Smart Data-Driven GRU Predictor for SnO$_2$ Thin films Characteristics

TL;DR

The paper tackles the challenge of characterizing crystalline thin films when access to X-ray diffraction data is limited by cost and complexity. It proposes a smart data-driven approach using GRU-based predictors to estimate structural properties (e.g., lattice parameters $a$, $b$, and grain size $D$) of SnO$_2$(110) thin films from experimental cues, within a three-stage data framework that includes data preparation and model validation. The authors detail the XRD foundations (Bragg's law $2 d \sin(\theta) = n \lambda$, tetragonal spacing $1/d^2 = (h^2+k^2)/a^2 + l^2/c^2$, and Scherrer grain-size formula $D = \frac{K \lambda}{\beta \cos(\theta)}$), and implement GRU cells with gates $Z_t$, $R_t$, and $G_t$ to perform regression. Through data augmentation, normalization, and careful hyperparameter tuning (e.g., time steps, layers, and cell counts), the GRU models achieve high fidelity predictions with small $MSE$ and high $R^2$, demonstrating the viability of a data-driven framework for rapid material-property inference. This work potentially reduces experimental burden and accelerates materials discovery by enabling accurate structural predictions from limited diffraction data.

Abstract

In material physics, characterization techniques are foremost crucial for obtaining the materials data regarding the physical properties as well as structural, electronics, magnetic, optic, dielectric, and spectroscopic characteristics. However, for many materials, ensuring availability and safe accessibility is not always easy and fully warranted. Moreover, the use of modeling and simulation techniques need a lot of theoretical knowledge, in addition of being associated to costly computation time and a great complexity deal. Thus, analyzing materials with different techniques for multiple samples simultaneously, still be very challenging for engineers and researchers. It is worth noting that although of being very risky, X-ray diffraction is the well known and widely used characterization technique which gathers data from structural properties of crystalline 1d, 2d or 3d materials. We propose in this paper, a Smart GRU for Gated Recurrent Unit model to forcast structural characteristics or properties of thin films of tin oxide SnO$_2$(110). Indeed, thin films samples are elaborated and managed experimentally and the collected data dictionary is then used to generate an AI -- Artificial Intelligence -- GRU model for the thin films of tin oxide SnO$_2$(110) structural property characterization.

Figures (14)

• Figure 1: AI-Based Materials Characterization Framework.
• Figure 2: XRD Diffraction Scheme.
• Figure 3: X-Ray diffraction patterns of SnO2 thin films obtained by Sol-Gel (Dip Coating) technique. a) ideal pattern of Sno2, b) pur SnO2, c) SnO2 with HCI solution, d) SnO2 with DEA solution, e) SnO2 with acetic acide.
• Figure 4: GRU Cell/Unit Computationxu2020deep.
• Figure 5: GRU-Based Model Implementation