Prerpints.org logo
Preprint
Article

This version is not peer-reviewed.

Is ChatGPT a Reliable Source for Writing Review Articles in Catalysis Research? A Case Study on CO2 Hydrogenation to Higher Alcohols

  + These authors have contributed equally.

Submitted:

16 February 2023

Posted:

17 February 2023

You are already at the latest version

Abstract
ChatGPT is an AI language model trained on vast amounts of text data, including scientific papers, providing a comprehensive understanding of catalysis. However, its reliability in catalysis research is unknown. To evaluate reliability, we compared a ChatGPT-generated review article on heterogeneous catalysts for higher alcohols synthesis by CO2 hydrogenation to published peer-reviewed papers. Although the ChatGPT review article covers most necessary parts, it lacks sufficient discussion of the reaction mechanism. The core sections are too general, being not specific enough to the topic, and contain errors. The lack of citations further increases unreliability. While ChatGPT can provide much content on catalysis, it is insufficient and inaccurate for research on specific topics.
Keywords: 
ChatGPT
;  
heterogeneous catalysis
;  
CO2 hydrogenation
;  
reliability
Subject: 
Chemistry and Materials Science  -   Chemical Engineering

1. Introduction

Artificial Intelligence (AI) is the simulation of human intelligence in machines that are designed to think and act like humans [1]. It encompasses the creation of computer programs and systems that can carry out tasks requiring human intelligence, such as speech recognition, visual perception, language translation, information analysis, pattern recognition, and decision-making [2,3]. AI plays a critical role in scientific research by offering new tools for data analysis [4], knowledge discovery [5,6], and repetitive task automation [7,8]. As a result, it is widely used across a range of scientific disciplines, including information science, mathematics, medicine, materials science, geoscience, life science, physics, and chemistry [3].
In the field of chemistry research, the lack of comprehensive and analytical theories for the structures, properties, and transformations of macroscopic substances leads to a reliance on unreliable heuristics and fragmented rules. AI has the potential to revolutionize chemistry by recognizing patterns from vast data and transforming how complexity is managed [3]. AI has been applied in several sub-fields of chemistry, including analytical and computational chemistry, organic chemistry, catalysis, and medical chemistry [3]. AI has helped in overcoming the limitations of manual feature selection methods [9,10] and has improved the accuracy and efficiency of various computational theories [11,12]. Additionally, AI has empowered robotics to automate molecule synthesis [13,14] and has assisted in exploring extensive catalyst design spaces [15,16]. Furthermore, AI has facilitated chemical screening in toxicology with reduced ethical concerns [17].
AI has also been widely utilized in the field of catalysis research, playing a significant role in improving the efficiency and accuracy of the research process. AI can be applied in several key ways, including predictive modeling of catalytic reaction kinetics and mechanisms [18,19], assisting in the screening of potential catalysts for a specific reaction [20,21], optimizing reaction conditions such as temperature, pressure, and concentration [22,23], and real-time monitoring and control of catalytic processes [24].
ChatGPT is a particular AI technology that utilizes the Generative Pretrained Transformer (GPT) architecture. It is trained on large amounts of text data to generate human-like responses in natural language processing tasks, making it ideal for conversational applications [25,26]. In essence, ChatGPT is an AI model designed specifically for conversational purposes. ChatGPT is a powerful tool for scientific research, enabling researchers to quickly and efficiently summarize scientific papers and articles, analyze large amounts of data to uncover patterns and correlations, answer complex scientific questions in a variety of fields, and assist in the process of reviewing scientific literature [25]. With its broad understanding of the scientific world, derived from its training on diverse text data, ChatGPT can significantly streamline and enhance the research process, providing researchers with a valuable resource in their pursuit of knowledge [27].
As an AI language model, ChatGPT has been trained on a vast amount of text data, including scientific papers and articles, allowing it to have a comprehensive understanding of the field of catalysis. In terms of catalysis, ChatGPT's training data may include information on various topics such as types of catalysts, including homogeneous, heterogeneous, and enzymatic catalysts and their specific applications. Additionally, it likely has information on catalyst design and synthesis, including the optimization of their properties for specific reactions. It may also have information on reaction kinetics, including the rate of chemical reactions involving catalysts and the factors that influence it. Furthermore, ChatGPT is likely to have knowledge of the thermodynamics of catalytic reactions, including activation energy and reaction enthalpies, as well as industrial applications of catalysts, such as their use in the production of chemicals, fuels, and materials. (Generated by ChatGPT by asking what content on catalysis is involved in ChatGPT.)
The application of ChatGPT in catalysis research is an area deserving of further investigation, as its reliability in this field is yet to be fully established. Despite being a valuable tool for scientific research and possessing a wealth of information on catalysis, the validity of its outputs in the context of catalysis research needs to be assessed. The utilization of CO2 through catalytic conversion into value-added products is a crucial method for reducing CO2 emissions and mitigating the effects of global warming. Higher alcohols, such as C2-4OH, have a wide range of uses, including as fuels, fuel additives, solvents, reactants, and intermediates for chemical synthesis, making them highly valuable [28,29,30]. As such, the synthesis of higher alcohols through CO2 hydrogenation has garnered significant attention [30,31,32,33]. In this paper, we evaluate the reliability of ChatGPT in catalysis research by analyzing a review paper generated by ChatGPT on heterogeneous catalysts for the synthesis of higher alcohols through CO2 hydrogenation. We find that the generated review article lacks a sufficient discussion of the reaction mechanism. Additionally, the core sections are too general and not specific enough to the topic, containing errors and lacking citations. All these make the generated review article unreliable. While ChatGPT can provide a lot of content on catalysis, it may not be suitable for in-depth research on specific topics due to its inaccuracies and insufficiencies.

2. Methodology

A review paper on the topic of heterogeneous catalysts for the synthesis of higher alcohols through CO2 hydrogenation was generated using ChatGPT (https://chat.openai.com/, ChatGPT Jan 9 Version). The authors first asked ChatGPT to provide an outline for the paper, then used the table of contents provided to request the generation of the content for each section. The resulting output from ChatGPT was then integrated and only underwent minor modifications by the authors to form a complete review paper. The reliability of ChatGPT in catalysis research was evaluated by comparing the ChatGPT-generated paper to peer-reviewed research and review papers on the same topic.

