Join Brian Rohrback for his talk on ChemMLometrics. Perform. Repeat., November 16th at 10:15AM.
ChemMLometrics. Perform. Repeat.
Doing a one-off research project can be very satisfying, but in industry the money is made when the results of such a project can be placed into routine quality assessment. There is much discussion today revolving around machine learning and some of this discussion has invaded the space that has been occupied by chemometrics over the last few decades. There is a large overlap as these techniques are applied in instruments aimed at process quality control. To a large extent, any differentiation will simply be a question of the jargon chosen. An on-line Stanford University class on machine learning covers Principal Components Analysis, Principal Components Regression, Partial Least Squares, K-Nearest Neighbor, and other mainstays of the chemometrics toolbox. However, there are techniques that are new in the machine learning realm that can be employed for targeted tasks, improving the traditional chemometrics regime of supervised learning. The key is to narrow the focus for each component in a system and to understand the extent to which you can control the inputs. This talk highlights examples in optical spectroscopy calibration particularly for the identification of outliers, and in chromatography for both signal processing and the management of chromatographic libraries. The emphasis is to highlight both the similarities and the uniqueness of machine learning and chemometrics and show how they combine to form robust solutions for industry.
Join Brian Rohrback for his talk on Automating Calibrations for Optical Spectroscopy, November 16th at 1:30PM.
Automating Calibrations for Optical Spectroscopy
This talk represents a summary of a multi-industry consortium established eight years ago to re-evaluate how the calibration process in optical spectroscopy could be managed more efficiently. The idea is to enable a shift from current practices to approaches that take better advantage of the computational power and some newer concepts supplied by research into machine learning algorithms. The result is a solution that is not disruptive of any legacy instruments or software already in place and lessens the workload rather than laying on additional requirements. The approach uses all readily available components and can be assembled easily for any specified purpose. The use of commercial components reduces the cost of deployment and assembling pieces in a plug-and-play manner minimizes the impact of any previous selections of hardware and software.
Scott Ramos, recipient of the 2021 EAS Award for Outstanding Achievements in Chemometrics, will give his talk on “Multivariate Lessons for the Analytical Chemist”. Join us November 16th at 11am.
Multivariate Lessons for the Analytical Chemist
The field of chemometrics is a relatively new discipline, with its genesis about 40 years ago. Despite this relatively short history, it is now thriving as a vibrant area of research and practice, finding place in a wide variety of chemical applications. Some of the tools of the trade have found acceptance well outside of chemistry. For example, PLS (Partial Least Squares Regression) has become popular in statistics which was lacking methods for data with highly correlated variables.
Two main thrusts have propelled the evolution of chemometrics: innovation and evangelism. The toolkit available to practitioners is continually being augmented by improvements to current methods as well as creation of new algorithms. But, for the field to succeed, it must reach the hands of those who can benefit: the many analysts who utilize these tools in their daily work.
To meet the needs of already-overworked analysts, working solo or in teams, we can identify at least 3 ways in which multivariate tools can become part of the company work practice: hire a dedicated chemometrician, train one or more of staff members in the use of chemometrics, or contract an outside entity to provide chemometrics services.
Whichever the pathway a company chooses, understanding how best to optimize chemometrics models is paramount to success. This talk will review some of these concepts, covering issues that impact model quality, and will reflect on the viability of automating these decisions.
Join Brian Rohrback on 10/12/2021 at the Orchid Room, 9:40 AM – 10:10 AM.
A multi-industry consortium got together 8 years ago to rethink how calibrations need to be performed for spectroscopy instruments and analyzers. The priority was on solutions that are non-disruptive, fully utilize legacy systems, and lessen the workload rather than layer on additional requirements. The result is a foolproof, simple approach that can be used with any type of brand of spectrometer, any type or brand of chemometrics, and ensures robust and reliable calibrations. For more information, email firstname.lastname@example.org.
Join Brian Rohrback on October 5th at 11:00 am – 12:00 pm CST for panel discussion on The Role of Artificial Intelligence in Manufacturing and Petroleum Refining at the 2021 AFPM Summit.
Artificial intelligence and machine learning are inevitable results of the work driven by the consumer side of our economy. The question is not whether it will impact refining and chemical plant operation, but how soon and how long it will take for the benefits to outstrip the costs. The goal is to distinguish between vision and hallucination and to provide some practical guidance for making progress in this complicated set of fields. For more information, email email@example.com.