Machine Learning-Assisted Design of Thin-Film Composite Membranes for Solvent Recovery.

Organic solvents are extensively utilized in industries as raw materials, reaction media, and cleaning agents. It is crucial to efficiently recover solvents for environmental protection and sustainable manufacturing. Recently, organic solvent nanofiltration (OSN) has emerged as an energy-efficient membrane technology for solvent recovery; however, current OSN membranes are largely fabricated by trial-and-error methods. In this study, for the first time, we develop a machine learning (ML) approach to design new thin-film composite membranes for solvent recovery. The monomers used in interfacial polymerization, along with membrane, solvent and solute properties, are featurized to train ML models via gradient boosting regression. The ML models demonstrate high accuracy in predicting OSN performance including solvent permeance and solute rejection. Subsequently, 167 new membranes are designed from 40 monomers and their OSN performance is predicted by the ML models for common solvents (methanol, acetone, dimethylformamide, and n-hexane). New top-performing membranes are identified with methanol permeance superior to that of existing membranes. Particularly, nitrogen-containing heterocyclic monomers are found to enhance microporosity and contribute to higher permeance. Finally, one new membrane is experimentally synthesized and tested to validate the ML predictions. Based on the chemical structures of monomers, the ML approach developed here provides a bottom-up strategy toward the rational design of new membranes for high-performance solvent recovery and many other technologically important applications.

One-step uranium extraction and brine desalination via adsorptive pervaporation by graphene-oxide scaffold membranes.

The ocean reserves nearly four billion tons of uranium, providing an inexhaustible supply of nuclear energy if the limits of ultralow U(VI) concentration (3.3 µg·L-1) are addressed. Membrane technology is promising to make this happen by simultaneous U(VI) concentration and extraction. Herein, we report a pioneering adsorption-pervaporation membrane for efficient enrichment and capture of U(VI) along with clean water production. A bifunctional poly(dopamine-ethylenediamine) and graphene oxide 2D scaffold membrane was developed and further crosslinked by glutaraldehyde, capable of recovering over 70% U(VI) and water from simulated seawater brine, which validates the feasibility of one-step water recovery, brine concentration, and uranium extraction from seawater brine. Moreover, compared with other membranes and adsorbents, this membrane exhibits fast pervaporation desalination (flux: 153.3 kg·m-2·h-1, rejection: >99.99%) and excellent uranium capture properties of 228.6 mg·m-2 benefiting from plentiful functional groups provided by embedded poly(dopamine-ethylenediamine). This study aims to provide a strategy for recovering critical elements from the ocean.

The development of novel Nexar block copolymer/Ultem composite membranes for C2-C4 alcohols dehydration via pervaporation.

Novel composite membranes comprising sulfonated styrenic Nexar pentablock copolymers were developed by dip-coating on poly(ether imide) hollow fibers for pervaporation dehydration of C2-C4 alcohols. The advantages of using block copolymers as the selective layer are (1) their effectiveness to synergize the physicochemical properties of different chemical and structural moieties and (2) tunable nanoscale morphology and nanostructure via molecular engineering. To achieve high-performance composite membranes, the effects of coating time, ion exchange capacity (IEC) of the copolymer, and solvent systems for coating were investigated. It is revealed that a minimum coating time of 30 s is needed for the formation of a continuous and less-defective top layer. A higher IEC value results in a membrane with a higher flux and lower separation factor because of enhanced hydrophilicity and stretched chain conformation. Moreover, the composite membranes prepared from hexane/ethanol mixtures show higher separation factors and lower fluxes than those from the hexane solvent owing to microdomain segregation induced by ethanol and a smooth and dense top selective layer. These hypotheses were verified by atomic force microscopy and positron annihilation spectroscopy. The newly developed composite membranes demonstrate impressive separation performance with fluxes exceeding 2 kg/m(2) h and separation factors more than 200 for isopropyl alcohol and n-butanol dehydration from 85/15 wt % alcohol/water feed mixtures at 50 °C.