3. Results and discussion

3.1. General comments on the ChatGPT-generated review article

The article was generated by ChatGPT after we asked it to create an outline and then requested the contents for each chapter based on that outline. The final result was a comprehensive review article on heterogeneous catalysts for higher alcohol synthesis via CO2 hydrogenation, with minor modifications made to the generated contents. The chat history and generated review paper are available in the supporting information.
It is worth mentioning that the review paper generated by ChatGPT does not include figures or citations. As suggested by ChatGPT, it is a text-based AI model, not capable of providing figures or images as it can't generate or display them. It can only generate and provide text-based answers to questions. Besides, ChatGPT was not designed to provide references or citations for the information it provides. Its primary purpose is to generate human-like text based on the input it receives and the vast amounts of text data it was trained on. The information it generates is not always verifiable and should not be taken as authoritative or necessarily accurate. The absence of figures decreases the visual appeal and readability of the generated content, while the lack of references or citations undermines the credibility and reliability. Other challenges that may arise when using ChatGPT to generate a review article include the possibility of generating incorrect information, producing harmful or biased content, and having limited knowledge of events and developments after 2021 [26].

3.2. Evaluation of the structure of the review article

Initially, we requested ChatGPT to produce an outline for a review article focused on heterogeneous catalysts for the synthesis of higher alcohols such as ethanol, propanol, and butanol through CO2 hydrogenation. ChatGPT drafted an outline for a review article on the assigned topic, which includes five sections: introduction, CO2 hydrogenation reaction, heterogeneous catalysts for CO2 hydrogenation, case studies, and conclusion. Moreover, ChatGPT also suggested the contents should be included in every chapter of the review article (Table 1).
As shown in Table 1, the introduction section provides a comprehensive overview of the background of the topic. It highlights the significance of higher alcohols as sustainable energy sources and chemicals, details the current state of their synthesis methods, and underscores the pressing need for a thorough review on this topic. Chapter 2, which focuses on the CO2 hydrogenation reaction, offers a comprehensive understanding of the synthesis of higher alcohols through this method. It provides critical information, including reaction chemistry, key parameters, and challenges, which are essential for a deeper appreciation of the catalysis involved in the synthesis of higher alcohols through CO2 hydrogenation. Chapter 3, which focuses on heterogeneous catalysts for CO2 hydrogenation, serves as the cornerstone of the review article. It provides an overview and comparison of various heterogeneous catalyst types and highlights the key parameters that impact their performance, offering a comprehensive guide for designing effective catalysts. Chapter 4 delves into the examination of specific catalysts used in the CO2 hydrogenation process to produce higher alcohols. It provides an in-depth analysis of the catalytic performances of these catalysts and the impact of reaction conditions on the outcome. The chapter presents a comprehensive overview of the most recent and advanced catalysts in the field. In the conclusion section, ChatGPT recommends summarizing the findings of the review, addressing the obstacles and prospects, and proposing future research directions.
Compared to other published review articles on the same topic [30,34], the outline generated by ChatGPT appears to encompass most of the crucial aspects and has a well-structured presentation of information. However, the arrangement of the contents may vary, which is simply a matter of personal preference. Unfortunately, this review article does not cover the reaction mechanism, a crucial aspect of catalysis, as indicated by the outline. This is a significant shortfall of this review article.

3.3. Evaluation of the introduction section

The introduction chapter thoroughly covers the essential aspects of the background of higher alcohol synthesis. Despite its well-structured format, there are still some mistakes in the contents (Table 2). These mistakes occur when discussing the advantage of the high energy density of higher alcohols and the thermochemical conversion methods for higher alcohol synthesis. When discussing the chemical synthesis method for higher alcohol synthesis, several critical reactions are overlooked. Thus, the introduction section can be further improved.

3.4. Evaluation of Chapter 2: Fundamentals and challenges of higher alcohols synthesis by CO2 hydrogenation

In Chapter 2, ChatGPT addresses the basics and challenges of synthesizing higher alcohols through CO2 hydrogenation. The chapter provides a brief overview of the reaction, an oversimplified mechanism, and the reaction conditions. The challenges related to catalyst selectivity, stability, low conversion rates, and cost are also discussed. However, in comparison to existing review articles, some crucial aspects regarding CO2 hydrogenation to higher alcohols are not covered. The complex reaction system, including side reactions such as methane formation, methanol formation, and the reverse water gas shift reaction (RWGSR), is not introduced. Additionally, the provided reaction mechanism is oversimplified, omitting alternative routes for CO2 hydrogenation to higher alcohols. The thermodynamics of the reactions, which plays a crucial role in determining the feasibility, direction, and extent of a reaction, is also not discussed. This information is vital for understanding catalytic phenomena and designing catalysts.
Additionally, there are some inaccuracies or mistakes in Chapter 2 (Table 3). For instance, the reaction equation lacks stoichiometric numbers and does not mention the presence of side products. The explanation of the reaction mechanism and the route is overly simplified. The impact of temperature and pressure, as well as the cause of low conversion rates, are not accurately described. This chapter could be improved by incorporating missing information and correcting these inaccuracies.

