A framework for controllable Pareto front learning with completed scalarization functions and its applications

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time.

Arsenate removal by layered double hydroxides embedded into spherical polymer beads: Batch and column studies

In this study, the performance of poly(layered double hydroxides) [poly(LDHs)] beads as an adsorbent for arsenate removal from aqueous solution was investigated. The poly(LDHs) beads were prepared by immobilizing LDHs into spherical alginate/polyvinyl alcohol (PVA)-glutaraldehyde beads (spherical polymer beads). Batch adsorption studies were conducted to assess the effect of contact time, solution pH, initial arsenate concentrations and co-existing anions on arsenate removal performance. The potential reuse of these poly(LDHs) beads was also investigated. Approximately 79.1 to 91.2% of arsenic was removed from an arsenate solution (50 mg As L(-1)) by poly(LDHs). The adsorption data were well described by the pseudo-second-order kinetics model and the Langmuir isotherm model, and the adsorption capacities of these poly(LDHs) beads at pH 8 were from 1.64 to 1.73 mg As g(-1), as calculated from the Langmuir adsorption isotherm. The adsorption ability of the poly(LDHs) beads decreased by approximately 5-6% after 5 adsorption-desorption cycles. Phosphates markedly decreased arsenate removal. The effect of co-existing anions on the adsorption capacity declined in the following order: HPO4 (2-) >> HCO3 (-) > SO4 (2-) > Cl(-). A fixed-bed column study was conducted with real-life arsenic-containing water. The breakthrough time was found to be from 7 to 10 h. Under optimized conditions, the poly(LDHs) removed more than 82% of total arsenic. The results obtained in this study will be useful for further extending the adsorbents to the field scale or for designing pilot plants in future studies. From the viewpoint of environmental friendliness, the poly(LDHs) beads are a potential cost-effective adsorbent for arsenate removal in water treatment.