Failure‐Experiment‐Supported Optimization of Poorly Reproducible Synthetic Conditions for Novel Lanthanide Metal‐Organic Frameworks with Two‐Dimensional Secondary Building Units**

Abstract

Novel metal-organic frameworks containing lanthanide double-layer-based secondary building units (KGF-3) were synthesized by using machine learning (ML). Isolating pure KGF-3 was challenging, and the synthesis was not reproducible because impurity phases were frequently obtained under the same synthetic conditions. Thus, dominant factors for the synthesis of KGF-3 were identified, and its synthetic conditions were optimized by using two ML techniques. Cluster analysis was used to classify the obtained powder X-ray diffractometry patterns of the products and thus automatically determine whether the experiments were successful. Decision-tree analysis was used to visualize the experimental results, after extracting factors that mainly affected the synthetic reproducibility. Water-adsorption isotherms revealed that KGF-3 possesses unique hydrophilic pores. Impedance measurements demonstrated good proton conductivities (σ = 5.2 × 10 À 4 S cm À 1 for KGF-3(Y)) at a high temperature (363 K) and relative humidity of 95 % RH.

Phase Control in the Modulated Self‐Assembly of Lanthanide MOFs of a Flexible Tetratopic Bis‐Amide Linker

“…The flexible coordination chemistry of the lanthanides means controlling Ln(III) MOF syntheses to reproducibly prepare the same, phase pure material is challenging. [11] Subtle modifications to synthetic conditions, such as changes in solvent, temperature, pH and starting material ratios, therefore present an opportunity to synthesise many new structures. [12] Modulation, the purposeful addition of a compound to influence the crystallinity, particle size, morphology and/or the phase of the resulting MOF, [13] has been shown to exert phase control in MOFs linked by trivalent metals such as Al(III), [14] Fe(III), [15] and Cr(III), [16] but has not been widely investigated in the synthesis of Ln(III) MOFs, with examples limited to morphological control.…”

“…The flexible coordination chemistry of the lanthanides means controlling Ln(III) MOF syntheses to reproducibly prepare the same, phase pure material is challenging [11] . Subtle modifications to synthetic conditions, such as changes in solvent, temperature, pH and starting material ratios, therefore present an opportunity to synthesise many new structures [12] .…”

Data-driven efficient synthetic exploration of anionic lanthanide-based metal–organic frameworks

“…In our previous work, we used a machine-learning technique to successfully optimize the synthetic conditions for novel Ln-MOFs with poor synthetic reproducibility. 26 Establishing a database of the synthetic conditions for reported Ln-MOFs would make it possible to reveal the bias of previously investigated synthetic conditions. Synthesis experiments focusing on experimental conditions that have not been reported previously would improve the possibility of discovering new Ln-MOFs.…”

“…Consequently, we used cluster analysis to automatically classify the PXRD patterns, 29 as this approach has been found to be capable of automatic classification with high accuracy in previous studies. 26,30 Clustering analysis involves grouping based on similarity between samples. This analysis successfully classified the obtained PXRD patterns into eight groups (clusters) (Fig.…”

“…In addition, the experimental results were visualized by decision tree learning, which is an easily interpretable visualization method for experimental results. 19,25,26,30,31 Each group of PXRD patterns classified by the cluster analysis was used as an objective variable, and various experimental parameters were used as explanatory variables. The decision tree analysis results (Fig.…”