INFORM April 2026

inform April 2026 Volume 37 (4)

AI-ASSISTED PROCESS AUTOMATION

EMERGENCY ACTION PLANS

CARBON NEUTRAL PROCESSING

COMPARING EXTRACTION SOLVENTS

Copyright INFORM 3

AOCS MAILING ADDRESS PO Box 7230 Champaign, IL 61826 USA +1 217-359-2344 | publications@aocs.org

AOCS MISSION STATEMENT AOCS advances the science and technology of oils, fats, proteins, surfactants, and related materials, enriching the lives of people everywhere. inform International News on Fats, Oils, and Related Materials ISSN: 1528-9303 IFRMEC 34 (4) Copyright © 2013 AOCS Press

ADVERTISING INSTRUCTIONS AND DEADLINES Closing dates are published on the AOCS website (aocs.org). Insertion orders received after closing will be subject to acceptance at advertisers’ risk. No can cellations accepted after closing date. Ad materials must be prepared per published print ad specifica tions (posted on aocs.org) and received by the pub lished material closing dates. Materials received after deadline or materials requiring changes will be pub lished at advertisers’ risk. Send insertion orders and materials to the email address below. NOTE: AOCS reserves the right to reject advertising copy which in its opinion is unethical, misleading, unfair, or otherwise inappropriate or incompatible with the character of Inform. Advertisers and advertising agencies assume liability for all content (including text, representation, and illustrations) of advertisements printed and also assume responsibility for any claims arising therefrom made against the publisher. AOCS ADVERTISING: Travis Skodack, Director Membership +1 217-693-4897 | travis.skodack@aocs.org Formerly published as Chemists’ Section, Cotton Oil Press, 1917–1924; Journal of the Oil and Fat Industries, 1924–1931; Oil & Soap, 1932–1947; news portion of JAOCS, 1948–1989. The American Oil Chemists’ Society assumes no responsibility for statements or opinions of contributors. Inform (ISSN: 1528-9303) is published 10 times per year in January, February, March, April, May, June, July/ August, September, October, November/December by AOCS Press, 2710 South Boulder Drive, Urbana, IL 61802-6996 USA. Phone: +1 217-359-2344. Periodicals Postage paid at Urbana, IL, and additional mailing offices. POSTMASTER: Send address changes to Inform, P.O. Box 17190, Urbana, IL 61803-7190 USA. Subscriptions to Inform for members of the American Oil Chemists’ Society are included in the annual dues. An individual subscription to Inform is $195. Outside the U.S., add $35 for surface mail, or add $125 for air mail. Institutional subscriptions to the Journal of the American Oil Chemists’ Society and Inform combined are now being handled by Wiley. Price list information is available at http://olabout. wiley.com/WileyCDA/Section/id-406108.html. Claims for copies lost in the mail must be received within 30 days (90 days outside the U.S.) of the date of issue. Notice of change of address must be received two weeks before the date of issue. For subscription inquiries, please contact Julie May at AOCS, julie. may@aocs.org. AOCS membership information and applications can be obtained from: AOCS, P.O. Box 17190, Urbana, IL 61803-7190 USA or membership@ aocs.org. NOTICE TO COPIERS: Authorization to photocopy items for internal or per sonal use, or the internal or personal use of specific clients, is granted by the American Oil Chemists’ Society for libraries and other users registered with the Copyright Clearance Center (www.copyright. com) Transactional Reporting Service, provided that the base fee of $15.00 and a page charge of $0.50 per copy are paid directly to CCC, 21 Congress St., Salem, MA 01970 USA.

EDITORIAL ADVISORY COMMITTEE

Julian Barnes Etienne Guillocheau Jerry King

Gary List Thaís Lomônaco Raj Shah

Ryan Stoklosa Ignacio Vieitez Bryan Yeh

AOCS OFFICERS PRESIDENT: Gerard Baillely, Procter & Gamble, Mason, Ohio, USA VICE PRESIDENT: Fabiola Dionisi, Societe’ Des Produits Nestlé - Nestlé Research, Lausanne, Vaud, Switzerland TREASURER: Greg Hatfield, Bunge Limited, Oakville, Ontario, Canada SECRETARY: Roger Nahas, Kalsec, Kalamazoo, Michigan, USA PAST PRESIDENT: Tony O’Lenick, SurfaTech, Lawrenceville, Georgia, USA

AOCS STAFF EDITOR-IN-CHIEF: Rebecca Guenard MEMBERSHIP DIRECTOR: Travis Skodack PAGE LAYOUT: Moon Design

The views expressed in contributed and reprinted articles are those of the expert authors and are not official positions of AOCS. Some articles may be written using an AI companion.

ADVERTISING INDEX * CPM Crown................................................................................................................ C4 * French Oil Mill Machinery Co. .....................................................................31 Körting Hannover GmbH...................................................................................11 * Myande..............................................................................................................................17 * Desmet NV...................................................................................................................C2 * Oil-Dri Corp of America..................................................................................C3 * Pope Scientific, Inc. ..................................................................................................9 * Visionary Fiber Technologies.............................................................21, 36 * Corporate member of AOCS who supports the Society through corporate membership dues.

Achieve It. Clean-label processing at scale.

Safe. Scalable. Sustainable. Alcohol-based. Monarc Clean Oilseed Processing TM is a proven, patented alcohol-based process that enables companies to replace current solvents in their extraction supply chains, deliver high-value clean label ingredients and products (including organic), create an overall safer working environment and meet sustainability goals – all at the scale and economics of current solvent technology. Future proof your operations while seizing the opportunity to meet growing public demand for clean-label. Products made with Monarc show superior characteristics. CPM|Crown enables you to expand your clean-label options without abandoning legacy oilseed processing. Our first plant installation is already in process..

