The evolution of artificial intelligence (AI), machine learning (ML), and neural networks (NN) is transforming the landscape of scientific and engineering modeling. It also prompts a debate on the role of first-principles modeling (FPM) in chemical engineering. While data-driven methods excel at interpolation and very rapid development, they often lack physical fidelity, interpretability, and reliable extrapolation capabilities. This article provides a personal academic and industrial perspective on the synergistic integration of FPM and AI-based methods, highlighting their complementary roles in process systems engineering. We argue that FPM (based on fundamental conservation laws and mechanistic understanding of phenomena), remains indispensable for ensuring robustness, safety, physical consistency, and adaptability of models in PSE. Moreover, we analyze the synergistic potential of hybrid approaches by deconstructing the model-building workflow. The latter is the primary lens to identify key decision points where integration delivers maximum value, moving beyond a simple paradigm comparison. Using this structured analysis of the model-building workflow, we identify several major opportunities for this integration, particularly where first-principles knowledge is incomplete. The discussion extends to practical strategies for model validation, scalability, and industrial applications, supported by case studies, as well as the potential of LLMs in assisting the future developments of FPM. Finally, we conclude that a physics-informed foundation for modeling is not obsolete but is instead critical for guiding the safe and reliable application of AI in chemical engineering.

Process Intensification (PI) is an effective way to enhance process efficiency and sustainability at affordable costs and efforts, attracting particular interest in the European area, as one of the most important chemical production areas in the world. PI primarily contributes by developing and testing new processing technologies that once integrated within a process improve the overall process performance substantially but as a result, it may alter the overall process (flowsheet) structure and its dynamic behavior. As such PI plays a key role in improving energy efficiency, optimizing resource allocation, and reducing environmental impact of industrial processes, and thereby leading to a cost-effective, eco-efficient, low-carbon and sustainable industry. However, along with opportunities, the PI new technologies have challenges related to failures in longer-term performance. In this respect, Process Systems Engineering (PSE) stance is more on integration aspects of new PI technologies into processes by making process (re)designs, doing operability studies, and performance optimizations within a supply chain setting. PSE contributes to overcoming the challenges by providing systematic approaches for the design and optimization of PI technologies. This perspective paper is a lightly referenced scholarly opinion piece about the status and directions of process intensification field from a PSE viewpoint. Primarily, it focuses on PSE perspectives towards sustainable lower energy usage process systems and provides a brief overview of the current situation in Europe. It also emphasizes the key challenges and opportunities for (new) PI technologies considering their integration in a process in terms of process synthesis and design, process flowsheet optimization, process and plantwide control, (green) electrification, sustainability improvements. Potential research directions on these aspects are given from an industrial and academic perspective of the authors.

Process Systems Engineering (PSE) is a discipline that deals with decision-making, at all levels and scales, by understanding any complex process system using a holistic view and a systems thinking framework. A closely related discipline (considered usually a part of PSE) is the Computer Aided Process Engineering (CAPE) which is a complementary field that focuses on developing methods and providing solution through systematic computer aided techniques for problems related to the design, control and operation of chemical systems. Nowadays, the ‘PSE’ term suffers from a branding issue to the point that PSE no longer gets the recognition that it deserves. In chemical engineering education the integrative systems frame for process design, control and operations is virtually absent. Its application potential in process industry lags relative to academic research progress and results. This work aims to provide an informative industrial and academic perspective on PSE (focused on the European region), arguing that the ‘systems thinking’ and ‘systems problem solving’ have to be given priority over just applications of computational problem solving methods. A multi-level view of the PSE field is provided within the academic and industrial context, and enhancements for PSE are suggested at their industrial and academic interfaces to create win-win situations.

Process Systems Engineering (PSE) deals with decision-making, at all levels and scales, by understanding complex process systems using a holistic view. Computer Aided Process Engineering (CAPE) is a complementary field that focuses on developing methods and providing solution through systematic computer aided techniques for problems related to the design, control and operation of chemical systems. The ‘PSE’ term suffers from a branding issue to the point that PSE does not get the recognition it deserves. This work aims to provide an informative industrial and academic perspective on PSE, arguing that the ‘systems thinking’ and ‘systems problem solving’ have to be prioritized ahead of just applications of computational problem solving methods. A multi-level view of the PSE field is provided within the academic and industrial context, and enhancements for PSE are suggested at their industrial and academic interfaces.

Atomic layer deposition (ALD) is a gas-phase coating technique that can be used to coat nanoparticles in a fluidized bed reactor. ALD is based on the alternating supply of two precursors, which makes it an inherent dynamic process. We discuss a multi-scale, multiphase mass transfer-diffusion-reaction model capable of predicting the evolution of surface coverage of particles at different local operating conditions. The dynamic ALD-reactor model can be extended with operational scenarios. The reactor design combined with the scenarios has many degrees of freedom, yielding ample opportunities to optimize the process with efficient utilization of precursors.

In this work, we develop a mixed integer linear optimization model that can be used to select appropriate sources, capture technologies, transportation network and CO₂ storage sites and optimize for a minimum overall cost for a nationwide CO₂ emission reduction in the Netherlands. Five different scenarios are formulated by varying the location of source and storage sites available in the Netherlands. The results show that the minimum overall cost of all scenarios is €47.8 billion for 25 years of operation and 54Mtpa capture of CO₂. Based on the investigated technologies, this work identifies Pressure Swing Adsorption (PSA) as the most efficient for post-combustion CO₂ capture in the Netherlands. The foremost outcome of this study is that the capture and compression is the dominant force contributing to a majority of the cost.

A major challenge for the industrial deployment of a CO₂ emission reduction methodology is to reduce the overall cost and the integration of all the nodes in the supply chain for CO₂ emission reduction. In this work, we develop a mixed integer linear optimization model that selects appropriate sources, capture process, transportation network and CO₂ storage sites and optimize for a minimum overall cost. Initially, we screen the sources and storage options available in the Netherlands at different levels of detail (locations and industrial activities) and present the network of major sources and storage sites at the more detailed level. Results for a case study estimate the overall optimized cost to be €47.8 billion for 25 years of operation and 54 Mtpa reduction of CO₂ emissions (30% of the 2013 levels). This work also identifies the preferred technologies for the CO₂ capture and we discuss the reasons behind it. The foremost outcome of this case study is that capture and compression consumes the majority of the costs and that further optimization or introduction of new efficient technologies for capture can cause a major reduction in the overall costs.