Benchmarking chemical neural ordinary differential equations to obtain reaction network-constrained kinetic models from spectroscopic data

Puliyanda, Anjana; Srinivasan, Karthik K.; Li, Zukui; Prasad, Vinay

doi:10.1016/j.engappai.2023.106690

Cited by 3 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The thermodynamic feasibility of certain pathways under the process conditions can be computed to exclude unfavorable ones. Our other studies involve the estimation of kinetic parameters for the reactions and extending them toward control and monitoring of the process …”

Section: Discussionmentioning

confidence: 99%

“… Analyses performed in our other works indicate that the results of the deconvolution are influenced by the amount of noise present in the spectroscopic measurement. Though not a theoretical limitation, this does pose a practical limitation on the validity of the deconvolution for samples with low signal-to-noise ratios. The type of spectroscopic measurement provided to the system affects the expanse of the networks generated.…”

Section: Limitationsmentioning

confidence: 94%

See 1 more Smart Citation

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

Srinivasan,

Puliyanda,

Prasad

2024

J. Phys. Chem. A

Self Cite

View full text Add to dashboard Cite

In this work, we detail an automated reaction network hypothesis generation protocol for processes involving complex feedstocks where information about the species and reactions involved is unknown. Our methodology is process agnostic and can be utilized in any reactive process with spectroscopic measurements that provide information on the evolution of the components in the mixture. We decompose the mixture spectra to obtain spectroscopic signatures of the individual components and use a 1-D convolutional neural network to automatically identify functional groups indicated by them. We employ atom−atom mapping to automatically recover reaction rules that are applied on candidate molecules identified from chemistry databases through fingerprint similarity. The method is tested on synthetic data and on spectroscopic measurements of lab-scale batch hydrothermal liquefaction (HTL) of biomass to determine the accuracy of prediction across datasets of varying complexities. Our methodology is able to identify reaction network hypotheses containing reaction networks close to the ground truth in the case of synthetic data, and we are also able to recover candidate molecules and reaction networks close to the ones reported in the previous literature studies for biomass pyrolysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Limitationsmentioning

confidence: 94%

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

Srinivasan,

Puliyanda,

Prasad

2024

J. Phys. Chem. A

Self Cite

View full text Add to dashboard Cite

show abstract

“…Derivatives of non-integer order can therefore provide a more thorough definition of memory and inherited characteristics. Here, for some significance use of said derivatives, a thorough introduction, background material, and core findings were looked at in we refer to [5][6][7][8]. The full spectrum of a function is presented via the derivatives of real or complex orders.…”

Section: Introductionmentioning

confidence: 99%

On complex fractal-fractional order mathematical modeling of CO ₂ emanations from energy sector

Shah,

Abdeljawad

2023

Phys. Scr.

View full text Add to dashboard Cite

This research work is devoted to undertake a mathematical model for emissions of carbon dioxide (CO 2) from energy sector using the concept of fractals-fractional differential (FFD) operator. Here, it should be kept in mind that as the population is expanding, so the need of energy increasing day by day. Burning fossil fuels accounts for a sizable amount of the world’s energy production, which increases the concentration of CO 2 in the atmosphere and causes the global warming. It’s critical to reduce CO 2 emissions from the energy industry. Therefore, via the use of FFD operator, we investigate a mathematical model which is addressing the mentioned process. We deduce some qualitative results regarding the existence of such models in real life using mathematical analysis. The aforesaid analysis is based on some fixed points approaches. Additionally, some analysis devoted to stability is also derived for the proposed model. In addition, a numerical algorithms based on modified Euler method is constructed to simulate the results graphically.

show abstract

Fuzzy fractional generalized Bagley–Torvik equation with fuzzy Caputo gH-differentiability

Muhammad,

Akram

2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Benchmarking chemical neural ordinary differential equations to obtain reaction network-constrained kinetic models from spectroscopic data

Cited by 3 publications

References 36 publications

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

On complex fractal-fractional order mathematical modeling of CO ₂ emanations from energy sector

Fuzzy fractional generalized Bagley–Torvik equation with fuzzy Caputo gH-differentiability

Contact Info

Product

Resources

About

Benchmarking chemical neural ordinary differential equations to obtain reaction network-constrained kinetic models from spectroscopic data

Cited by 3 publications

References 36 publications

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

Identification of Reaction Network Hypotheses for Complex Feedstocks from Spectroscopic Measurements with Minimal Human Intervention

On complex fractal-fractional order mathematical modeling of CO 2 emanations from energy sector

Fuzzy fractional generalized Bagley–Torvik equation with fuzzy Caputo gH-differentiability

Contact Info

Product

Resources

About

On complex fractal-fractional order mathematical modeling of CO ₂ emanations from energy sector