Molecular-fingerprint machine-learning-assisted design and prediction for high-performance MOFs for capture of NMHCs from air

N-doped graphene for electrocatalytic O2 and CO2 reduction

“…102 Theoretically, machine learning is a powerful strategy to almost exhaustively screen the NG with various N species and predict the desirable NG electrocatalyst. [103][104][105][106] The combination of high-throughput screening of big data with purposeful experiments would open a new avenue for the development of NG used as electrocatalysts.…”

Multifunctional Fe3O4/TiO2/NH2–UiO–66 with integrated interfacial features for favorable phosphate adsorption

“…NH 2 -UiO-66, one of the metal-organic framework (MOF) materials, is composed of a Zr 4+ node and an organic ligand. It possesses a large specific surface area (S BET ), 22,23 high thermal stability (thermal decomposition temperature is greater than 540 1C), 24,25 resistance to extreme pH environments, several metal sites, regular pores, and adjustable pore size making it play an irreplaceable role in the field of adsorption, especially in the adsorption of phosphate. [26][27][28] In our previous work, NH 2 -UiO-66 adsorbent loaded with cerium dioxide was prepared, which showed efficient adsorption capacity for phosphate.…”

Multi-Scale Computer-Aided Design of Covalent Organic Frameworks for CO2 Capture in Wet Flue Gas

“…21−30 The machine-learningobtained useful information can contribute to design materials in a more effective way. For example, Qiao and co-workers 28 combined machine learning and molecular fingerprint to identify the excellent bits (aromatic rings, double bonds, transition metals, halogens, and oxygen heterocycles) that could promote the non-methane hydrocarbon capture performance of MOFs. Instead of counting the common characteristics that may benefit the property, Boyd et al 12 used data mining to directly search for the water-resistant CO 2 adsorption sites (named adsorbaphores), from the top-ranked 8325 MOFs.…”