Want to create interactive content? It’s easy in Genially!

Get started free

Copy - NTNU AI day

Idelfonso Bessa

Created on March 14, 2024

Start designing with a free template

Discover more than 1500 professional designs like these:

Transcript

All-FACET Meeting

Machine Learning as a Bridge: Enhanced High-Throughput Materials Screening Considering Application Scale

A short tal by Idelfonso Nogueira

Associate Professor in Process Systems EngineeringDepartment of Chemical Engineeringidelfonso.b.d.r.nogueira@ntnu.no +47 73592399 Kjemi 4, 232, Gløshaugen

Concise Integration: Developing a new standpoint of Chemical Engineering

L4

L3

L2

L1

15

Bridging two scales L1+L2

Modeling

Estimation

Experimental approach

Reliable

X Time demanding

X Limited to the system in analysis

Ab initio molecular simulations

High predictive capacity for several systems

X High computational cost

Bridging two scales L1+L2

Approach Ongoing Research

Advantages

If ML is used, only computational resources are used to build the data base

Molecular strucutures can be encoded as inputs

Reverse Engineering is easier, i.e., generative models.

Challenges

Creating a data base.

Encoding molecular and materials structures.

14

Bridging two scales L1+L2

Bridging two scales L1+L2

Bridging two scales L1+L2

General database

Bridging two scales L1+L2

Bridging two scales L1+L2

Bridging two scales L1+L2

Bridging three scales

Generative Neural Networks + Reinforcement learning + Process Scale

Bridging three scales

Generative Neural Networks + Reinforcement learning + Process Scale

Bridging three scales

Generative Neural Networks + Reinforcement learning + Process Scale

FundamentalScale

L1

L2

Process Design & Modeling

15

Let's discuss these topics Please feel free to ask or to get in touch!

Idelfonso Nogueira Associate Professor Department of Chemical Engineering Process Systems Engineering Research Group idelfonso.b.d.r.nogueira@ntnu.no +47 73592399 Kjemi 4, 232, Gløshaugen