Adopt the cleanest oilseed processing technology for humans, animals and biofuels.

Feeding, Fueling and Building a Better World.

crownsales@cpm.net | +1.651.639.8900 | OneCPM.com

CRACKING MILLS

FLAKING MILLS

SCREW PRESSES

YOUR SOURCE FOR OILSEED PROCESSING SOLUTIONS ACHIEVER SCREW PRESSES, ROLLER MILLS, PILOT SCALE LAB TESTING, AND MORE.

We make machines to make people’s lives better. French Oil Mill Machinery Company | Piqua, Ohio

WWW.FRENCHOIL.COM

In 1900 The French Oil Mill Machinery Company began as a new idea - an idea that improved manufacturing processes and challenged established industry methods. Always focused on innovation and engineering creativity, our fourth generation family-owned company continues this tradition for the benefit of our customers.

4 INFORM APRIL 2026 , VOL. 37, NO. 4

THIS MONTH IN INFORM

6 PROCESSING DIVISION SPOTLIGHTS The 2026 AOCS Alton E. Bailey Awardee, Jerry King, and Student Excellence Awardee, Yue Wang

8 FROM THE FRYER

TO THE WIRE: TECHNICAL CONNECTIONS AT THE 2026 AOCS ANNUAL MEETING Each year, AOCS Annual Meeting brings together scientists, technical experts, and industry leaders to exchange ideas, shape analytical standards, and strengthen the global fats and oils community.

12 On the Cover THE RISE OF AI‑ASSISTED PROCESS AUTOMATION AI tools are being applied across every stage of edible oil production. Read about the latest real-time automation and sensor-integrated AI that optimize process parameters, provide virtual testing, or characterize feedstocks. AI is speeding up innovation, accelerating time-to-market, and saving energy resources, creating efficiency, sustainability, and profitability for the modern processing plant.

Table of Contents INFORM 5

26 CARBON NEUTRAL PROCESSING THAT ENHANCES THE NUTRITIONAL VALUE OF MEAL Global regulation changes concerning the treatment of animal feed have sparked new oilseed meal processing challenges. Some methods create an unwelcome reaction between the animal feed and the added reagent, while others involve excessive heat that causes protein to be less digestible, or an unevenly heated product. Read about how to protect oilseed meal and recover energy using moving bed heat exchangers while improving carbon intensity and sustainability in oilseeds operations.

22 WHEN DISASTER STRIKES: ENSURING SAFETY IN OILSEED PROCESSING When the unthinkable happens, personnel safety is the priority. After that a long list of procedures follows, like an incident investigation, before you can get the plant up and running again. Having a well-established and practiced Emergency Action Plan is critical to ensure a safe and rapid recovery. This article addresses the safety challenges associated with oilseed refineries and the proper steps to take in the event of an emergency.

32 ECO-EXTRACTION A VIABLE INDUSTRIAL OPTION This story describes a comparison of soybean oil extraction using 2-methyloxolane, a biobased solvent, and hexane in a semi-industrial continuous multistage countercurrent extractor. In this trial, 2-MeOx yielded an oil richer in phenolic compounds than the hexane extracted oil resulting in higher oxidative stability. The authors describe extraction conditions along with other details about the resulting oils, and assess the scale-up potential of their experiment.

38 REGULATORY REVIEW Rapid risk assessment on acute reference dose of cereulide in infants 39 EXTRACTS & DISTILLATES Processing articles picked by researchers

25 AOCS EVENTS WATCH

6 INFORM APRIL 2026 , VOL. 37, NO. 4

PROCESSING DIVISION SPOTLIGHTS

THE 2026 AOCS ALTON E. BAILEY AWARDEE The Processing Division is proud to announce that Jerry King, a long-time member of the Division, is this year’s recipient of the Alton E. Bailey Award, sponsored by ADM. The Alton E. Bailey Award recognizes outstanding research contributions and exceptional service in the field of fats, oils, lipids and related disciplines. INFORM: WHAT WAS YOUR MOTIVATION TO JOIN AOCS? King: Membership and participation in AOCS were invaluable to my research activities in oilseeds processing, analysis and utilization - during my tenure with USDA (1986-2002). INFORM: HOW HAS AOCS CONTRIBUTED TO YOUR CAREER DEVELOPMENT? King: Recognition of my efforts has been greatly aided via involvement in AOCS, through publication in JAOCS, fairly consistent attendance and participation at annual and specialty meetings sponsored by AOCS and taking up leadership roles in AOCS and related societies. Unexpectantly, this has had a carrying over into disciplines outside of AOCS which involve

lipid technology, for example, cleaning technology and cannabis/hemp R&D. INFORM: HOW HAS AOCS HELPED YOU DEVELOP COMMUNICATION, LEADERSHIP, OR NETWORKING SKILLS? King: Organizing and chairing sessions were seminal in developing my communication and leadership skills. Of particular value, was my interface with industrial companies via the Expo during AOCS annual meetings. INFORM: HOW DO YOU SEE YOUR FIELD EVOLVING IN THE COMING YEARS King: Since my career has been multidisciplinary over the years, “my field” is difficult to define. In the processing and extraction field, integrating green principles can be challenging. I started in the wide application of chromatography which led me into super fluid extraction, solution thermodynamics (inverse gas chromatography), surface chemistry, and more. I have come to realize that as I have persisted in my career, you have only so much control over the evolution of “your field”. Through flexibility and acceptance of new challenges, you will not only grow your own career, but “your field” as well.

