Artificial intelligence simulation of Pb(II) and Cd(II) adsorption using a novel metal organic framework-based nanocomposite adsorbent

Machine-learning-driven discovery of metal-organic framework adsorbents for hexavalent chromium removal from aqueous environments

HYPOTHESIS

Metal-organic frameworks (MOFs) have been widely studied for Cr(VI) adsorption in water. Theoretically, numerous MOFs can be synthesised by assembling diverse metals and ligands. However, the traditional manual experimentation for screening high-performance MOFs is resource-intensive and inefficient.

EXPERIMENTS

A screening strategy for MOFs based on machine learning was proposed for the adsorption and removal of Cr(VI) from water. By collecting the characteristics of MOFs and the experimental parameters of Cr(VI) adsorption from the literature, a dataset was constructed to predict the adsorption performance. Among the six regression models, the model trained by the extreme gradient boosted tree algorithm had the best performance and was used to simulate the adsorption and screen potential high-performance adsorbents.

FINDINGS

Structure-property analysis indicated that prepared MOF adsorbents with properties of 0.37 < largest cavity diameter < 0.71 nm, 0.18 < pore volume < 0.57 cm3/g, 412 < specific surface area < 1588 m2/g, 0.43 < void fraction < 0.62 will achieve enhanced adsorption of Cr(VI) in water. High-performance adsorbents were successfully screened using a combination of machine-learning prediction and analysis. Experiments were conducted to verify the exceptional adsorption capacity of UiO-66 and MOF-801. This method effectively identified adsorbents and accelerated the development of new MOF adsorbents for contaminant removal, providing a novel approach for the discovery of superior adsorbents.

Functional Materials for Water Restoration: A "Fish Cage" for Efficient Capture of Pb(II) Ions

In this work, a "fish cage" material for trapping Pb(II) ions has been successfully obtained, which is a novel clathrate functionalized metal-oganic framework (Cage-MOF) by introducing free adsorption sites (SO42-). The three-dimensional (3D) cage structure of Cage-MOF gives it a larger contact area and can capture "swimming fish" (Pb(II)) like a "fishing cage" in a water solution. This is the first high-efficiency adsorption material obtained by introducing free coordination groups. Cage-MOF not only has excellent water stability but also improves the selectivity and affinity for Pb(II) ions in water because of the presence of sulfate adsorption sites, and its adsorption capacity is as high as 806 mg/g. This work shows a novel and effective idea for the synthesis of water restoration materials.

Modeling, optimization and understanding of adsorption process for pollutant removal via machine learning: Recent progress and future perspectives

It is crucial to reduce the concentration of pollutants in water environment to below safe levels. Some cost-effective pollutant removal technologies have been developed, among which adsorption technology is considered as a promising solution. However, the batch experiments and adsorption isotherms widely employed at present are inefficient and time-consuming to some extent, which limits the development of adsorption technology. As a new research paradigm, machine learning (ML) is expected to innovate traditional adsorption models. This reviews summarized the general workflow of ML and commonly employed ML algorithms for pollutant adsorption. Then, the latest progress of ML for pollutant adsorption was reviewed from the perspective of all-round regulation of adsorption process, including adsorption efficiency, operating conditions and adsorption mechanism. General guidelines of ML for pollutant adsorption were presented. Finally, the existing problems and future perspectives of ML for pollutant adsorption were put forward. We highly expect that this review will promote the application of ML in pollutant adsorption and improve the interpretability of ML.

Applications of soft computing techniques for prediction of pollutant removal by environmentally friendly adsorbents (case study: the nitrate adsorption on modified hydrochar)

Artificial intelligence has emerged as a powerful tool for solving real-world problems in various fields. This study investigates the simulation and prediction of nitrate adsorption from an aqueous solution using modified hydrochar prepared from sugarcane bagasse using an artificial neural network (ANN), support vector machine (SVR), and gene expression programming (GEP). Different parameters, such as the solution pH, adsorbent dosage, contact time, and initial nitrate concentration, were introduced to the models as input variables, and adsorption capacity was the predicted variable. The comparison of artificial intelligence models demonstrated that an ANN with a lower root mean square error (0.001) and higher R² (0.99) value can predict nitrate adsorption onto modified hydrochar of sugarcane bagasse better than other models. In addition, the contact time and initial nitrate concentration revealed a higher correlation between input variables with the adsorption capacity.

Neural-based modeling adsorption capacity of metal organic framework materials with application in wastewater treatment

We developed a computational-based model for simulating adsorption capacity of a novel layered double hydroxide (LDH) and metal organic framework (MOF) nanocomposite in separation of ions including Pb(II) and Cd(II) from aqueous solutions. The simulated adsorbent was a composite of UiO-66-(Zr)-(COOH)2 MOF grown onto the surface of functionalized Ni50-Co50-LDH sheets. This novel adsorbent showed high surface area for adsorption capacity, and was chosen to develop the model for study of ions removal using this adsorbent. A number of measured data was collected and used in the simulations via the artificial intelligence technique. Artificial neural network (ANN) technique was used for simulation of the data in which ion type and initial concentration of the ions in the feed was selected as the input variables to the neural network. The neural network was trained using the input data for simulation of the adsorption capacity. Two hidden layers with activation functions in form of linear and non-linear were designed for the construction of artificial neural network. The model's training and validation revealed high accuracy with statistical parameters of R2 equal to 0.99 for the fitting data. The trained ANN modeling showed that increasing the initial content of Pb(II) and Cd(II) ions led to a significant increment in the adsorption capacity (Qe) and Cd(II) had higher adsorption due to its strong interaction with the adsorbent surface. The neural model indicated superior predictive capability in simulation of the obtained data for removal of Pb(II) and Cd(II) from an aqueous solution.