Machine learning analysis of gas phase photocatalytic CO2 reduction for hydrogen production

Saadetnejad, Dilara; Oral, Burcu; Can, Elif; Yıldırım, Ramazan

doi:10.1016/j.ijhydene.2022.02.030

Cited by 19 publications

(9 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[98] In addition, models have also been built based on literature data for establishing trends and connections for products, catalysts, and material properties for CO 2 photocatalysis in both the gas and liquid phases. [99] Traditionally, most ML models have been "data-driven", meaning that the connection between input and output is established based solely on statistical fitting of the dataset provided. With these data-driven statistical models, there are often challenges with interpretability, [100][101][102] in that it typically decreases when model accuracy increases.…”

Section: A Way Forwardmentioning

confidence: 99%

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

Loh,

Wang,

Mohan

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Although solar fuels photocatalysis offers the promise of converting carbon dioxide directly with sunlight as commercially scalable solutions have remained elusive over the past few decades, despite significant advancements in photocatalysis band‐gap engineering and atomic site activity. The primary challenge lies not in the discovery of new catalyst materials, which are abundant, but in overcoming the bottlenecks related to material‐photoreactor synergy. These factors include achieving photogeneration and charge‐carrier recombination at reactive sites, utilizing high mass transfer efficiency supports, maximizing solar collection, and achieving uniform light distribution within a reactor. Addressing this multi‐dimensional problem necessitates harnessing machine learning techniques to analyze real‐world data from photoreactors and material properties. In this perspective, the challenges are outlined associated with each bottleneck factor, review relevant data analysis studies, and assess the requirements for developing a comprehensive solution that can unlock the full potential of solar fuels photocatalysis technology. Physics‐informed machine learning (or Physics Neural Networks) may be the key to advancing this important area from disparate data towards optimal reactor solutions.

show abstract

Section: A Way Forwardmentioning

confidence: 99%

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

Loh,

Wang,

Mohan

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…CFD would provide flow patterns, radiation and chemical species distributions and reactor performance (see figure 13(b)). In this respect, by evaluating new designs with the proper instrumentation and data acquisition, large databases could become available, for ML applications [129,130]. ML (i.e.…”

Section: Computational Fluid Dynamics (Cfd) and Machine Learning (Ml)mentioning

confidence: 99%

2023 roadmap on photocatalytic water splitting

et al. 2023

View full text Add to dashboard Cite

As a consequence of the issues resulting from global climate change many nations are starting to transition to being low or net zero carbon economies. To achieve this objective practical alternative fuels are urgently required and hydrogen gas is deemed one of the most desirable substitute fuels to traditional hydrocarbons. A significant challenge, however, is obtaining hydrogen from sources with low or zero carbon footprint i.e. so called “green” hydrogen. Consequently, there are a number of strands of research into processes that are practical techniques for the production of this “green” hydrogen. Over the past five decades there has been a significant body of research into photocatalytic/photoelectrocatalytic processes for hydrogen production through water splitting or water reduction. There have, however been significant issues faced in terms of the practical capability of this promising technology to produce hydrogen at scale. This road map article explores a range of issues related to both photocatalytic and photoelectrocatalytic hydrogen generation ranging from basic processes, materials science through to reactor engineering and applications for biomass reforming.

show abstract

“…This was followed by a prediction, the overall accuracy of which was only 78% due to the limitation of the amount of data. In 2022, Saadetnejad et al 76 sorted out 549 pieces of data on photocatalytic carbon dioxide reduction reactions from 80 experimental studies, and constructed a predictive model with an accuracy of more than 80%. However, they pointed out that the weakness of the predictive model may have been due to ambiguity and a lack of data.…”

Section: Machine Learningmentioning

confidence: 99%

“…The light time and surface area play important roles in decomposition. In 2022, Saadetnejad et al 76 extracted 549 data points (268 for gases and 281 for liquids) from published papers on carbon dioxide photoreduction, including titanium dioxide, C 3 N 4 , cadmium sulfide, and gold. The band gap of a photocatalyst was found to be successfully predicted by the RF algorithm with an MSE of 0.15, and the DT algorithm was found to be more suitable for the prediction of the total gas production rate with an accuracy of about 80%.…”

Section: Applicationmentioning

confidence: 99%

Methods, progresses, and opportunities of materials informatics

Li,

Zheng

2023

InfoMat

View full text Add to dashboard Cite

As an implementation tool of data intensive scientific research methods, machine learning (ML) can effectively shorten the research and development (R&D) cycle of new materials by half or even more. ML shows great potential in the combination with other scientific research technologies, especially in the processing and classification of large amounts of material data from theoretical calculation and experimental characterization. It is very important to systematically understand the research ideas of material informatics to accelerate the exploration of new materials. Here, we provide a comprehensive introduction to the most commonly used ML modeling methods in material informatics with classic cases. Then, we review the latest progresses of prediction models, which focus on new processing–structure–properties–performance (PSPP) relationships in some popular material systems, such as perovskites, catalysts, alloys, two‐dimensional materials, and polymers. In addition, we summarize the recent pioneering researches in innovation of material research technology, such as inverse design, ML interatomic potentials, and microtopography characterization assistance, as new research directions of material informatics. Finally, we comprehensively provide the most significant challenges and outlooks related to the future innovation and development in the field of material informatics. This review provides a critical and concise appraisal for the applications of material informatics, and a systematic and coherent guidance for material scientists to choose modeling methods based on required materials and technologies.

show abstract

Machine learning analysis of gas phase photocatalytic CO2 reduction for hydrogen production

Cited by 19 publications

References 55 publications

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

2023 roadmap on photocatalytic water splitting

Methods, progresses, and opportunities of materials informatics

Contact Info

Product

Resources

About