JERRY KING Retired processing industry professional, R&D and education consultant

Joined AOCS: 1982

AOCS UPDATES | INFORM | 7

INFORM: WHAT ADVICE WOULD YOU OFFER TO INDIVIDUALS WHO WANT TO PURSUE A CAREER IN PROCESSING? King: Expand your knowledge base beyond your current comfort zone and treasure

the interconnections. Try and become a polymath as opposed to over specialization in your field. However, an oil-fat-lipid base can serve you well when unexpected opportunities come up to use this knowledge base. Try and

leave a legacy of educational outreach and become a sponsor/supporter in the societies you belong to. Giving back is key to achieving some degree of success along with nurturing the careers of others.

STUDENT EXCELLENCE AWARDEE Yue Wang’s research focuses on upcycling food processing waste using supercritical carbon dioxide for extraction and enzymatic transesterification. Her work aims to advance the development of sustainable, green biorefineries using bioactive compounds from agricultural byproducts. INFORM: WHAT SPARKED YOUR INTEREST IN FOOD PROCESSING RESEARCH? Wang: My interest in food processing research grew when I realized the huge potential in food waste valorization research. During my studies, I became fascinated by how food processing can transform byproducts into valuable, functional products. Meanwhile, the innovation and development of sustainable processing technologies bring new approaches to create new opportunities for the industry. Moreover, food

processing is the combination of chemistry and engineering which allows me to apply scientific principles to create practical solutions that can make a real impact on the food industry. INFORM: WHAT DO YOU FIND MOST EXCITING ABOUT YOUR CURRENT RESEARCH? Wang: My research focuses on upcycling and adding value to food processing waste. I am especially excited about the potential to design efficient and sustainable processing steps. It feels rewarding to work on solutions that reduce waste while producing functional products. INFORM: IS THERE ONE PROJECT THAT YOU BELIEVE COULD HAVE MEANINGFUL IMPACT? Wang: One project I am particularly proud of is the development of an integrated continuous extraction– reaction system using supercritical carbon dioxide to valorize food processing byproducts. The goal is to combine multiple processing

YUE WANG Doctoral student in Food Science and Technology at the University of Nebraska–Lincoln, under the advisement of Ozan Ciftci.

Joined AOCS: 2025

8 INFORM APRIL 2026 , VOL. 37, NO. 4

INFORM: WHERE DO YOU SEE YOUR RESEARCH AND THE FOOD PROCESSING FIELD AS A WHOLE HEADING IN THE NEXT FIVE YEARS? Wang: In the next five years, I envision myself moving further toward scalable and sustainable processing innovation in the industry. I think the food industry is moving toward a similar direction of promoting circular processing, reducing waste and minimizing environmental impact. AI is reshaping our life and I am excited about the opportunity to apply these tools to improve efficiency in food processing. INFORM: HOW HAS THE AOCS COMMUNITY SUPPORTED YOUR GROWTH AS A RESEARCHER? Wang: The AOCS community has been incredibly supportive of my growth as a researcher. AOCS, as the leading international conference in the field of oils, fats, and lipids, offers me a platform to present cutting-edge research, discuss emerging technologies, and explore future career opportunities. Attending this conference

steps into a single, efficient platform that reduces solvent use, improves yield, and lowers environmental impact. I believe this work has meaningful potential because it demonstrates how sustainable technologies can be scaled toward industrial applications, turning waste streams into valuable bioactive compounds. It is exciting to see how process intensification can reshape the way we think about resource efficiency in food processing. INFORM: WHAT CHALLENGES HAVE YOU OVERCOME IN YOUR RESEARCH? Wang: One of the challenges I have faced in my research is finding the right balance between extraction and reaction in the process. Optimizing both steps simultaneously requires carefully adjusting conditions. I have learned the trade-off between different conditions and refining the process to achieve the best overall performance.

will enhance my knowledge, inspire future research, and help me stay up to date on the latest scientific advancements. It will also provide invaluable opportunities to network with peers, mentors, and industry leaders fostering collaborations, internships, and career growth for a lifetime. INFORM: WHAT DOES RECEIVING THIS AWARD MEAN TO YOU? Wang: Receiving the PRO Student Excellence Award is both an honor and a source of motivation for me. Personally, it is encouraging to see my work in sustainable food processing be meaningful and recognized in the field. Professionally, it provides visibility within the AOCS community, strengthens my network, and opens doors to potential collaborations and career opportunities. INFORM: WHAT ADVICE WOULD YOU GIVE TO OTHER STUDENTS? Wang: My advice is to actively participate in and contribute to extracurricular and professional activities to build leadership and involvement. Volunteer for divisions, present your research at conferences, and participate in research competitions.

Superior Oil Products Start with Pope Distillation! CELEBRATING 60 YEARS LAB, PILOT PLANT AND PRODUCTION SCALE CAPABILITIES Pope Scientific’s state-of-the-art wiped-film distillation equipment is expertly designed for industries specializing in oleochemicals and fats. Our innovative approaches, including continuous hybrid fractional distillation, are engineered to minimize thermal impact during processing, preserving product quality and integrity. By leveraging Pope's advanced equipment, producers can create higher-value, dierentiated products that meet evolving market demands. Additionally, Pope oers in-house feasibility testing and Toll Processing Services to support the development and production of new, high-value oerings.