3.5. Evaluation of Chapter 3: Heterogeneous catalysts for CO2 hydrogenation to higher alcohols

In Chapter 3, an overview of heterogeneous catalysts for CO2 hydrogenation to higher alcohols is provided. The categorization of these catalysts into metal and metal oxide catalysts by ChatGPT is insufficient, as many higher alcohol catalysts contain both metal and metal oxide. Supported catalysts, for instance, typically consist of a metal supported on a metal oxide, as exemplified by RhFeLi/TiO2 [43] and Pt/Co3O4 [44]. Furthermore, the synergy between metal and metal oxide sites is often vital for higher alcohol formation, as demonstrated by the importance of the synergy between metallic Co and Co oxide[45]. Additionally, other catalysts, such as MoS2 [46], Mo2C [47], and Co2C [48], are also effective for CO2 hydrogenation to higher alcohols but cannot be classified as metal or metal oxide-based catalysts. A more appropriate categorization approach would involve classifying catalysts based on the types of constituent elements, as is commonly done in published review articles [30,49].
Then, ChatGPT examines metal catalysts, specifically palladium (Pd), platinum (Pt), and nickel (Ni) based catalysts, as well as bimetallic catalysts, for application in producing higher alcohols via CO2 hydrogenation. While palladium has been demonstrated as an effective catalyst for ethanol production, only a limited number of examples have been published [50,51,52]. Platinum, on the other hand, has been reported to be active for higher alcohol synthesis, but is typically combined with cobalt-based materials [44,53,54], and is regarded as a promoter for cobalt-based catalysts [44]. However, even platinum-containing catalysts that produce small amounts of butanol exhibit low selectivity for this alcohol, with ethanol being the main product. Similarly, nickel is utilized as a promoter to enhance the synthesis of higher alcohols in cobalt-based catalysts, but results in only small amounts of propanol, lacking high selectivity [55]. Thus, the assertion that platinum and nickel exhibit selectivity towards butanol and propanol, respectively, as suggested by ChatGPT, is deemed inadequate. Bimetallic catalysts, such as palladium-copper, have shown improved selectivity towards higher alcohols [52]. However, palladium-zinc and platinum-zinc suggested by ChatGPT as efficient are not known to be active catalysts for higher alcohol synthesis via CO2 hydrogenation. Notably, while palladium, platinum, and nickel-containing catalysts have demonstrated activity in CO2 hydrogenation to higher alcohols, they are not the most commonly studied catalysts [30,34], with rhodium, copper, cobalt, and molybdenum-based catalysts being more widely researched, which have not been discussed in the ChatGPT generated review paper.
In regards to metal oxide catalysts, ChatGPT suggested that TiO2, ZnO, and CeO2 exhibit activity. However, while metal oxides may be included as a component of certain CO2 to higher alcohols catalysts for their ability to activate CO2 [56] and stabilize intermediates [57], act as a promoter [58,59], or serve as support [60], they typically require the presence of a metal to be active for higher alcohols synthesis. It should be noted that other oxides, such as SiO2 [48], Al2O3 [45], MnO [61], ZrO2 [62], In2O3 [33], and Ga2O3 [63], play a similar role but are not included by ChatGPT.
Then, ChatGPT discussed the photocatalytic activity of TiO2 for synthesizing ethanol from the reaction of CO2 and water under light irradiation, which should not be confused with CO2 hydrogenation reactions. Catalysts containing TiO2 for CO2 hydrogenation to higher alcohols, such as RhFe/TiO2 [64], Rh10Se/TiO2 [60], NaCo/TiO2 [48], and PdCu/TiO2 [52], are not covered in the ChatGPT generated review. ChatGPT suggests that ZnO can be used alone or as a support for metal to selectively produce propanol. While ZnO-containing catalysts such as K/Cu-Zn [65] and NaCo/ZnO [48] exist, there is no evidence of their selectivity for propanol or the application of sole ZnO catalysts for CO2 hydrogenation to higher alcohols. Similarly, CeO2 can be used as a promoter (e.g. RhCe/SiO2 [58]) or support (e.g. Rh/CeO2 [59]) for CO2 hydrogenation to higher alcohols, but ChatGPT's assertion of their high selectivity for high butanol is not proven, and sole CeO2 is not active for higher alcohols synthesis.
After that, ChatGPT presented a general comparison between the advantages and disadvantages of metal and metal oxide catalysts. However, as previously noted, it is not reasonable to categorize catalysts solely into these two groups. Therefore, a comparison between different catalysts for higher alcohol synthesis by CO2 hydrogenation would require more information. The reliability of this chapter is compromised due to unreasonable categorization and lack of information on representative catalysts.
The factors that affect catalyst performance, including composition, crystal structure, and surface properties are also discussed in this chapter. First, the effects of composition on CO2 hydrogenation to higher alcohols are discussed, with a focus on metal and metal oxide catalysts. As suggested by ChatGPT, copper, nickel, and cobalt-based metal catalysts possess high activity and selectivity for ethanol, propanol, and butanol, respectively. Similarly, copper oxide, nickel oxide, and cobalt oxide exhibit high activity and selectivity for ethanol, propanol, and butanol. However, it is worth noting that the discussion on composition effects lacks sufficient evidence from published articles and appears to be template-driven. Then, the effects of catalyst loading and catalyst support choice are discussed, but the information provided is too general to be useful for understanding their specific effects in catalysts used for synthesizing higher alcohols through CO2 hydrogenation.
In the following paragraphs, the effects of the crystal structure are discussed. Some examples (FCC vs HCP copper, FCC vs BCC cobalt, tetragonal vs cubic copper oxide, and tetragonal vs hexagonal nickel oxide) are provided after a general discussion on crystal structure’s effects. However, these claims lack a reliable source to support them.
The effects of surface properties on the catalytic performance of metal and metal oxide catalysts are discussed, including examples of the impact of surface area. ChatGPT suggested that high surface area copper and copper oxide catalysts have been found to exhibit higher activity and selectivity for ethanol synthesis compared to their low surface area counterparts. Similarly, high surface area cobalt/nickel oxide catalysts have been found to have higher activity and selectivity for butanol/propanol synthesis. However, the provided examples lack reliable sources to support them and appear to be template-driven. Additionally, the effects of synthesis and post-treatment methods are discussed in general terms but not specific to higher alcohol synthesis by CO2 hydrogenation.
Finally, the combined effects of various factors are discussed in this chapter. ChatGPT notes that copper catalysts' composition significantly influences their crystal structure and surface properties, ultimately impacting their catalytic activity and selectivity. Examples of promoter-enhanced copper catalysts, such as copper-zinc and copper-manganese, are presented. These catalysts' synergy leads to more active and selective surfaces and specific crystal structures, improving their overall performance. While the effects of zinc on CO2 hydrogenation have been documented [65], copper-manganese catalysts have only been reported in the literature for syngas conversion to higher alcohols [66]. Additionally, the discussion lacks sufficient catalytic data to substantiate its claims.

