Transition of electrochemical measurement to machine learning in the perspective of two-dimensional materials

Abstract

Two-dimensional materials (e.g. graphene, and transition metal dichalcogenides) have become ubiquitous in electrochemical contexts including energy storage, electrocatalyst, and ion-selective membranes. This is due to its superior electrochemical properties, specifically “capacitance”, which can be referred to the storage ions at the electrolyte/materials interfaces. Experimental work and computational chemistry were carried out in the past decade for solving and improving the understanding of two-dimensional materials; however, these techniques are relatively expensive, complex, and time-consuming. Therefore, we accentuate the future trend of two-dimensional material study with machine learning as the modest alternative. In this perspective, the intrinsic capacitance properties of the two dimension materials were described from an atomic level, explaining the heteroatom doping to a nanoscopic level, showing (basal vs edge capacitance). The studies also extended to the macroscopic level i.e., the flake size of the two-dimensional materials. We then shed more light on the applicability of machine learning coupled with the “fundamental measurement” for solving electrochemistry of two-dimensional materials. The shallow artificial neural network was demonstrated for the prediction of CV curves using the data from size-dependent graphene. In addition, the application of deep neural networks with complicated architecture has also been explored through the prediction of capacitance for heteroatom-doped graphene. This perspective provides a clear background and creates the connection between fundamental measurement and machine learning for understanding the capacitance properties of two-dimensional materials.

Unlocking the Full Potential of Heteroatom-Doped Graphene-Based Supercapacitors through Stacking Models and SHAP-Guided Optimization

“…The data were collected from multiple literature and compiled into a CSV file (available in Supporting Information .CSV and their source in Table S1), with references to the sources provided ,,,− ,− and our previous work. , The collected information includes parameters such as SA, DG, percentage of nitrogen dopant (% N), oxygen dopant (% O), sulfur dopant (% S), current density (CD), electrolyte concentration (CONC), and CAP. In the case of missing data (e.g., DG), the K -Nearest Neighbors imputation (KNN imputation) will be used to fill in the gaps.…”

“…Knowing the optimal doping condition is crucial to enhance the capacitive properties of graphene-based supercapacitors and can reduce experimental time, this could be done by employing data analysis and machine learning. 18,19 This approach can avoid the random synthesis procedure, which results in a randomly doped content without knowing the final CAP properties. Hence, the understanding of graphene doping can be done within a single click instead of performing a traditional synthesis method, which require almost a week.…”

“…Hence, it is essential to investigate the underlying factors that influence supercapacitor CAP, such as SA, doping contents including oxygen, sulfur, and nitrogen, as well as the defect ratio (DG). Knowing the optimal doping condition is crucial to enhance the capacitive properties of graphene-based supercapacitors and can reduce experimental time, this could be done by employing data analysis and machine learning. , This approach can avoid the random synthesis procedure, which results in a randomly doped content without knowing the final CAP properties. Hence, the understanding of graphene doping can be done within a single click instead of performing a traditional synthesis method, which require almost a week. ,, By utilizing the vast experimental data available in the literature, ,,,− the optimum doping condition can be determined to avoid trial-and-error doping and achieve superior CAP.…”

Ultrahigh stable laminar graphene membranes for effective ionic and molecular nanofiltration with a machine learning-assisted study

“…The shallow neural network consisted of three layers, i.e., input layers, hidden layers, and output layers. 39 The signal transmitted through each node can be divided into two parts: (i) the edge which was the real number at the connected site between nodes and (ii) the output of each node was computed by a non-linear transfer function, the hyperbolic tangent sigmoid function in this work, based on the sum of inputs. The calculation of this transfer function is equivalent to the hyperbolic tangent function; however, the calculation speed will be much faster.…”

“…36,37,55 they have attracted substantial attention from various research areas due to their effectiveness and modesty in computational cost, especially the shallow neural network. 39 For example, ANNs have been previously used to evaluate the permeability decline in a permeable reactive barrier for a groundwater treatment method, at which the network consists of a single input layer, a hidden layer, and an output layer. 37 The ANN method can also be used to effectively determine the permeability of a reservoir rock, capable of predicting the permeability values in the incomplete permeability wells.…”