Discover, Connect & Collaborate at TECHINNOVATION 2021

Machine Learning for Materials, Chemicals, and Advanced Manufacturing

Technology Overview

Our deep learning software helps development organisations in sectors including manufacturing, materials, chemicals, formulated products, and drug discovery to speed up innovation, reduce experimental costs, and gain breakthrough insights into their data.

Based on novel machine learning methods developed at the University of Cambridge with our company, our software is able to extract value from real-world experimental and process data, even where that data is sparse and noisy. Most conventional machine learning and data analysis approaches fail with sparse, noisy data. With this software you can optimise products and processes, save time by focusing experimental programs, and increase return on investment from expensively-acquired data.

Technology Features, Specifications and Advantages

Our deep learning software is powered by a novel machine learning algorithm developed at the University of Cambridge, which is able to train deep neural networks in order to build useful models from sparse, noisy data. Most machine learning methods can only predict or optimise properties for which they have a critical mass of fully-populated training data. Our software generates useful results even when there are significant gaps in data, as in most real-world experimental or process datasets.

Key capabilities that this enables are :

  • Enrich, validate, and understand existing data, maximising return on investment.
  • Guide experimental programs - for example, by telling the user what experiments to perform next to gain maximum information from minimum effort.
  • Propose novel products and processes that optimise target properties.
  • Test candidate products or process changes, reducing the need for expensive experiment or simulation.
  • Capture and share knowledge by providing company-standard models and tools.

Our software also helps with the deployment challenges many organisations face when they try to use machine learning in practice. Powerful machine learning techniques can be accessed by scientists, engineers, and analysts via a simple web browser interface, while data science teams can integrate its algorithms into existing tools and workflows.

Potential Applications

  • Design and optimisation of formulated products such as specialty chemicals, foods and beverages, inks, dyes, paints, and cosmetics.
  • Design of new materials and optimisation of related processes - e.g., metal alloys, ceramics, plastics, surface treatments.
  • Drug discovery - for example, guiding experimental programs to identify compounds of interest.
  • Additive Manufacturing - exploring critical property / process relationships and enabling data-driven decisions about AM processes.
  • Manufactured products - supporting informed decisions about product choices and process improvements, and enabling predictive maintenance.
  • Data science - extract value from any numerical or categorical dataset.

Customer Benefits

With our software, businesses extract value from experimental, process, or product data to :

  • Discover new product and process solutions, faster.
  • Identify product and process changes that enhance performance, increasing customer satisfaction and market share.
  • Solve or avoid problems in processing and production, reducing time-to-market, improving quality, and protecting the corporate reputation.
  • Dramatically reduce the amount of expensive experimentation required to achieve results (examples of 80%+ savings).
Contact Person

Stuart Dyer



Technology Category

  • Chemicals
  • Coatings/Paints
  • Life Sciences
  • Additive Manufacturing
  • Manufacturing
  • Materials
  • Ferrous Metals and Alloys, Non-Ferrous Metals and Alloys, Polymers

Technology Readiness Level


Machine learning, formulations, chemicals, materials, design of experiments, drug discovery, data science