3.6. Evaluation of Chapter 4: Case studies

Chapter 4 provides case studies on heterogeneous catalysts for CO2 hydrogenation to synthesize higher alcohols, which are categorized into copper, nickel, cobalt, and iron-based catalysts. This categorization differs from Chapter 3, which focused on metal (palladium, platinum, nickel, bimetallic catalysts) and metal oxide catalysts (TiO2, ZnO, and CeO2). Interestingly, copper and cobalt-based catalysts are commonly used for this purpose, while nickel and iron-based catalysts are less frequently reported. The chapter includes various examples of each type of catalyst.
Table 4 presents a list of catalysts discussed in Chapter 4. Copper, nickel, and cobalt catalysts with the same catalyst supports are provided, and their discussions are similar in format, lacking supports by catalytic results. For instance, in the case of Cu-ZnO catalysts, ChatGPT stated that they are active in the synthesis of ethanol and propanol through CO2 hydrogenation. The addition of zinc oxide to copper enhances the catalyst's selectivity and stability. The descriptions of all the other catalysts follow a similar pattern, which reduces the reliability of the ChatGPT-generated review article. Among the catalysts listed in Table 4, only Cu-zeolite [67] and Co-Al2O3 [45] are reported active for higher alcohols synthesis by CO2 hydrogenation. Other listed catalysts without further promotion are not effective.
ChatGPT conducted a performance comparison of various catalysts for the synthesis of higher alcohols through CO2 hydrogenation. As stated by ChatGPT, the comparison can be complicated due to several factors that can influence catalyst performance, but certain trends can still be identified. The discussion covers metal and metal oxide catalysts, the impact of support, and the effects of post-treatment.
When discussing general trends in metal catalysts, it is suggested that copper catalysts display the highest selectivity towards ethanol, while nickel catalysts show the highest selectivity towards propanol. Cobalt catalysts are active for synthesizing both ethanol and propanol but with lower selectivity compared to copper and nickel catalysts. While iron catalysts are active for synthesizing ethanol, propanol, and butanol, their selectivity is lower than that of copper, nickel, and cobalt catalysts. It should be noted that nickel and iron catalysts are not commonly studied and are typically used as promoters, rendering such comparisons meaningless.
Additionally, it is suggested by ChatGPT that metal oxide-based catalysts, including copper oxide, nickel oxide, and cobalt oxide, have demonstrated superior selectivity and stability in comparison to metal-based catalysts. However, the selectivity and stability of metal oxides can vary depending on the particular metal oxide used and the reaction conditions. It should be noted that, as far as the authors are aware, these metal oxides alone are not active for higher alcohol synthesis through CO2 hydrogenation without metal promotion.
In regards to the effects of support, it is suggested by ChatGPT that catalysts supported on silica display the highest selectivity towards ethanol, while catalysts supported on zeolites show the highest selectivity towards butanol. However, it should be noted that most reported catalysts are typically selective towards ethanol. Moreover, the published paper provides evidence that the presence of zeolite does not have to result in the formation of butanol [67,68]. Concerning the effects of post-treatment, ChatGPT suggested that catalysts that undergo calcination or reduction are more active for synthesizing higher alcohols through CO2 hydrogenation. Nonetheless, since calcination and reduction are commonly used post-treatment methods, it is difficult to draw such a conclusion without additional information on the synthesis process.
In the following section, ChatGPT explores the factors that impact the performance of a catalyst in various conditions, including temperature, pressure, flow rate of reactants, and impurities. After a general overview, specific examples are given to demonstrate the effects of these factors. Since the influence of reaction conditions is very complicated, and the examples provided by ChatGPT often lack details about the catalysts, the described trend may be accurate in some cases but incorrect in others. To highlight the effect of temperature on CO2 hydrogenation to form higher alcohols, two examples are provided. Copper-based catalysts exhibit higher activity but lower selectivity at high temperatures, while cobalt-based catalysts exhibit higher selectivity but lower activity at lower temperatures. However, it's important to note that these trends are not consistently observed in many published papers and in some cases, an increase in selectivity to higher alcohols is observed with a higher reaction temperature [44,45,55,69].
Regarding the effects of pressure on catalytic conversion of CO2, ChatGPT suggested that for copper-based catalysts, increasing the pressure of CO2 and H2 can enhance the conversion of CO2, but may decrease selectivity towards higher alcohols. For cobalt-based catalysts, decreasing the pressure of CO2 may improve selectivity towards higher alcohols, but this may decrease the conversion of CO2. However, there are some discrepancies in the literature, as An et al. observed decreased CO2 conversion with unchanged ethanol selectivity when using copper-based catalysts at higher reaction pressures [70]. Furthermore, the trends over cobalt-based catalysts have not been found in published papers.
When discussing the effects of the flow rate of reactants, it is suggested that a high flow rate of CO2 favors high CO2 conversion and low selectivity to higher alcohols over copper and cobalt-based catalysts. However, the effects of CO2 flow rate or the GHSV (gas hourly space velocity) can be complex and depend on the specific catalyst used and the range of GHSV[71]. Therefore, the description provided may not be entirely accurate. The effects of impurities are also discussed, covering the impact of impurities such as water, sulfur, and chlorine, along with specific strategies to mitigate their effects. A general discussion on the subject is provided before delving into practical solutions.

3.7. Evaluation of the conclusion section

In the conclusion section, ChatGPT briefly summarizes the topics discussed and highlights the challenges and opportunities in the field of CO2 hydrogenation to higher alcohols. Future research directions in the field include the development of more efficient and selective catalysts, optimization of reaction conditions, study of reaction mechanism, scale-up of the process, exploration of alternative feedstocks, exploration of other catalytic systems, and study of the reaction intermediates. However, more specific and detailed information may be needed to fully address the challenges and realize the potential of higher alcohols as renewable energy sources and chemicals.

4. Conclusions

ChatGPT is an artificial intelligence language model that has been trained on large amounts of text data, including scientific papers. As a result, it has a comprehensive understanding of catalysis. We requested ChatGPT to generate a review article on the topic of heterogeneous catalysts for higher alcohol synthesis by CO2 hydrogenation. The article covers the necessary parts, including the introduction, CO2 hydrogenation reaction, heterogeneous catalysts for CO2 hydrogenation, case studies, and conclusion. However, the reaction mechanism is missing, which is an essential part of this topic. Although the introduction and CO2 hydrogenation parts contain some errors, they can still provide the necessary background and fundamental knowledge on this topic. The heterogeneous catalysts for CO2 hydrogenation and case studies are the core parts of this review article. However, their structure is not well-organized, and important content on this topic is missing. Many contents are also incorrect or unreliable. The conclusion section summarizes the topics discussed and highlights the challenges and opportunities, as well as future research directions in the field of CO2 hydrogenation to higher alcohols, which are helpful but lacking more specific and detailed information. In conclusion, while ChatGPT can provide a considerable amount of content on catalysis, it is insufficient and inaccurate for research on specific topics.

Acknowledgments

We acknowledge the financial support from National Natural Science Foundation of China (22208143), Nanjing Tech University (39801170), and the State Key Laboratory of Materials-Oriented Chemical Engineering (38901218).