WIPED FILM DISTILLATION SYSTEMS • Molecular (short-path) still & evaporator (WFE) configurations • Providing gentlest thermal separations of materials high in BP, MW, heat sensitivity & viscosity HYBRID DISTILLATION SYSTEMS • Customized Hybrid Fractionating Column systems combine the multi-plate e ciency of fractional columns with the gentle reboiling e€ect of Wiped-Film Evaporators. FRACTIONAL DISTILLATION SYSTEMS • Batch or continuous, vacuum or pressure modes • Designs for testing, piloting or production; also combinable with WFEs as Hybrid systems TOLL DISTILLATION PROCESSING SERVICES • Contract processing, process development and feasibility testing • cGMP & Kosher Certified

LEARN MORE, SCAN BELOW.

Enhance your product lines – Consult Pope! +1-262-268-9300 | www.popeinc.com

10 INFORM APRIL 2026 , VOL. 37, NO. 4

FROM THE FRYER TO THE WIRE: TECHNICAL CONNECTIONS AT THE 2026 AOCS ANNUAL MEETING

As winter gives way to spring across the US Midwest, the season of renewal also signals one of the most anticipated gatherings of the year—the AOCS Annual Meeting, taking place May 3–6 in New Orleans, Louisiana. Each year, this event brings together scientists, technical experts, and industry leaders to exchange ideas, shape analytical standards, and strengthen the global fats and oils community. A key highlight of the meeting is the series of technical panels, roundtables, and committee discussions designed to foster collaboration and advance the science behind our work. These sessions provide a unique opportunity for members at all career stages to engage directly with subject‑matter experts, contribute to evolving discussions, and stay informed on emerging priorities. Importantly, the Sunday technical sessions are open to all attendees, making early arrival a valuable investment for anyone looking to maximize their meeting experience. ADVANCING TECHNICAL DIALOGUE The Avocado Expert Panel convenes on Sunday, May 3 at 9:00 AM, bringing together specialists to explore developments in avocado oil analysis and production. Led by Selina Wang and Jill Moser, this session emphasizes collaboration and knowledge sharing across the industry. At 11:00 AM, the Laboratory Proficiency Committee, chaired by Susan Seegers, will address the technical direction of the AOCS Laboratory Proficiency Program—an essential initiative that supports analytical accuracy and laboratory performance worldwide.

Later in the day, the Uniform Method Roundtable, at 1:00 PM, offers an open forum for discussing current analytical challenges and method-related topics. This interactive session encourages dialogue among participants and reflects the Society’s commitment to transparent and inclusive technical development. The afternoon concludes with the Uniform Methods Committee meeting at 3:00 PM, led by Steve Hansen. This group of dedicated volunteers plays a vital role in reviewing and approving methods that help maintain consistency and scientific rigor across the field.

AOCS Updates INFORM 11

The best ice condensation of all time

For those seeking deeper engagement, agendas and notes from these sessions are available through AOCS. The Society is committed to knowledge sharing and community participation. SPOTLIGHT ON EMERGING CONTAMINANT TOPICS Another important gathering during the Annual Meeting is the Process Contaminants Expert Panel, scheduled for Wednesday, May 6 at 7:30 AM. This session explores evolving issues such as hexane analysis, MOSH/MOAH, phthalates, and other contaminants impacting the industry. In 2025, contributions from leading experts—Jan Kuhlmann, Mark Collison, Carlos Martin Alberca, Jiang Yuan Rong, and Giorgia Purcaro—highlighted the global scope and collaborative nature of these discussions. LOOKING AHEAD: LABORATORY PROFICIENCY PROGRAM The upcoming launch of the 2026–2027 Laboratory Proficiency Program marks another milestone for AOCS. Designed to help laboratories strengthen analytical performance and ensure reliable results, the program continues to expand its technical offerings. Current participants are recognized for their ongoing commitment to quality, and new organizations are encouraged to explore how proficiency testing can enhance their operations. As the Society prepares to gather in New Orleans, the message is clear: progress in our field depends on connection, collaboration, and continuous learning. Whether through committee work, expert panels, or informal conversations, the Annual Meeting remains a cornerstone of the AOCS technical community—a place where ideas move from the fryer to the wire and initiate real-world impact.

THE NEW ICE GENERATION

• Enhanced flow design • A system independent of refrigerants • A turnkey system from one source • A consistent vacuum 24 / 7

+1 832 258 8098 | sales@koerting.com | koerting.de

THE RISE OF AI‑ASSISTED PROCESS AUTOMATION Laura Cassiday

ARTIFICIAL INTELLIGENCE INFORM 13

From olive mills to biomass reactors, AI is redefining process optimization and automation in the fats and oils sector. Across the fats and oils industry, researchers are facing the same challenges: Processes are messy, nonlinear, and expensive to optimize. Traditional trial-and-error experiments can take months or years, demand expensive pilot facilities, and generate large, difficult-to-interpret datasets. Variables interact in complex ways that defy conventional data analysis tools. At the same time, manufacturers need equipment that can sense changing conditions and instantly adapt to maintain quality and efficiency. Against this backdrop, many industry leaders are partnering with a new type of process engineer: artificial intelligence (AI). In recent years, AI-driven tools, from machine-learning models to embedded optimization chips, have begun to automate decisions once left to expert operators, accelerating discovery and reshaping how fats and oils are processed, from edible oils to biofuels.

