orchestrating R&D that works in a complex ecosystem, ensure that a wider range of stakeholders and involved and that industry can access emerging developments from academia more readily. The paper discusses the emergence of marketplaces and e-commerce in general and provides successful examples of marketplaces in R&D outsourcing, materials expertise, data and simulations. Emerging marketplaces in materials modelling based on the EU H2020 MarketPlace and VIMMP projects are introduced.

Data background

OntoCommons: An industrial ontology journey of Standardisation, FAIR Data & Innovation

In this first webinar of the OntoCommons project we will provide a brief overview about the OntoCommons EcoSystem (OCES), Top Reference Ontologies, Industrial Domain Ontologies, FAIR Ontologies, Standardisation in the ontology ecosystem, the OntoCommons Community and the Focus Areas of the OntoCommons project.

The webinar will be held on 23 February 2021 at 2pm GMT (15:00 CET).

Ontologists, industrial stakeholders, implementers, and end users should participate to learn more about: 

  • The Ontology Commons EcoSystem (OCES)
  • The roles played by the Top Reference Ontologies, Industrial Domains and FAIR Ontologies
  • Standardisation in the ontology ecosytem
  • Our plans to grow the OntoCommons Community through engagement with key Focus Areas
Data background

OntoCommons: ontology-driven data documentation across materials and manufacturing domains

The OntoCommons project, an H2020 Coordination and Support Action, launched in November 2020 with three online kickoff sessions, during which more than 60 delegates from 19 partner organisations as well as Advisory Board Members discussed its objectives and actions.

OntoCommons aims to create harmonised and ontology-driven data documentation for Industry Commons, overcoming interoperability bottlenecks and facilitating data sharing and valorisation.

Over its thirty-six-month duration, the project will bring together and coordinate data documentation and standardisation activities from the most relevant EU and international stakeholders and initiatives.

OntoCommons provides a reliable turnkey solution for industrial stakeholders to confidently use ontologies in their businesses and to share their data. In addition, OntoCommons will prove the long-awaited key role of ontology in ensuring data interoperability and will promote data-driven innovation by boosting trust in the semantics of the shared industrial data.”   Hedi Karray – OntoCommons Technical Coordinator

Data background

European Materials & Modelling Ontology (EMMO) Release

The much anticipated release of EMMO is now available under a Creative Commons licence.

EMMO is a multidisciplinary effort to develop a standard representational framework (the ontology) based on physical sciences, materials modelling knowledge, analytical philosophy and information and communication technologies. EMMO is designed to be able to represent the complex multiscale nature of chemicals and materials, multiple perspectives on those and of course all types of models, represented in line with a previously established standard for materials modelling terminology and classification (CWA 17284). Properties of materials are strictly related to measurements, in line with ISO standards.  Quantum Mechanics representations cover the two major interpretations: Copenhagen and de Broglie-Bohm. All relations in the ontology are based on just four primitives: taxonomy (is-a relations), set-theory (membership), mereotopology (parthood and connections), and semiotics (representations, properties).

EMMO is ready to drive the integration of heterogeneous data sources, interoperability of modelling, integrated digital marketplaces and digitalisation of R&D. It is already being applied in a number of European projects (e.g. SimDome).

For further information there are resources on the EMMC website (note that registration may be required) which will be further updated with recordings of a recent EMMO Training workshop.  For reference, bookmark EMMO.tech or contact us via email.

Acknowledgement: EMMO is a result of the EMMC-CSA project which has received funding from the European Union‘s Horizon 2020 research and innovation programme under Grant Agreement No 723867.