References

  1. Garg, P. K. Overview of Artificial Intelligence. In Artificial Intelligence; Chapman and Hall/CRC, 2021. [Google Scholar]
  2. Joiner, I. A. Chapter 1 - Artificial Intelligence: AI Is Nearby. In Emerging Library Technologies; Joiner, I. A., Ed.; Chandos Information Professional Series; Chandos Publishing, 2018; pp 1–22. [CrossRef]
  3. Xu, Y.; Liu, X.; Cao, X.; Huang, C.; Liu, E.; Qian, S.; Liu, X.; Wu, Y.; Dong, F.; Qiu, C.-W.; Qiu, J.; Hua, K.; Su, W.; Wu, J.; Xu, H.; Han, Y.; Fu, C.; Yin, Z.; Liu, M.; Roepman, R.; Dietmann, S.; Virta, M.; Kengara, F.; Zhang, Z.; Zhang, L.; Zhao, T.; Dai, J.; Yang, J.; Lan, L.; Luo, M.; Liu, Z.; An, T.; Zhang, B.; He, X.; Cong, S.; Liu, X.; Zhang, W.; Lewis, J. P.; Tiedje, J. M.; Wang, Q.; An, Z.; Wang, F.; Zhang, L.; Huang, T.; Lu, C.; Cai, Z.; Wang, F.; Zhang, J. Artificial Intelligence: A Powerful Paradigm for Scientific Research. The Innovation 2021, 2, 100179. [Google Scholar] [CrossRef] [PubMed]
  4. Rahmani, A. M.; Azhir, E.; Ali, S.; Mohammadi, M.; Ahmed, O. H.; Yassin Ghafour, M.; Hasan Ahmed, S.; Hosseinzadeh, M. Artificial Intelligence Approaches and Mechanisms for Big Data Analytics: A Systematic Study. PeerJ Comput. Sci. 2021, 7, e488. [Google Scholar] [CrossRef] [PubMed]
  5. Fayyad, U.; Piatetsky-Shapiro, G.; Smyth, P. From Data Mining to Knowledge Discovery in Databases. AI Mag. 1996, 17, 37–37. [Google Scholar] [CrossRef]
  6. Kiarashinejad, Y.; Zandehshahvar, M.; Abdollahramezani, S.; Hemmatyar, O.; Pourabolghasem, R.; Adibi, A. Knowledge Discovery in Nanophotonics Using Geometric Deep Learning. Adv. Intell. Syst. 2020, 2, 1900132. [Google Scholar] [CrossRef]
  7. Epps, R. W.; Bowen, M. S.; Volk, A. A.; Abdel-Latif, K.; Han, S.; Reyes, K. G.; Amassian, A.; Abolhasani, M. Artificial Chemist: An Autonomous Quantum Dot Synthesis Bot. Adv. Mater. 2020, 32, 2001626. [Google Scholar] [CrossRef] [PubMed]
  8. Burger, B.; Maffettone, P. M.; Gusev, V. V.; Aitchison, C. M.; Bai, Y.; Wang, X.; Li, X.; Alston, B. M.; Li, B.; Clowes, R.; Rankin, N.; Harris, B.; Sprick, R. S.; Cooper, A. I. A Mobile Robotic Chemist. Nature 2020, 583, 237–241. [Google Scholar] [CrossRef] [PubMed]
  9. Leong, Y. X.; Lee, Y. H.; Koh, C. S. L.; Phan-Quang, G. C.; Han, X.; Phang, I. Y.; Ling, X. Y. Surface-Enhanced Raman Scattering (SERS) Taster: A Machine-Learning-Driven Multireceptor Platform for Multiplex Profiling of Wine Flavors. Nano Lett. 2021, 21, 2642–2649. [Google Scholar] [CrossRef] [PubMed]
  10. Weng, S.; Yuan, H.; Zhang, X.; Li, P.; Zheng, L.; Zhao, J.; Huang, L. Deep Learning Networks for the Recognition and Quantitation of Surface-Enhanced Raman Spectroscopy. Analyst 2020, 145, 4827–4835. [Google Scholar] [CrossRef]
  11. Hermann, J.; Schätzle, Z.; Noé, F. Deep-Neural-Network Solution of the Electronic Schrödinger Equation. Nat. Chem. 2020, 12, 891–897. [Google Scholar] [CrossRef]
  12. Tavadze, P.; Avendaño Franco, G.; Ren, P.; Wen, X.; Li, Y.; Lewis, J. P. A Machine-Driven Hunt for Global Reaction Coordinates of Azobenzene Photoisomerization. J. Am. Chem. Soc. 2018, 140, 285–290. [Google Scholar] [CrossRef]
  13. Gao, H.; Struble, T. J.; Coley, C. W.; Wang, Y.; Green, W. H.; Jensen, K. F. Using Machine Learning To Predict Suitable Conditions for Organic Reactions. ACS Cent. Sci. 2018, 4, 1465–1476. [Google Scholar] [CrossRef] [PubMed]
  14. Grzybowski, B. A.; Szymkuć, S.; Gajewska, E. P.; Molga, K.; Dittwald, P.; Wołos, A.; Klucznik, T. Chematica: A Story of Computer Code That Started to Think like a Chemist. Chem 2018, 4, 390–398. [Google Scholar] [CrossRef]
  15. Goldsmith, B. R.; Esterhuizen, J.; Liu, J.; Bartel, C. J.; Sutton, C. Machine Learning for Heterogeneous Catalyst Design and Discovery. AIChE J. 2018, 64, 2311–2323. [Google Scholar] [CrossRef]
  16. Li, Z.; Wang, S.; Xin, H. Toward Artificial Intelligence in Catalysis. Nat. Catal. 2018, 1, 641–642. [Google Scholar] [CrossRef]
  17. Szegedy, C.; Zaremba, W.; Sutskever, I.; Bruna, J.; Erhan, D.; Goodfellow, I.; Fergus, R. Intriguing Properties of Neural Networks. arXiv , 2014. 19 February. [CrossRef]
  18. Kunz, M. R.; Yonge, A.; Fang, Z.; Batchu, R.; Medford, A. J.; Constales, D.; Yablonsky, G.; Fushimi, R. Data Driven Reaction Mechanism Estimation via Transient Kinetics and Machine Learning. Chem. Eng. J. 2021, 420, 129610. [Google Scholar] [CrossRef]
  19. Ulissi, Z. W.; Medford, A. J.; Bligaard, T.; Nørskov, J. K. To Address Surface Reaction Network Complexity Using Scaling Relations Machine Learning and DFT Calculations. Nat. Commun. 2017, 8, 14621. [Google Scholar] [CrossRef] [PubMed]
  20. Liu, X.; Cai, C.; Zhao, W.; Peng, H.-J.; Wang, T. Machine Learning-Assisted Screening of Stepped Alloy Surfaces for C1 Catalysis. ACS Catal. 2022, 12, 4252–4260. [Google Scholar] [CrossRef]
  21. Zhang, N.; Yang, B.; Liu, K.; Li, H.; Chen, G.; Qiu, X.; Li, W.; Hu, J.; Fu, J.; Jiang, Y.; Liu, M.; Ye, J. Machine Learning in Screening High Performance Electrocatalysts for CO2 Reduction. Small Methods 2021, 5, 2100987. [Google Scholar] [CrossRef]
  22. Al-Jamimi, H. A.; BinMakhashen, G. M.; Saleh, T. A. Multiobjectives Optimization in Petroleum Refinery Catalytic Desulfurization Using Machine Learning Approach. Fuel 2022, 322, 124088. [Google Scholar] [CrossRef]
  23. Kim, H. W.; Lee, S. W.; Na, G. S.; Han, S. J.; Kim, S. K.; Shin, J. H.; Chang, H.; Kim, Y. T. Reaction Condition Optimization for Non-Oxidative Conversion of Methane Using Artificial Intelligence. React. Chem. Eng. 2021, 6, 235–243. [Google Scholar] [CrossRef]