14 INFORM APRIL 2026 , VOL. 37, NO. 4

AI TOOLS FOR PROCESS CONTROL AI tools for process optimization and automation span a wide range of methods and capabilities. Among them, machine learning (ML) approaches are especially effective at analyzing large experimental datasets, identifying patterns, and making predictions or classifications. Artificial neural networks (ANN), one of the earliest types of ML, remain a workhorse for process optimization. Inspired by the structure of the human brain, ANN consist of interconnected layers of computational units, or artificial neurons, that transmit signals to one another. Each neuron processes inputs and sends outputs to other connected neurons, while weighted connections determine how strongly one neuron influences another. During training of an ANN, connection weights are iteratively adjusted to

Input Layer

Intermediate Layers

Output Layer

Scheme of a multilayer perceptron, the most widely used type of artificial neural network in bioinformatics prediction models. Source: Gonzalez-Fernandez, I., et al., Crit. Rev. Food Sci. Nutr. 59 (2018)

minimize error between predicted and actual outcomes, which enables the AI to learn complex, nonlinear relationships. Some optimization algorithms, including particle swarm optimization (PSO) and genetic

algorithms, are also inspired by biology. For example, PSO mimics the collective behavior of animals—flocks of birds, schools of fish, or swarms of insects—as they search for food. PSO searches large, complex spaces of variables to identify optimal outcomes,

Examples of AI tools for process optimization and automation in the fats and oils industry. Sources: in table.

Sample References

Category

Examples

General Mechanism

Sample Applications

Machine Learning ANN, Random Forest, XGBoost, CatBoost, MTDL

Learn nonlinear relationships from historical or experimental data to make predictions or classifications Optimize process parameters directly or in combination with ML models Simulate factory behavior or use predictive models to adjust variables in real time Combine sensor data with ML to interpret real-time signals for classification and defect detection

Predict biofuel yield; detect adulterants; predict catalyst performance; conduct life cycle assessments Optimize reaction conditions; detect adulterants Virtual testing; adaptive reactor control; predictive maintenance

1 , 2 , 3 , 4

Optimization Algorithms

PSO, GA

1 , 5

Tools for Process Simulation and Real Time Control

Digital twins, ML-augmented MPC, RL

6

Sensor-Integrated AI IoT sensors + ML; CNN-based vision systems

Fruit grading; impurity detection; feedstock characterization

2

ARTIFICIAL INTELLIGENCE INFORM 15

such as maximum yield or minimum cost. In PSO, each “particle” moves through the search space, updating its position based on its own best result and the best result found by the swarm. Over time, the swarm converges toward a high‑quality solution. Used alone or with machine‑learning models, PSO excels at solving nonlinear, multidimensional optimization problems. Other AI tools, such as digital twins and reinforcement learning (RL), can simulate factory behavior or use predictive models to adjust process variables without interrupting production. A digital twin provides a virtual replica of a facility, continuously synchronized with sensor data to update parameters and improve predictions. Within this environment, an RL agent can learn how to respond to changing conditions, such as shifts in feedstock, and test process adjustments before they are implemented in the actual plant. Although still in early stages, these AI tools could enable real‑time, adaptive process control. EDIBLE OILS AI tools are now being applied across every stage of edible oil production, from plant care and harvesting to processing, packaging, and quality assurance. “A few years ago, AI tools were used in the olive oil sector primarily for offline tasks, such as process optimization modeling,

AI tools have been used to optimize every stage of olive oil production, including cultivation, extraction, storage, quality assurance, and authentication. Source: Shutterstock

quality characterization, and authenticity verification,” says Juan Carlos Mejuto, professor of physical chemistry at the University of Vigo, in Spain. “Since then, the field has evolved from retrospective data analysis toward real time, integrated process control.” Jesus Simal-Gándara, also a professor at the University of Vigo, notes that the European Union’s OLEUM project and initiatives in Spain and Italy are already deploying AI-driven smart mills. As early as 2008, researchers combined an ANN with online near-infrared (NIR) spectroscopy to accurately predict moisture and fat content in olive pomace during cold extraction, allowing real‑time adjustment of centrifugation parameters to maximize yield. Since then, AI tools have expanded to

enable online monitoring of key quality indicators—such as acidity, peroxide value, moisture, and polyphenols— throughout the extraction process. AI tools are also reshaping quality assurance. ANN paired with UV/Vis spectrophotometry can estimate olive oil degradation during transportation and storage, enabling predictions of remaining shelf life. Other ANN models link chemical attributes (such as free acidity, peroxide value, specific absorbance, and phenol content) with sensory properties, demonstrating that AI can rapidly and objectively grade olive oil quality. Adulteration of extra virgin olive oil with cheaper seed oils remains a persistent challenge, driving interest in

16 INFORM APRIL 2026 , VOL. 37, NO. 4

BIODIESEL PRODUCTION Biodiesel is a renewable fuel made from lipids such as vegetable oils, waste cooking oils, and animal fats, offering a lower carbon footprint than petroleum diesel. However, its production depends on complex variables—feedstock composition, catalyst performance, and reaction conditions—that affect yield, quality, and cost. As the industry pushes toward higher efficiency, greater sustainability, and the use of waste feedstocks, AI has become an essential tool. Biodiesel is produced by reacting triglycerides with an alcohol (usually methanol

