Machine learning for industrial processes: Forecasting amine emissions from a carbon capture plant

Aug 5, 2026

Upload by Jiven

Amine-based carbon capture affects the environment through solvent emissions released to the atmosphere. To quantify how emissions change under intermittent power-plant operation, stress tests were conducted on a pilot capture plant using a two-amine mixture (2-amino-2-methyl-1-propanol and piperazine, CESAR1). A machine learning model was developed to forecast emissions and evaluate intervention impacts, revealing opposite effects among solvent components. Mitigation strategies designed for single-component solvents may not transfer to mixed-amine operation. Because this process is highly complex for conventional process models, the approach is positioned for broader application.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Experimental campaign and stress tests

Machine learning approach for dynamic forecasting

UC Berkeley UC Berkeley Previously Published Works Title Machine learning for industrial processes: Forecasting amine emissions from a carbon capture plant Permalink [https://escholarship.org/uc/item/3cd037qh](https://escholarship.org/uc/item/3cd037qh) Journal Science Advances, 9(1) ISSN 2375-2548 Authors Jablonka, Kevin Maik Charalambous, Charithea Sanchez Fernandez, Eva et al. Publication Date 2023-01-06 DOI 10.1126/sciadv.adc9576 Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California APPLIED SCIENCES AND ENGINEERING Machine learning for industrial processes: Forecasting amine emissions from a carbon capture plant Kevin Maik Jablonka1†, Charithea Charalambous2†, Eva Sanchez Fernandez3, Georg Wiechers4, Juliana Monteiro5, Peter Moser4, Berend Smit1*, Susana Garcia2* One of the main environmental impacts ofamine-based carbon capture processes is the emission of the solvent into the atmosphere. To understand how these emissions are affected by the intermittent operation of a powerplant, we performed stress tests on a plant operating with a mixture of two amines, 2-amino-2-methyl-1-propanol and piperazine (CESAR1). To forecast the emissions and model the impact of interventions, we developed a machine learning model. Our model showed that some interventions have opposite effects on the emissions of the components of the solvent. Thus, mitigation strategies required for capture plants operating on a single component solvent (e.g., monoethanolamine) need to be reconsidered if operated using a mixture ofamines. Amine emissions from a solvent-based carbon capture plant are an example of a process that is too complex to be described by conventional process models. We, therefore, expect that our approach can be more generally applied. Copyright © 2023 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC) . INTRODUCTION The most well-known and broadly used benchmark solvent to capture CO2 is monoethanolamine (MEA) ( 1) . Energy efficiency, however, is not the only criterion that is important in selecting a solvent for a carbon capture process. Amine emissions are equally important, as these may require cost-incurring gas treatment strategies to meet the operational permits and address environmental concerns (2, 3) . At present, we do not have a clear understanding of these amine emissions from a capture plant operating with these new solvent mixtures such as CESAR1 (4, 5) . Amine emissions from carbon capture plants are one example of an industrial process for which the plant’s design, control, and optimization require detailed knowledge of how the process parameters interact and affect the operation of the plant and what the (chemical) mechanisms and rate constants are. Because of the complexity of such plants, process models typically focus on capturing the steady-state operation (6) . However, there are many cases in which operation beyond the steady state is required. For instance, the design and operation of current and future power plants will need to constantly adapt to the increased share of intermittent renewable energy generation (7, 8, 9, 10). This requires tools that fully capture the dynamic and multivariate behavior of the plant away from its steady-state operation. The classical analysis techniques, such as response function fits (11, 12), or chemometrics approaches (13) give some insights into the typical response to the different perturbations. However, these techniques cannot take the full multivariate, nonlinear nature of the time-dependent behavior of a complex plant into account. In addition, conventional causal analysis techniques cannot be used without an understanding of the mechanisms (i.e., the causal graph) ( 14)

FAQs

Why are amine emissions important in carbon capture processes?

Amine emissions influence environmental and regulatory compliance, often requiring gas treatment strategies to meet operational permits and address environmental concerns.

How were intermittent operation effects studied in the work?

Stress tests were performed on a pilot capture plant at Niederaußem with the CESAR1 solvent mixture, using multiple scenarios to mimic intermittency from future power plants.

What did the machine learning model enable beyond basic forecasting?

It forecasted emissions from time-dependent plant behavior and supported modeling of emission mitigation interventions, including identifying that some measures have opposite effects on different solvent components.

Aug 5, 2026

Upload by Jiven