  24. Min, Q.; Lu, Y.; Liu, Z.; Su, C.; Wang, B. Machine Learning Based Digital Twin Framework for Production Optimization in Petrochemical Industry. Int. J. Inf. Manag. 2019, 49, 502–519. [Google Scholar] [CrossRef]
  25. Lund, B.; Ting, W. Chatting about ChatGPT: How May AI and GPT Impact Academia and Libraries? Rochester, NY , 2023. 22 January. [CrossRef]
  26. ChatGPT: Optimizing Language Models for Dialogue. OpenAI. https://openai.com/blog/chatgpt/ (accessed 2023-02-14).
  27. M. Alshater, M. Exploring the Role of Artificial Intelligence in Enhancing Academic Performance: A Case Study of ChatGPT. Rochester, NY , 2022. 26 December. [CrossRef]
  28. Zeng, F.; Xi, X.; Cao, H.; Pei, Y.; Heeres, H. J.; Palkovits, R. Synthesis of Mixed Alcohols with Enhanced C3+ Alcohol Production by CO Hydrogenation over Potassium Promoted Molybdenum Sulfide. Appl. Catal. B Environ. 2019, 246, 232–241. [Google Scholar] [CrossRef]
  29. Xi, X.; Zeng, F.; Cao, H.; Cannilla, C.; Bisswanger, T.; de Graaf, S.; Pei, Y.; Frusteri, F.; Stampfer, C.; Palkovits, R. Enhanced C3+ Alcohol Synthesis from Syngas Using KCoMoSx Catalysts: Effect of the Co-Mo Ratio on Catalyst Performance. Appl. Catal. B Environ. 2020, 272, 118950. [Google Scholar] [CrossRef]
  30. Zeng, F.; Mebrahtu, C.; Xi, X.; Liao, L.; Ren, J.; Xie, J.; Heeres, H. J.; Palkovits, R. Catalysts Design for Higher Alcohols Synthesis by CO2 Hydrogenation: Trends and Future Perspectives. Appl. Catal. B Environ. 2021, 291, 120073. [Google Scholar] [CrossRef]
  31. He, Y.; Liu, S.; Fu, W.; Wang, C.; Mebrahtu, C.; Sun, R.; Zeng, F. Thermodynamic Analysis of CO2 Hydrogenation to Higher Alcohols (C2–4OH): Effects of Isomers and Methane. ACS Omega 2022, 7, 16502–16514. [Google Scholar] [CrossRef]
  32. Fu, W.; Tang, Z.; Liu, S.; He, Y.; Sun, R.; Mebrahtu, C.; Zeng, F. Thermodynamic Analysis of CO2 Hydrogenation to Ethanol: Solvent Effects. ChemistrySelect 2023, 8, e202203385. [Google Scholar] [CrossRef]
  33. Xi, X.; Zeng, F.; Zhang, H.; Wu, X.; Ren, J.; Bisswanger, T.; Stampfer, C.; Hofmann, J. P.; Palkovits, R.; Heeres, H. J. CO2 Hydrogenation to Higher Alcohols over K-Promoted Bimetallic Fe–In Catalysts on a Ce–ZrO2 Support. ACS Sustain. Chem. Eng. 2021, 9, 6235–6249. [Google Scholar] [CrossRef]
  34. Xu, D.; Wang, Y.; Ding, M.; Hong, X.; Liu, G.; Tsang, S. C. E. Advances in Higher Alcohol Synthesis from CO2 Hydrogenation. Chem 2020, 7, 849–881. [Google Scholar] [CrossRef]
  35. Rao, A. G. Ahead: Paving the Way for Next Generation Aircraft and Engine; London: United Kingdom, 2015. [Google Scholar]
  36. Boerrigter, H.; Rauch, R. Review of Applications of Gases from Biomass Gasification. Handb. Biomass Gasif.
  37. Luk, H. T.; Mondelli, C.; Ferré, D. C.; Stewart, J. A.; Pérez-Ramírez, J. Status and Prospects in Higher Alcohols Synthesis from Syngas. Chem. Soc. Rev. 2017, 46, 1358–1426. [Google Scholar] [CrossRef]
  38. Hidzir, N. S.; Som, A.; Abdullah, Z. Ethanol Production via Direct Hydration of Ethylene: A Review. 2014. [Google Scholar]
  39. Dong, X.; Lei, J.; Chen, Y.; Jiang, H.; Zhang, M. Selective Hydrogenation of Acetic Acid to Ethanol on Cu-In Catalyst Supported by SBA-15. Appl. Catal. B Environ. 2019, 244, 448–458. [Google Scholar] [CrossRef]
  40. Morales Torres, G.; Frauenlob, R.; Franke, R.; Börner, A. Production of Alcohols via Hydroformylation. Catal. Sci. Technol. 2015, 5, 34–54. [Google Scholar] [CrossRef]
  41. Fan, T.; Liu, H.; Shao, S.; Gong, Y.; Li, G.; Tang, Z. Cobalt Catalysts Enable Selective Hydrogenation of CO2 toward Diverse Products: Recent Progress and Perspective. J. Phys. Chem. Lett. 2021, 12, 10486–10496. [Google Scholar] [CrossRef] [PubMed]
  42. Lee, W. J.; Li, C.; Prajitno, H.; Yoo, J.; Patel, J.; Yang, Y.; Lim, S. Recent Trend in Thermal Catalytic Low Temperature CO2 Methanation: A Critical Review. Catal. Today 2021, 368, 2–19. [Google Scholar] [CrossRef]
  43. Kusama, H.; Okabe, K.; Sayama, K.; Arakawa, H. The Effect of Rhodium Precursor on Ethanol Synthesis by Catalytic Hydrogenation of Carbon Dioxide over Silica Supported Rhodium Catalysts. In Studies in Surface Science and Catalysis; Elsevier, 1998; Vol. 114, pp 431–434. [CrossRef]
  44. He, Z.; Qian, Q.; Ma, J.; Meng, Q.; Zhou, H.; Song, J.; Liu, Z.; Han, B. Water-Enhanced Synthesis of Higher Alcohols from CO2 Hydrogenation over a Pt/Co3O4 Catalyst under Milder Conditions. Angew. Chem. Int. Ed. 2016, 55, 737–741. [Google Scholar] [CrossRef] [PubMed]
  45. Wang, L.; Wang, L.; Zhang, J.; Liu, X.; Wang, H.; Zhang, W.; Yang, Q.; Ma, J.; Dong, X.; Yoo, S. J.; Kim, J.-G.; Meng, X.; Xiao, F.-S. Selective Hydrogenation of CO2 to Ethanol over Cobalt Catalysts. Angew. Chem. Int. Ed. 2018, 57, 6104–6108. [Google Scholar] [CrossRef]
  46. Nieskens, D. L. S.; Ferrari, D.; Liu, Y.; Kolonko, R. The Conversion of Carbon Dioxide and Hydrogen into Methanol and Higher Alcohols. Catal. Commun. 2011, 14, 111–113. [Google Scholar] [CrossRef]
  47. Chen, Y.; Choi, S.; Thompson, L. T. Low Temperature CO2 Hydrogenation to Alcohols and Hydrocarbons over Mo2C Supported Metal Catalysts. J. Catal. 2016, 343, 147–156. [Google Scholar] [CrossRef]
  48. Zhang, S.; Liu, X.; Shao, Z.; Wang, H.; Sun, Y. Direct CO2 Hydrogenation to Ethanol over Supported Co2C Catalysts: Studies on Support Effects and Mechanism. J. Catal. 2020, 382, 86–96. [Google Scholar] [CrossRef]