AI‑enabled detection. In one study, researchers combined multitask deep learning (MTDL) with Raman spectroscopy to qualitatively and quantitatively assess blends of extra virgin olive oil with soybean, peanut, sunflower, corn, and palm oils with 99.3 percent accuracy. Geographic authentication is another active area of research. The European Union’s Protected Designation of Origin (PDO) certification recognizes olive oils whose characteristics arise from unique local cultivars, environments, and practices. Because these differences stem from minor chemical components, researchers are pairing advanced chemometrics with AI models to classify oils by origin. A recent study integrating ion mobility mass spectrometry with a Random Forest ML model achieved 100 percent accuracy in distinguishing oils from four PDO regions (Spain, Portugal, Morocco, and Italy), compared with 68 percent accuracy for a tasting panel. Given the high value of extra virgin olive oil, the industry has pioneered many AI frameworks that are now being extended to other premium oils, such as avocado, argan, and walnut, as well as to large-scale seed oil refining. In the palm oil industry, ML applications include yield prediction, disease detection, price forecasting, and sustainability improvement.

or ethanol) and a catalyst (typically sodium or potassium hydroxide) to form fatty acid methyl esters (biodiesel) and glycerol, a process known as transesterification. Refined vegetable oils such as palm, soybean, and canola can be directly transesterified, but crude or waste oils with more than 2.5 percent free fatty acids require pretreatment to avoid saponification. This pretreatment, commonly with sulfuric acid and methanol, converts free fatty acids to methyl esters before transesterification. Because biodiesel has been criticized for relying on food-grade feedstocks like soybeans and corn, the industry has increasingly turned to waste oils, such as used cooking oil, animal fats,

Biodiesel production from waste vegetable oils involves two chemical reactions: esterification of free fatty acids with sulfuric acid and methanol, followed by transesterification of triglycerides with methanol and a catalyst, usually NaOH or KOH. Source: Popescu, F., and Ionel, I., Alternative Fuel , 2010

Waste vegetable oil >2.5% FFA

Esterification

Sulfuric acid + Methanol

Methanol + NaOH

Transesterification

Crude Biodiesel

Glycerol

Washing

Methanol Recovery

Finished Biodiesel

Integrated Engineering Solutions From ConceptTo Reality

Patentsand copyrights 600 + 1,200 + Com pleted plants

Exportdestinations 80 + M odern inteligent m anufacturing base 130,000 ㎡

O ilseed Preparation Capacityof100-10,000t/d

SolventExtraction Capacityof100-10,000t/d

O ilRefinery Capacity of50-3,000t/d

O leochem ical,Biodiesel, HVO Pre-treatm ent

Plant-based Protein Capacity of100-1,200 t/d

SiloStorageand Conveying

Tel:+86-514-8784 911 www.m yandegroup.com E-m ail:info@ m yande.com m yande@ gm ail.com

18 INFORM APRIL 2026 , VOL. 37, NO. 4

and brown grease. However, these “dirty oils” are far more challenging to process due to their variable composition, high free fatty acid levels, and need for extensive pretreatment. A recent study combined ML with PSO to optimize biodiesel production from fats, oils, and grease (FOG). FOG, collected from restaurants and food processing facilities, varies widely in composition and contains high levels of free fatty acids (nearly half), making conversion difficult. To build predictive models, researchers used a dataset of more than 20,000 experiments spanning six esterification and transesterification variables. Among eight algorithms tested, XGBoost delivered the most accurate predictions for the dataset. The team then applied PSO to further refine the model. Working within defined parameter ranges, PSO generated random input values that were fed into the XGBoost model for evaluation. This process was repeated, and after about 350 iterations, the system converged on the optimal conditions, achieving 99.4 percent conversion of free fatty acids and triglycerides to fatty acid methyl esters. Another study used ML to maximize biodiesel production from waste cooking oil using an eggshell-derived calcium oxide (CaO) catalyst. This reusable catalyst offers a cheaper, more sustainable alternative to NaOH and KOH, which require purification and generate chemical

XGBoost Predictions (R = 0.999)

100.0

97.5

95.0

92.5

90.0

87.5

Predicted Values

85.0

82.5

82.5 85.0 87.5 90.0 92.5 95.0 97.5 100.0

Actual Values

An XGBoost machine learning model showed high accuracy (R 2 =0.999) for predicting biodiesel yields under different reaction conditions. Source: Azhar, B., et al. , Energy Convers. Manag. : X, 2025.

wastewater. To prepare the catalyst, researchers washed and milled eggshells collected from restaurants, then heated them to convert calcium carbonate into CaO. The resulting eggshell-derived powder could be used without purification. The team collected 16 datasets to train and test four AI models. Waste cooking oil was first esterified with methanol and sulfuric acid to decrease free fatty acids. Then, the researchers examined how varying CaO catalyst concentration, reaction temperature, and methanol to-oil ratio affected yield during transesterification. They used 80 percent of the data for training the models and 20 percent for testing. CatBoost emerged as the top performer, identifying optimal conditions

of 3 percent catalyst, 80 °C, and a 6:1 methanol‑to‑oil ratio to produce a biodiesel yield of 95 percent. “Without AI, optimizing this green catalyst would require countless trial-and error experiments,” says Krishnamoorthy Ramalingam, postdoctoral researcher at the Universiti Sains Malysia in George Town. “Machine learning allowed us to pinpoint the most efficient reaction conditions quickly and accurately, saving time and resources.” He adds that AI models like CatBoost could be embedded in industrial control systems for real-time monitoring, fault detection, and adaptive tuning of reaction conditions. “Exploring this integration is a natural next step in our research,” he says.

