IFPAC 2023 – The Multiverse of Challenges for Spectral Libraries

IFPAC 2023 Conference Short Course and Paper

Time to be announced
Bethesda North Marriott Hotel and Conference Center

Presented by:
Brian Rohrback, Ph.D., MBA, President, Infometrix, Inc.


There are challenges when considering application-specific libraries of optical spectra. For most quality control applications in industry, there is no standard set of spectra available as the process is typically tied to a set of (unique) analytes mixed in various proportions. Add in changes from ingredient suppliers, seasonal variations, and changes in unit operation, there is not a pinpoint target for assessing quality. Luckily, we have more than a half century of processing data like this using chemometrics and the newer moniker machine learning. But handling process libraries is not just a simple application of an appropriate algorithm; there are challenges that need to be considered in all aspects of sample collection, handling instrument drift, and ensuring consistency across all operators. An outline of best practices needs to include how to match laboratory reference data to spectral data, an unbiased mechanism for selecting validation samples, an optimal mechanism for model construction, establishing standards for quality reports, tracking model performance over time, handling process or ingredient transitions, and much more. A systematic approach to building, maintaining, and benefiting from an application-specific spectral library is presented as part of the USP effort to establish appropriate standard practices.

Register at www.IFPACglobal.org/attendee-registration.

IFPAC 2023 – Speed Dating Chemometrics and Machine Learning

IFPAC 2023 ConferenceVenue:
June 4, 2023, 8:30am – 12:00pm
Bethesda North Marriott Hotel and Conference Center

Presented by:
Brian Rohrback, Ph.D., MBA, President, Infometrix, Inc.
Barry M. Wise, Ph.D., President, Eigenvector Research, Inc.



Course Description:

There is a lot of confusion on what constitutes best practices in the application of multivariate statistics to laboratory, process, and field analytics. The terminology in use does not always clarify and most of the time a technique touted in the literature is not compared to any other technology that could be applied to the same problem. Tools from chemometrics and machine learning categories benefit from some user experience and this course is aimed at refreshing the basics of the field of multivariate analysis and data visualization, supplying applications that tie to routine product quality maintenance, and focusing in on the most common use of the algorithms – those employed in instrument calibration.

An introduction to data visualization and exploratory data analysis techniques such as principal component analysis (PCA) and hierarchical cluster analysis (HCA) will be covered along with the practical basis for their use. A wide variety of examples will be shown ranging from laboratory analysis, in-line and on-line process monitoring, and field applications. Infometrix President Brian Rohrback will cover the thought process that helps organize and complete the implementation of a bespoke evaluation system.

Calibration models are a critical part of spectroscopic and other methods in Process Analytical Technology (PAT) and in the laboratory. But there’s more to getting a good calibration model than simply measuring a few samples and doing a Partial Least Squares (PLS) regression. The process starts with planning for calibration samples and ends with deployment and maintenance considerations. Eigenvector Research President Barry M. Wise covers the steps required to produce a quality calibration model, including data screening, visualization, and model creation. Also covered will be common mistakes and how not to make them.

These topics are designed to cover the best practices of chemometrics technology and will prepare participants for tackling a vast array of problems. This course is useful for any scientist concerned with optimizing their analytical methods to get the most out of either laboratory or process operations.

To Register:
This course will be presented prior to the IFPAC Annual Meeting. Register at www.IFPACglobal.org/attendee-registration.

ISA 2020 – Rethinking Calibration for Process Spectrometers II

The Long Beach Convention Center
Long Beach, CA
1:30pm, April 27th


Brian Rohrback
Infometrix, Inc.
Will Warkentin
Chevron Richmond Refinery


Best Practices, Calibration, Cloud Computing, Database, Gasoline Blending, Optical Spectroscopy, PLS, Process Control

Optical spectroscopy is a favored technology to measure chemistry and is ubiquitous in the hydrocarbon processing industry. In a previous paper, we focused on a generic, machine-learning approach that addressed the primary bottlenecks of mustering data, automating analyzer calibration, and tracking data and model performance over time. The gain in efficiency has been considerable, and the fact that the approach does not disturb any of the legacy (i.e., no changes or alterations to any analyzer or software in place) made deployment simple.

We also standardized a procedure for doing calibrations that, adheres to best practices, archives all data and models, provides ease of access, and delivers the models in any format. What remains is to assess the speed of processing and the quality of the models. To that end a series of calibration experts were tasked with model optimization, restricting the work to selecting the proper samples to include in the computation and setting the number of factors in PLS.  The amount of time and the quality of the models were then compared.  The automated system performed the work in minutes rather than hours and the quality of the predictions at least matched the best experts and performed significantly better than the average expert.  The conclusion is that there is a large amount of recoverable giveaway that can be avoided through automation of this process and the consistency it brings to the PLS model construction.

There is a lot of mundane work tied to the assembly of spectra and laboratory reference values to enable quality calibration work.  There is also insufficient guidance when it comes to the model construction task.  How much time should be spent on this task?  How to best assess whether a spectrum-reference pair is an outlier or not? How many cycles of regression-sample elimination make sense? Where do we switch over from improving the model by adding PLS factors to overfitting and incorporating destabilizing noise?

For more information or the full paper, contact us.

Rethinking Calibration for Process Spectrometers

Click on image to view the full paper.



Rethinking Calibration for Process Spectrometers

Will Warkentin, Chevron
Brian Rohrback, Infometrix

Optical spectroscopy is a great source of process chemistry knowledge. It has the advantage of speed, sensitivity, and simple safety requirements. As one of very few analyzer technologies that can measure chemistry, it has become a workhorse in the hydrocarbon processing industry. What if we could put a spectroscopy system in place and have it handle the application and communicate results as soon as it is turned on? Then, if predictions do not match legacy standards, the system dials itself in or calls for help. And, we are not constrained on either the hardware or the software front. In this paper, we address the primary bottleneck of mustering data, automating analyzer calibration, and tracking data and model performance over time.

Best Practices, Calibration, Cloud Computing, Database, Optical Spectroscopy, PLS, Process Control