Random Forest Algorithm-Based Prediction of Solvation Gibbs Energies

Liao, Meiping; Wu, Feng; Yu, Xinliang; Zhao, Ling; Wu, Hongxun; Zhou, Jian

doi:10.1007/s10953-023-01247-6

Cited by 5 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, most of these models do not provide explanations for their statistical forecasts, reinforcing the "black-box" nature of machine learning-based predictions. Previous models, except for Low et al [38], which still employ quantum mechanics calculations, fail to elucidate the physical significance of each prediction [39].…”

Section: Related Workmentioning

confidence: 99%

Evaluation of Explainable Deep Learning Models in Predicting Hydrogen Production

Ukwuoma,

Cai,

Ukwuoma

et al. 2024

Preprint

View full text Add to dashboard Cite

To meet the difficulties of the current energy environment, hydrogen has enormous potential as a clean and sustainable energy source. Utilizing hydrogen's potential requires accurate hydrogen production prediction. Due to its capacity to identify intricate patterns in data, Machine learning alongside deep learning models has attracted considerable interest from a variety of industries, including the energy industry. These algorithms are inherently black boxes, which makes it difficult to comprehend and interpret their predictions, particularly in important sectors like hydrogen generation. First, this study conducted an extensive experiment using 4 machine learning regression models and a novel deep learning model based on Keras API for hydrogen production prediction based on the co-gasification of biomass and plastics datasets. Secondly, this study investigates the application of explainable AI models including Shapley Additive Explanation (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), and Explain Like I'm Five (ELi5) in predicting hydrogen production. We explore the significance of these models in providing insights into the underlying mechanisms and factors influencing hydrogen production processes hence improving our understanding of the relationships between input factors and hydrogen production outputs. This will allow for better-informed decision-making and process optimization in the energy industry. Our results demonstrate the interpretability and transparency of these models, highlighting their potential to raise the accuracy and dependability of forecasts of hydrogen generation. These models provide a useful resource for stakeholders to make informed decisions and enhance the use of hydrogen as a sustainable energy source by bridging the gap between predicted accuracy and interpretability.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation of Explainable Deep Learning Models in Predicting Hydrogen Production

Ukwuoma,

Cai,

Ukwuoma

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…50,51 With the exception of Low et al 33 (while still using QM calculations), previous models fail to describe the physical meaning behind each prediction. 52 This work aims precisely to tackle these three issues. We present a supervised ML model to predict ΔG sol from a wide array of experimental results.…”

Section: Introductionmentioning

confidence: 99%

“…Second, data availability jeopardizes model development, as great detail in experimental data for Δ G sol limits models to specific free energy determinations, relinquishing important arrays of aqueous or organic solvents. Finally, most of these models lack explanatory arguments for their statistical predictions, enhancing the “black-box” mantra of ML-based predictions. , With the exception of Low et al (while still using QM calculations), previous models fail to describe the physical meaning behind each prediction …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Supervised Machine Learning Model To Predict Solvation Gibbs Energy

Ferraz-Caetano,

Teixeira,

Cordeiro

2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Many challenges persist in developing accurate computational models for predicting solvation free energy (ΔG sol). Despite recent developments in Machine Learning (ML) methodologies that outperformed traditional quantum mechanical models, several issues remain concerning explanatory insights for broad chemical predictions with an acceptable speed–accuracy trade-off. To overcome this, we present a novel supervised ML model to predict the ΔG sol for an array of solvent–solute pairs. Using two different ensemble regressor algorithms, we made fast and accurate property predictions using open-source chemical features, encoding complex electronic, structural, and surface area descriptors for every solvent and solute. By integrating molecular properties and chemical interaction features, we have analyzed individual descriptor importance and optimized our model though explanatory information form feature groups. On aqueous and organic solvent databases, ML models revealed the predictive relevance of solutes with increasing polar surface area and decreasing polarizability, yielding better results than state-of-the-art benchmark Neural Network methods (without complex quantum mechanical or molecular dynamic simulations). Both algorithms successfully outperformed previous ΔG sol predictions methods, with a maximum absolute error of 0.22 ± 0.02 kcal mol–1, further validated in an external benchmark database and with solvent hold-out tests. With these explanatory and statistical insights, they allow a thoughtful application of this method for predicting other thermodynamic properties, stressing the relevance of ML modeling for further complex computational chemistry problems.

show abstract

Calculation of Solute Partition Coefficient Using the A-P Scheme

Yu,

Zhang

2024

J Solution Chem

View full text Add to dashboard Cite

Random Forest Algorithm-Based Prediction of Solvation Gibbs Energies

Cited by 5 publications

References 34 publications

Evaluation of Explainable Deep Learning Models in Predicting Hydrogen Production

Evaluation of Explainable Deep Learning Models in Predicting Hydrogen Production

Explainable Supervised Machine Learning Model To Predict Solvation Gibbs Energy

Calculation of Solute Partition Coefficient Using the A-P Scheme

Contact Info

Product

Resources

About