  49. Gao, P.; Zhang, L.; Li, S.; Zhou, Z.; Sun, Y. Novel Heterogeneous Catalysts for CO2 Hydrogenation to Liquid Fuels. ACS Cent. Sci. 2020, 6, 1657–1670. [Google Scholar] [CrossRef]
  50. Lou, Y.; jiang, F.; Zhu, W.; Wang, L.; Yao, T.; Wang, S.; Yang, B.; Yang, B.; Zhu, Y.; Liu, X. CeO2 Supported Pd Dimers Boosting CO2 Hydrogenation to Ethanol. Appl. Catal. B Environ. 2021, 291, 120122. [Google Scholar] [CrossRef]
  51. Caparrós, F. J.; Soler, L.; Rossell, M. D.; Angurell, I.; Piccolo, L.; Rossell, O.; Llorca, J. Remarkable Carbon Dioxide Hydrogenation to Ethanol on a Palladium/Iron Oxide Single-Atom Catalyst. ChemCatChem 2018, 10, 2365–2369. [Google Scholar] [CrossRef]
  52. Bai, S.; Shao, Q.; Wang, P.; Dai, Q.; Wang, X.; Huang, X. Highly Active and Selective Hydrogenation of CO2 to Ethanol by Ordered Pd–Cu Nanoparticles. J. Am. Chem. Soc. 2017, 139, 6827–6830. [Google Scholar] [CrossRef] [PubMed]
  53. Ouyang, B.; Xiong, S.; Zhang, Y.; Liu, B.; Li, J. The Study of Morphology Effect of Pt/Co3O4 Catalysts for Higher Alcohol Synthesis from CO2 Hydrogenation. Appl. Catal. Gen. 2017, 543, 189–195. [Google Scholar] [CrossRef]
  54. Liu, B.; Ouyang, B.; Zhang, Y.; Lv, K.; Li, Q.; Ding, Y.; Li, J. Effects of Mesoporous Structure and Pt Promoter on the Activity of Co-Based Catalysts in Low-Temperature CO2 Hydrogenation for Higher Alcohol Synthesis. J. Catal. 2018, 366, 91–97. [Google Scholar] [CrossRef]
  55. Wang, L.; He, S.; Wang, L.; Lei, Y.; Meng, X.; Xiao, F.-S. Cobalt–Nickel Catalysts for Selective Hydrogenation of Carbon Dioxide into Ethanol. ACS Catal. 2019, 9, 11335–11340. [Google Scholar] [CrossRef]
  56. Wang, D.; Bi, Q.; Yin, G.; Zhao, W.; Huang, F.; Xie, X.; Jiang, M. Direct Synthesis of Ethanol via CO2 Hydrogenation Using Supported Gold Catalysts. Chem. Commun. 2016, 52, 14226–14229. [Google Scholar] [CrossRef]
  57. Yang, C.; Mu, R.; Wang, G.; Song, J.; Tian, H.; Zhao, Z. J.; Gong, J. Hydroxyl-Mediated Ethanol Selectivity of CO2 Hydrogenation. Chem. Sci. 2019, 10, 3161–3167. [Google Scholar] [CrossRef]
  58. Kusama, H.; Okabe, K.; Arakawa, H. Effect of Ce Additive on CO2 Hydrogenation over Rh/SiO2 Catalysts. J. Jpn. Pet. Inst. 2001, 44, 384–391. [Google Scholar] [CrossRef]
  59. Kusama, H.; Okabe, K.; Sayama, K.; Arakawa, H. Rhodium Catalysts Promoted by Cerium Oxide in the CO2 Hydrogenation to Ethanol. J. Jpn. Pet. Inst. 1999, 42, 178–179. [Google Scholar] [CrossRef]
  60. Izumi, Y.; Kurakata, H.; Aika, K. I. Ethanol Synthesis from Carbon Dioxide on [Rh10Se]/TiO2 Catalyst Characterized by X-Ray Absorption Fine Structure Spectroscopy. J. Catal. 1998, 175, 236–244. [Google Scholar] [CrossRef]
  61. Kusama, H.; Okabe, K.; Sayama, K.; Arakawa, H. CO2 Hydrogenation to Ethanol over Promoted Rh/SiO2 Catalysts. Catal. Today 1996, 28, 261–266. [Google Scholar] [CrossRef]
  62. Guo, W.; Gao, W. G.; Wang, H.; Tian, J. J. Higher Alcohols Synthesis from CO2 Hydrogenation over K2O-Modified CuZnFeZrO2 Catalysts. Adv. Mater. Res. 2013, 827, 20–24. [Google Scholar] [CrossRef]
  63. Zheng, J. N.; An, K.; Wang, J. M.; Li, J.; Liu, Y. Direct Synthesis of Ethanol via CO2 Hydrogenation over the Co/La-Ga-O Composite Oxide Catalyst. J. Fuel Chem. Technol. 2019, 47, 697–708. [Google Scholar] [CrossRef]
  64. Gogate, M. R.; Davis, R. J. Comparative Study of CO and CO2 Hydrogenation over Supported Rh–Fe Catalysts. Catal. Commun. 2010, 11, 901–906. [Google Scholar] [CrossRef]
  65. Guo, H.; Li, S.; Peng, F.; Zhang, H.; Xiong, L.; Huang, C.; Wang, C.; Chen, X. Roles Investigation of Promoters in K/Cu–Zn Catalyst and Higher Alcohols Synthesis from CO2 Hydrogenation over a Novel Two-Stage Bed Catalyst Combination System. Catal. Lett. 2015, 145, 620–630. [Google Scholar] [CrossRef]
  66. Shao, F.; Cheng, J.; Song, X.; Wei, Z.; Zhong, X.; Yao, Z.; Wang, H.; Sun, X.; Li, A.; Wang, J. Effects of Manganese on the Catalytic Performance of CuCo Catalysts for Direct Conversion of CO/CO2 to Higher Alcohols. Dalton Trans. 2023, 52, 461–468. [Google Scholar] [CrossRef]
  67. Ding, L.; Shi, T.; Gu, J.; Cui, Y.; Zhang, Z.; Yang, C.; Chen, T.; Lin, M.; Wang, P.; Xue, N.; Peng, L.; Guo, X.; Zhu, Y.; Chen, Z.; Ding, W. CO2 Hydrogenation to Ethanol over Cu@Na-Beta. Chem 2020, 6, 2673–2689. [Google Scholar] [CrossRef]
  68. Bando, K. K.; Arakawa, H.; Ichikuni, N.; Asakura, K. A Novel Effect of Li Additive: Dynamic Control of Rh Mobility during CO2 Hydrogenation Reaction. In Studies in Surface Science and Catalysis; Corma, A., Melo, F. V., Mendioroz, S., Fierro, J. L. G., Eds.; 12th International Congress on Catalysis; Elsevier, 2000; Vol. 130, pp 3759–3764. [CrossRef]
  69. Takagawa, M.; Okamoto, A.; Fujimura, H.; Izawa, Y.; Arakawa, H. Ethanol Synthesis from Carbon Dioxide and Hydrogen. In Studies in Surface Science and Catalysis; Elsevier, 1998; Vol. 114, pp 525–528. [CrossRef]
  70. An, B.; Li, Z.; Song, Y.; Zhang, J.; Zeng, L.; Wang, C.; Lin, W. Cooperative Copper Centres in a Metal–Organic Framework for Selective Conversion of CO2 to Ethanol. Nat. Catal. 2019, 2, 709–717. [Google Scholar] [CrossRef]
  71. Inui, T.; Yamamoto, T.; Inoue, M.; Hara, H.; Takeguchi, T.; Kim, J. B. Highly Effective Synthesis of Ethanol by CO2-Hydrogenation on Well Balanced Multi-Functional FT-Type Composite Catalysts. Appl. Catal. Gen. 1999, 186, 395–406. [Google Scholar] [CrossRef]
Table 1. An outline of the review article on the topic of heterogeneous catalysts for the synthesis of higher alcohols through CO2 hydrogenation.