ARTIFICIAL INTELLIGENCE INFORM 19

OH

H-CH 3

OH

OH

H· ·CH 3

Catechol

Cresol

dehydroxylation

hydroxylation

OH

OH

demethylation

O

demethoxylation

dehydroxylation

methylation

Guaiacol

Phenol

Benzene

Toluene

dehydroxylation

methylation

methylation

demethylation

O

Polycondensation

Anisole

Xylene

Naphthalene

Proposed reaction pathway of guaiacol deoxygenation under a methane environment to form benzene, toluene, and xylene (BTX). Source: Kim, G., et al. , Cat. Today , 2025.

BIOMASS WASTE VALORIZATION AI tools are also accelerating efforts to convert biomass waste—crop residues, wood waste, and food byproducts—into higher-value products such as biofuels and chemicals. In particular, the valorization of biomass waste into bio-oil has the potential to reduce the world’s dependency on fossil fuels, converting agricultural wastes into liquid fuels identical to gasoline, diesel, and jet fuel. Unlike biodiesel, which consists of oxygen-rich fatty acid methyl esters, renewable diesel from biomass is made of fully saturated hydrocarbons. “Renewable

diesel is identical in molecular structure to petroleum based diesel,” says Hua Song, professor of chemical and petroleum engineering at the University of Calgary. In contrast, biodiesel is chemically distinct and must typically be blended at low levels with petroleum fuel to ensure engine performance. The first step in producing renewable fuel from biomass waste is fast pyrolysis, where biomass is rapidly heated without oxygen to form liquid bio‑oil, plus small amounts of syngas and biochar. This oxygen‑rich bio‑oil must then be upgraded through stabilization, hydrodeoxygenation, and catalytic cracking to create a hydrocarbon mixture. The

upgraded product can then be distilled into gasoline‑, diesel‑, or jet‑fuel‑range fractions. One of the most expensive and energy-intensive steps in biomass upgrading is hydrodeoxygenation, or the removal of oxygen from bio-oil, usually with large amounts of hydrogen. To reduce costs, Song and others have explored natural gas, or methane, as an alternative. Unlike hydrogen, methane is inexpensive, abundant, and naturally available. However, methane must be activated to form hydrogen atoms and methyl radicals, which requires a catalyst, typically noble metals.

20 INFORM APRIL 2026 , VOL. 37, NO. 4

Song wanted to develop catalysts based on zeolites modified with common transition metals, which are less expensive and can operate under milder conditions than noble metal catalysts. So, he used an ML model to screen catalysts for the deoxygenation of guaiacol, a lignin‑derived compound abundant in bio‑oil. The reaction converts guaiacol into the high-value products benzene, toluene, and xylene (BTX). Song chose guaiacol as a model compound because its hydroxyl and methoxy groups make it particularly difficult to deoxygenate. The team selected ZSM-5 as the catalyst base because its pore structure and strong acidity enhance selectivity and activity. Song’s earlier work showed that doping ZSM-5 with metals can alter its catalytic performance. Using in-house and external datasets, the researchers identified 21 metals commonly used in deoxygenation, yielding over 1,330 possible three‑metal combinations. A Random Forest ML model screened and ranked these options. Although a ZSM-5 catalyst doped with zinc (Zn), gallium (Ga), and cerium (Ce) ranked fourth overall, it was chosen for validation because it contained no precious metals. The researchers synthesized the Zn‑Ga‑Ce/ZSM‑5 catalyst predicted by the model. Experiments showed that Zn and Ga improved methane activation at low temperatures, while Ce

reduced over‑coking, or the buildup of carbonaceous deposits. The optimized catalyst achieved guaiacol conversion with a liquid yield of 58 percent and BTX selectively as high as 90 percent— significant improvements over the unmodified ZSM-5 catalyst. In another study, Song’s team combined ML with process simulations to conduct techno-economic and life cycle assessments of biomass-to-biofuel conversion. An ANN model predicted how feedstock type, reaction temperature, and catalyst choice affected bio‑oil yield. These predictions were then fed into simulations to establish material and energy balances and to guide equipment design. The analysis showed that replacing hydrogen with methane in the deoxygenation step reduced the minimum selling price of renewable diesel by 22 percent and cut greenhouse gas emissions by 66 percent. The team notes that this AI-enabled workflow avoids the need for costly pilot plant optimization. Song is now collaborating with fuel companies, including Shell International, to test the methane-based process at a one‑ton‑per‑day demonstration scale. His team is also developing an AI chip that integrates optimization algorithms directly into facility hardware. “Companies like Shell deal with a wide variety of organic solid wastes,” Song says. “Our chip scans the feedstock and automatically adjusts pressure, temperature,

and flow rate to maximize production.” He emphasizes that the technology is still emerging and will benefit from further industry partnerships. Across the fats and oils sector, AI is moving from the lab bench to the factory floor. AI tools support yield prediction, catalyst and feedstock selection, equipment design, and the replacement of pilot‑scale testing. Digital twins and real‑time control systems are closing the loop between prediction and operation, enabling dynamic adjustments for efficiency, sustainability, and profitability. As sensor networks expand and models mature, the field is moving toward fully autonomous process control—systems that learn continuously, anticipate disruptions, and optimize entire value chains. Does this mean the process engineer’s days are numbered? Not necessarily. “AI can process millions of data points, but expert judgment is irreplaceable for interpreting results, adjusting models, and validating predictions,” says Mejuto. “In the olive oil industry, the goal is not to replace the master miller or tasting panel, but to give them real‑time, scalable decision‑making tools.” For hyperlinks to references visit inform.aocs.org Laura Cassiday is a freelance science writer and editor based in Hudson, Colorado. She can be reached at laura.cassiday.phd@gmail.com.

