Machine learning approaches for predicting arsenic adsorption from water using porous metal–organic frameworks

Abstract

Arsenic in drinking water is a serious threat for human health due to its toxic nature and therefore, its eliminating is highly necessary. In this study, the ability of different novel and robust machine learning (ML) approaches, including Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting, Gradient Boosting Decision Tree, and Random Forest was implemented to predict the adsorptive removal of arsenate [As(V)] from wastewater over 13 different metal–organic frameworks (MOFs). A large experimental dataset was collected under various conditions. The adsorbent dosage, contact time, initial arsenic concentration, adsorbent surface area, temperature, solution pH, and the presence of anions were considered as input variables, and adsorptive removal of As(V) was selected as the output of the models. The developed models were evaluated using various statistical criteria. The obtained results indicated that the LightGBM model provided the most accurate and reliable response to predict As(V) adsorption by MOFs and possesses R2, RMSE, STD, and AAPRE (%) of 0.9958, 2.0688, 0.0628, and 2.88, respectively. The expected trends of As(V) removal with increasing initial concentration, solution pH, temperature, and coexistence of anions were predicted reasonably by the LightGBM model. Sensitivity analysis revealed that the adsorption process adversely relates to the initial As(V) concentration and directly depends on the MOFs surface area and dosage. This study proves that ML approaches are capable to manage complicated problems with large datasets and can be affordable alternatives for expensive and time-consuming experimental wastewater treatment processes.

Data Driven Discovery of MOFs for Hydrogen Gas Adsorption

“…The LGBM is one popular algorithm based on gradient boosting machine (GBM). It is a highly efficient decision tree, which shows good performance on the predicating CO 2 and arsenic adsorption using an MOF. Compared with the RF model, it may perform better because the LGBM trains the gradient boosting trees in a sequential manner; each tree was trained to correct the errors of the previous tree.…”

Metal-organic frameworks meet Uni-MOF: a revolutionary gas adsorption detector

“…Molecular dynamics (MD) 22,23 , Monte Carlo (MC) 24 and other simulation/calculation methods 25,26 have been applied to provide reference values, but these approaches are computationally expensive and complicated for implementation, limiting their application to large-scale, multi-gas and high-throughput calculations. Moreover, the vast range of operating conditions for gas adsorption further complicates the predictions.Machine learning techniques have demonstrated significant potential in accurately predicting properties of crystalline materials 18,27,28 , reducing the cost of traditional trial-and-error experiments, and eliminating the need for expensive simulations. However, these methods often rely on ad hoc feature engineering based on expert domain knowledge, leading to overfitting and biased performance when using a limited amount of labeled data.…”

“…Machine learning techniques have demonstrated significant potential in accurately predicting properties of crystalline materials 18,27,28 , reducing the cost of traditional trial-and-error experiments, and eliminating the need for expensive simulations. However, these methods often rely on ad hoc feature engineering based on expert domain knowledge, leading to overfitting and biased performance when using a limited amount of labeled data.…”

Metal-organic frameworks meet Uni-MOF: a transformer-based gas adsorption detector

“…Molecular dynamics (MD) 22,23 , Monte Carlo (MC) 24 and other simulation/calculation methods 25,26 have been applied to provide reference values, but these approaches are computationally expensive and complicated for implementation, limiting their application to large-scale, multi-gas and high-throughput calculations. Moreover, the vast range of operating conditions for gas adsorption further complicates the predictions.Machine learning techniques have demonstrated significant potential in accurately predicting properties of crystalline materials [27][28][29] , reducing the cost of traditional trial-and-error experiments, and eliminating the need for expensive simulations. However, these methods often rely on ad hoc feature engineering based on expert domain knowledge, leading to overfitting and biased performance when using a limited amount of labeled data.…”

“…Machine learning techniques have demonstrated significant potential in accurately predicting properties of crystalline materials [27][28][29] , reducing the cost of traditional trial-and-error experiments, and eliminating the need for expensive simulations. However, these methods often rely on ad hoc feature engineering based on expert domain knowledge, leading to overfitting and biased performance when using a limited amount of labeled data.…”