Transition-Metal Interlink Neural Network: Machine Learning of 2D Metal–Organic Frameworks with High Magnetic Anisotropy

Abstract

metal−organic framework (MOF) materials with large perpendicular magnetic anisotropy energy (MAE) are important candidates for high-density magnetic storage. The MAE-targeted high-throughput screening of 2D MOFs is currently limited by the time-consuming electronic structure calculations. In this study, a machine learning model, namely, transition-metal interlink neural network (TMINN) based on a database with 1440 2D MOF materials is developed to quickly and accurately predict MAE. The welltrained TMINN model for MAE successfully captures the general correlation between the geometrical configurations and the MAEs. We explore the MAEs of 2583 other 2D MOFs using our trained TMINN model. From these two databases, we obtain 11 unreported 2D ferromagnetic MOFs with MAEs over 35 meV/atom, which are further demonstrated by the high-level density functional theory calculations. Such results show good performance of the extrapolation predictions of TMINN. We also propose some simple design rules to acquire 2D MOFs with large MAEs by building a Pearson correlation coefficient map between various geometrical descriptors and MAE. Our developed TMINN model provides a powerful tool for high-throughput screening and intentional design of 2D magnetic MOFs with large MAE.

Advancements in High‐Throughput Screening and Machine Learning Design for 2D Ferromagnetism: A Comprehensive Review

“…A transition‐metal interlink neural network (TMINN) has been developed by Wang et al, which utilizing a database of 1440 2D MOF materials, to enable rapid and accurate prediction of MAE (see Figure (a)). [ 129 ] Additionally, they explore the MAEs of 2583 other 2D MOFs using the trained TMINN model. By utilizing these two datasets, they identify 11 previously unreported 2DFM MOFs with MAEs exceeding 35 meV atom −1 .…”

“…A transition-metal interlink neural network (TMINN) has been developed by Wang et al, which utilizing a database of 1440 2D MOF materials, to enable rapid and accurate prediction of MAE (see Figure 12(a)). [129] Understanding spin textures in magnetic systems is of utmost importance in the field of spintronics, bridging the gap between theoretical models and experimental observations. Extrapolating magnetic Hamiltonian parameters from experimentally determined spin configurations provides a valuable complementary link.…”

Giant magnetic anisotropy of adatoms on the graphane surface

“…[11][12][13][14][15][16][17][18][19][20][21] Thus far, magnetic properties with obvious magnetic anisotropy have been experimentally reported, e.g., Fe and Mn atoms on a CuN surface, 22 Co and Fe atoms on a Pd and Rh (111) surface, 23 Co atoms on MgO, 11,12 Pt (111) 14 and graphene surfaces, 24 Fe atoms on MgO (100) thin film, 25 and bimetallic nanoislands grown on fcc (111) metal surfaces. 26 Moreover, a series of magnetic metal atoms on various substrates (graphene, [27][28][29][30][31] metal oxides, pure metal surfaces, [32][33][34] transition metal dichalcogenides, [35][36][37] two dimensional organic framework, 38,39 etc.) have been theoretically predicted to have large MAE.…”

Understanding the Magnetic Microstructure through Experiments and Machine Learning Algorithms

“…In this paper, we are going to address the application of the convolutional neural network (CNN) to understand the modifications of magnetic domains in a perpendicularly magnetized multilayer, which has been observed experimentally by using ion-beam irradiation. Of late, advanced machine learning techniques have acquired immense importance in interdisciplinary research, such as in microstructure optimization, prediction of a magnetic field, phase transition, magnetic grain size study, modeling magnetic domains, , relation between different magnetic chiral states, prediction of effective magnetic spin configurations, , 2D metal–organic frameworks with high magnetic anisotropy, and different components of Hamiltonian including the Dzyaloshinskii–Moriya interaction (DMI), using different deep learning and machine learning methods. From the point of view of atomistic magnetism, researchers , have tried to estimate and analyze various components of Hamiltonian, such as exchange constant, anisotropy constant, and DMI, using different CNNs .…”