Visionary Fiber Technologies, Inc. (VFT) is a global leader in fiber reactor separation technology. Fiber reactor technology allows chemistry and separation of reaction products to proceed simultaneously without active mixing, substantially increasing throughput while reducing costs – both upfront and variable operating costs. MASSIVE MICROFLUIDIC ARRAYS

KEY ADVANTAGES:

• Minimized diffusional distances • Precisely controlled residence times

• Low shear conditions that suppress emulsion formation • Enzyme reutilization for operational cost reduction • Scalable, sustainable, next generation refining • Enhanced reactions with higher yield

Connect with Visionary Fiber Technologies to explore research, process evaluation, pilot testing, and commercial deployment opportunities.

KEVIN CATE DIRECTOR OF SALES kcate@visionaryfiber.com

VISIT VFT AT THE 2026 AOCS ANNUAL EXPO & MEETING — BOOTH 701

Visionary Fiber Technologies, Inc. • visionaryfiber.com • info@visionaryfiber.com

22 INFORM APRIL 2026 , VOL. 37, NO. 4

WHEN DISASTER STRIKES: ENSURING SAFETY IN OILSEED PROCESSING George Hale

Soybeans are a crucial part of the world’s food, agriculture, and industrial systems; however, the soybean’s journey from crop to oil is full of hazards ranging from chemical spills to fires and explosions caused by airborne dust. Because of this, oilseed processors rely on highly trained personnel, specialized safety equipment, and emergency action plans (EAP) designed to prevent safety incidents, protect people and infrastructure, and ensure a safe and rapid recovery should the unthinkable happen.

who can give more information about the plan and employee duties and outlining procedures for reporting an emergency, evacuating personnel or taking shelter, and accounting for employees after evacuation. “Basically, if there is an event, you need plant personnel to know where they should go and who should contact local authorities,” said Matthew Williamson, Director of Engineering at EDF Engineering. ACCORDING TO PLAN Developing and writing an EAP often falls on the facility’s safety department, with training departments playing a heavy role in many cases. OSHA provides guidance for making an EAP that can serve as a

The Occupational Safety and Health Administration (OSHA), which oversees workplace safety in the United States, requires certain employers to have an EAP. The purpose of an EAP is to prepare personnel for workplace emergencies to reduce the risk of severe injury or death, infrastructure damage, and prolonged loss of operations. Organizations with 10 or fewer employees can communicate their EAP with employees verbally, but larger employers must have a written plan that is kept on site and available for employees to review. OSHA regulations define what must be included in an EAP at a minimum. This includes identifying points of contact

PLANT SAFETY INFORM 23

starting point. A safety team can use the tool to create a simple EAP for an office or retail store, but an EAP for an oilseed processing facility will require more complex plans than OSHA’s tool can provide. For instance, oilseed processing facilities usually do not have a dedicated fire protection team, so they must rely on local fire departments. The EAP would provide fire department contact information and identify who is responsible for notifying them. Proper emergency planning would also mean giving local authorities key information on the facility ahead of time. “Part of your emergency action plan may involve having some kind of partnership with the local fire department,” said Williamson. “You need to let them know where all the main hazards are in the facility.” EAP should also include procedures that employees who are tasked with rescue or medical response should follow and what to do with key equipment before everyone evacuates. “When it comes to the extraction part of a plant, you cannot just walk away from it,” said Williamson. “You have to have some way to put it into a safe mode.” In addition, OSHA requires employers to have an alarm to notify employees of emergencies, with distinct signals for different incidents such as fires, spills, or weather hazards like tornadoes. Employers must also train

employees in EAP procedures and review the plan with employees when a plan is developed or changes, an employee starts a new job, or when a worker’s responsibilities under the EAP change. OSHA also recommends that organizations routinely practice evacuation drills. This helps reinforce the EAP in employees minds and can show any deficiencies in the plan or training before an emergency happens. OSHA recommends coordinating such drills with local authorities if possible and using the results of evacuation drills to refine EAP. AFTER THE UNTHINKABLE During an emergency the top priority is keeping personnel safe. Once everyone has been evacuated and accounted for, emergency services personnel can focus on putting out fires or containing leaks and spills. Companies will be eager to return to normal operations, but first they must figure out what caused the emergency. “Incident investigation is how you go back and find out what happened in a safe manner that preserves evidence,” said Williamson. However, before an investigation can begin, it must be safe to re-enter the building. For instance, a building might not be structurally sound after a dust explosion, making it too risky for investigators to collect evidence. In such a case the plant managers

should send in a drone with a camera to inspect the building. If everything looks sound, a structural engineering team can do a more thorough check before giving the green light for the investigation. After collecting evidence, investigators can begin their analysis to find out why the incident happened, and if it is safe to do so, the plant can resume operations. Much like a well-designed EAP keeps personnel safe, good incident investigation and recovery plans will help things return to normal quickly and give insights into why an emergency happened. With that information, plants can take steps to avoid future emergencies. FROM FARM TO MARKET The process of turning soybeans into refined soybean oil fit for food and industrial use involves a few different hazards. The actual process of refining oil extracted from soybeans is fairly safe, with most of the risks in this stage being related to food safety and product quality. However, the process of preparing soybeans and extracting their oil, known as upstream prep, is a different story. “Upstream prep can be very dangerous,” said Williamson. “And prep is often underappreciated, especially in older facilities.” After harvest, raw soybeans are first processed to remove their hulls. After that processors