Design & Production

The

of Next-Generation

Advanced Materials

The Design & Production of Next-Generation Advanced Materials

Consortia Partnerships 

Connect individuals and diverse communities with joint interests through funneled data sources, and promote collaborations between scientific leaders from your academia or industry network.

Sponsored Research Opportunities

Strategic feature discovery options, and accurate data models for academia and industries that share your common goals and scientific backgrounds.

Contract Research Organizations

Provide real-time research support and services on all your outsource requirements, cutting expenses, motoring and learning from fellow researchers.

Industry specific Case studies

Artificial Intelligence & Data Management for Colloidal Quantum Dots

The platform applies machine learning (ML) algorithms and online notebook management tools to the research on colloidal nanomaterials and their applications. MZ targets nanocrystal structures, highly luminescent quantum dots, and LED and PV devices.

MZ’s interfaces exploit large databases and suggest intelligent protocols for the synthesis of novel and improved crystals that are suitable for applications in the field of optoelectronics

In parallel, MZ will use ML for optimizing existing synthesis and fabrication protocols, also already employed at an industrial level, to obtain higher performance of the materials and devices, in particular for luminescent nanocrystals for solar concentration.

Consolidating data from Israels leading nano technology institute

Working with Israel’s leading NanoTech lab to make data available to its researchers, the MZ team took five years of experimental rust data and made it FAIR (Findable, Interoperable, Accessible and Re-usable).

One hypothesis is that rust can be fabricated to turn sunlight into electricity. Using the newly structured experimental data, the first attempt was to use ML (Machine Learning) and predict how to fabricate the optimal rust. The second attempt combined previous results, teaching the algorithm to find the optimal results on its own.

Based on the new recommendation results, the outcome was x5 greater than the previous 5 years, and with a higher reproducibility – all data was stored and accessible for any future research.

Turning skyscrapers into power plants

AI4QD is an EU funded bilateral agreement consortium. Glass to Power (G2P), Materials Zone (MZ) and IIT focused on the integration of luminescent nanocrystals in photovoltaic windows. The G2P team recently achieved an optical efficiency record of 6.8 percent and exceeded all their previous records.

Turning windows into solar panels, our platform is applying machine learning (ML) algorithms and utilising an online notebook management tool, to the research on colloidal nanomaterials and their applications. The interoperable data targets nanocrystal structures, highly luminescent quantum dots, and LED and PV devices.

MZ’s interfaces exploit large databases and suggest intelligent protocols for the synthesis of novel and improved crystals that are suitable for applications in the field of optoelectronics.

Wafer maps, histograms and correlation plots for Europes leading innovation hub

The experimental data generated by the metrology tools at our undisclosed R&D institute were under-exploited, with confidentiality constraints and complex diverse measurement report formats needing to be managed.

To overcome these limitations, the client joint hosted the experimental data and secured them by managing the confidentiality levels and visualizing the results in real-time to laboratories around the globe.

A database dedicated to the storage of data was setup, followed by a bespoke graphical user interface allowing access to the data. Files could also be exported and the interoperable visualizations demonstrated as a variety of chart types, wafer maps, histograms, and correlation plots.

Leveraging AI to create efficient production lines

A production line with many different processes, batch runs, and material properties to analyze is difficult to manage.

The products of the production line need to meet the strictest standards from the FDA, and efforts are being made towards minimizing the cost of products manufactured which don’t meet FDA standards and need to be disposed of.

The materials lifecycle management and advanced analytics practice designed, can alert the management of errors early on in the production line, and save the cost of production steps that result in products that don’t meet the requirements.