Table 1. An outline of the review article on the topic of heterogeneous catalysts for the synthesis of higher alcohols through CO2 hydrogenation.
Chapter title Contents of the chapter
1. Introduction
  • Brief overview of the importance of higher alcohols as renewable energy sources and chemicals
  • Summary of current methods for their synthesis, including CO2 hydrogenation
  • Statement of the research area and the motivation for the review
2. CO2 hydrogenation reaction
  • Description of the CO2 hydrogenation reaction and the products formed
  • Discussion of the challenges associated with the reaction, such as selectivity and stability
3. Heterogeneous catalysts for CO2 hydrogenation
  • Overview of different types of heterogeneous catalysts used for CO2 hydrogenation, such as metals and metal oxides
  • Comparison of the advantages and disadvantages of different catalysts
  • Discussion of the factors that affect catalyst performance, such as composition, crystal structure, and surface properties
4. Case studies
  • Detailed description of specific catalysts and their performance in CO2 hydrogenation
  • Comparison of the results obtained with different catalysts
  • Discussion of the factors that determine the catalyst performance in different conditions
5. Conclusion
  • Summary of the main findings of the review
  • Discussion of the current challenges and opportunities in the field of CO2 hydrogenation
  • Suggestions for future research directions.
Table 2. Comments on the contents of the introduction section.
Table 2. Comments on the contents of the introduction section.
Contents provided by ChatGPT Comments by authors
They can be produced from sustainable resources, such as biomass, and they have a higher energy density than traditional biofuels like ethanol. They can also be blended with gasoline, diesel, or jet fuel, to increase their energy content and reduce emissions. It is incorrect to state that higher alcohols have a higher energy density than ethanol, as ethanol itself is considered a higher alcohol.
The energy density of higher alcohols is higher than that of methanol but lower than that of gasoline, diesel, or jet fuel, so blending cannot increase their energy density [35].
This process can be divided into two main categories: pyrolysis and gasification. Pyrolysis is the thermal decomposition of biomass in the absence of oxygen, while gasification is the partial oxidation of biomass in the presence of oxygen. Gasification of biomass results primarily in the production of syngas, which can be further processed into higher alcohols through the application of heat, pressure, and catalysts. Direct gasification of biomass does not result in the production of higher alcohols [36].
Chemical synthesis. When discussing chemical synthesis methods for the production of higher alcohols, several critical reactions CO hydrogenation [37], ethylene hydration [38], acetic acid hydrogenation [39], and hydroformylation[40] reactions have been overlooked.
Table 3. Comments on the contents of Chapter 2.
Table 3. Comments on the contents of Chapter 2.
Contents provided by ChatGPT Comments by authors
CO2 + H2 → R-OH Stoichiometric number, which is helpful to determine the ratio of reactants in the feed is missing.
The side product, water, which may influence the structure and performance of the catalyst, as well as the equilibrium conversion, is not presented.
This equation, n CO2 + 3n H2 → CnH2n+1OH + (2n − 1) H2O, encompasses all necessary information.
The CO2 hydrogenation process can be divided into two stages: the activation of CO2 and the reduction of CO2 to the desired alcohol. In the first stage, the CO2 is activated by the catalyst, which weakens the C-O bond and allows for the adsorption of CO2 on the catalyst surface. In the second stage, hydrogen is added to the activated CO2, which leads to the formation of the corresponding alcohol. Adsorbed CO2 can react with hydrogen to form the desired products, or it can be dissociated into CO and then react with hydrogenation [41].
Generally, methanol is the major product formed at low temperatures and pressures, while at higher temperatures and pressures, ethanol, propanol, and butanol are formed. At low temperatures and low pressure, the formation of methanol is also difficult, methane is the main product under such conditions [42].
The effects of temperatures and pressures on alcohol formation are complicated. The described trend is inaccurate.
Low conversion rate: CO2 hydrogenation reaction is an endothermic process, which needs high energy input to activate the CO2. As a result, the conversion rate of CO2 to alcohols is relatively low. The hydrogenation of higher alcohol synthesized by CO2 hydrogenation is an exothermic reaction.
The low conversion rate should be ascribed to the high kinetic barrier for higher alcohol formation.
Table 4. Catalysts discussed in Chapter 4.
Table 4. Catalysts discussed in Chapter 4.
Copper-based Nickel-based Cobalt-based Iron-based
Cu-ZnO Ni-ZnO Co-MnO2 Fe-SiO2
Cu-MnO2 Ni-MnO2 Co-ZrO2 Fe-carbon
Cu-ZrO2 Ni-ZrO2 Co-Al2O3 Fe-clay
Cu-Al2O3 Ni-Al2O3 Co-zeolite Fe-zeolite
Cu-zeolite Ni-zeolite Co-graphene Fe-metallic NP
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
bsky
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

Privacy Settings

© 2025 MDPI (Basel, Switzerland) unless otherwise stated