Deep Mining Stable and Nontoxic Hybrid Organic-Inorganic Perovskites for Photovoltaics via Progressive Machine Learning

Revealing the role of local octahedral distortions in hybrid halide perovskites through physical-informed data-driven machine learning

Data-driven material designs often encounter challenges from small and imbalanced datasets. The complex structural and physicochemical properties of hybrid halide perovskites, coupled with these limitations, create obstacles for performing feature engineering and extracting key fingerprints. Herein, we employed a physical-informed data-driven modeling approach to identify lattice geometric fingerprints, such as the distortion index (DI) and effective coordination number (ECoN), and to establish a robust structure-property relationship mapping the electronic bandgap, resulting in improved model performance. Lattice compression simulations across multiple phases of MAPbI3 further confirmed a strong correlation between DI and ECoN with the electronic bandgap, validating the robustness of the selected octahedra geometrical fingerprints. By adjusting the s-p antibonding coupling, the pressure-driven reduction in local octahedral distortion, induced by the anisotropic hydrogen bonding between the inorganic framework and organic cation, narrows the electronic bandgap and facilitates the p-p transitions, thereby boosting the transition dipole moment and band-edge absorption. Combining data mining with physical analysis, we have successfully clarified the significant impact of lattice geometry on the electronic properties and identified key octahedral geometric fingerprints for effectively describing the electronic bandgap, while also revealing the microphysical mechanisms of local octahedral distortion on the optoelectronic properties of hybrid halide perovskites.

Strategic Integration of Machine Learning in the Design of Excellent Hybrid Perovskite Solar Cells

The photoelectric conversion efficiency (PCE) of perovskites remains beneath the Shockley-Queisser limit, despite its significant potential for solar cell applications. The present focus is on investigating potential multicomponent perovskite candidates, particularly on the application of machine learning to expedite band gap screening. To efficiently identify high-performance perovskites, we utilized a data set of 1346 hybrid organic-inorganic perovskites and employed 11 machine learning models, including decision trees, convolutional neural networks (CNNs), and graph neural networks (GNNs). Four descriptors were utilized for high-throughput screening: sine matrix, Ewald sum matrix, atom-centered symmetry functions (ACSF), and many-body tensor representation (MBTR). The results indicated that LightGBM and CatBoost somewhat surpassed XGBoost in decision tree models, but random forests lagged. Among the CNN models utilizing the same four descriptors, CustomCNN and VGG16 surpassed Xception, while EfficientNetV2B0 exhibited the least favorable performance. When the sine matrix and Ewald sum matrix served as adjacency matrices in GNN models, GCSConv exhibited a considerable improvement over GATConv and a slight advantage over GCNConv. Significantly, GCSConv outperformed other models when utilized with the Ewald sum matrix. The ideal combination of descriptors and algorithms identified was MBTR + CustomCNN, with an R2 of 0.94. Subsequently, three perovskites exhibiting appropriate Heyd-Scuseria-Ernzerhof (HSE06) band gaps were identified to define the defects. Among them, CH3C(NH2)2SnI3 exhibited superior performance in both vacancy and substitutional defects compared to C3H8NSnI3 and (CH3)2NH2SnI3. This high-throughput screening method with machine learning establishes a robust foundation for selecting solar materials with exceptional photoelectric properties.

Machine Learning for Experimental Reactivity of a Set of Metal Clusters toward C-H Activation

Understanding the mechanisms of C-H activation of alkanes is a very important research topic. The reactions of metal clusters with alkanes have been extensively studied to reveal the electronic features governing C-H activation, while the experimental cluster reactivity was qualitatively interpreted case by case in the literature. Herein, we prepared and mass-selected over 100 rhodium-based clusters (RhxVyOz- and RhxCoyOz-) to react with light alkanes, enabling the determination of reaction rate constants spanning six orders of magnitude. A satisfactory model being able to quantitatively describe the rate data in terms of multiple cluster electronic features (average electron occupancy of valence s orbitals, the minimum natural charge on the metal atom, cluster polarizability, and energy gap involved in the agostic interaction) has been constructed through a machine learning approach. This study demonstrates that the general mechanisms governing the very important process of C-H activation by diverse metal centers can be discovered by interpreting experimental data with artificial intelligence.

Prediction of Organic-Inorganic Hybrid Perovskite Band Gap by Multiple Machine Learning Algorithms

As an indicator of the optical characteristics of perovskite materials, the band gap is a crucial parameter that impacts the functionality of a wide range of optoelectronic devices. Obtaining the band gap of a material via a labor-intensive, time-consuming, and inefficient high-throughput calculation based on first principles is possible. However, it does not yield the most accurate results. Machine learning techniques emerge as a viable and effective substitute for conventional approaches in band gap prediction. This paper collected 201 pieces of data through the literature and open-source databases. By separating the features related to bits A, B, and X, a dataset of 1208 pieces of data containing 30 feature descriptors was established. The dataset underwent preprocessing, and the Pearson correlation coefficient method was employed to eliminate non-essential features as a subset of features. The band gap was predicted using the GBR algorithm, the random forest algorithm, the LightGBM algorithm, and the XGBoost algorithm, in that order, to construct a prediction model for organic-inorganic hybrid perovskites. The outcomes demonstrate that the XGBoost algorithm yielded an MAE value of 0.0901, an MSE value of 0.0173, and an R2 value of 0.991310. These values suggest that, compared to the other two models, the XGBoost model exhibits the lowest prediction error, suggesting that the input features may better fit the prediction model. Finally, analysis of the XGBoost-based prediction model's prediction results using the SHAP model interpretation method reveals that the occupancy rate of the A-position ion has the greatest impact on the prediction of the band gap and has an A-negative correlation with the prediction results of the band gap. The findings provide valuable insights into the relationship between the prediction of band gaps and significant characteristics of organic-inorganic hybrid perovskites.

Can Lead-Free Double Halide Perovskites Serve as Proper Photovoltaic Absorber?

The emerging Pb-free double perovskites (DPs) are acknowledged as the most potential nontoxic alternatives to lead halide perovskites for thin-film photovoltaics, yet their photophysical properties significantly lag behind expectations. To tackle this issue, it is imperative to conduct a systematic investigation of the structure and optoelectronic properties and to sift through vast chemical space to extract new types of Pb-free DPs with exceptional optoelectronic characteristics and thermal stability. Through high-throughput first-principal calculations, we demonstrate that apart from a select few Pb-free DPs (e.g., Cs2InSbCl6 and Cs2TlBiBr6), other categories, even with suitable direct electronic bandgaps, exhibit inferior optical absorption due to the inversion symmetry-induced parity-forbidden transitions. The mismatch between the electronic and optical bandgap, thence, casts doubt on the reliability of the electronic bandgap as a criterion for Pb-free DPs in various optoelectronics. The assessed limited thermostability under operational conditions, however, hinders any Pb-free DPs from effectively serving as photovoltaic absorbers. Alongside the compositional engineering discussed above, the prospect of manipulating local-site symmetry and disrupting the parity forbidden transitions in stabilized Pb-free DPs through materials engineering should be recognized as a pivotal and rational avenue toward achieving high performance.

Simple Structural Descriptor Obtained from Symbolic Classification for Predicting the Oxygen Vacancy Defect Formation of Perovskites

Symbolic classification is an approach of interpretable machine learning for building mathematical formulas that fit certain data sets. In this work, symbolic classification is used to establish the relationship between oxygen vacancy defect formation energy and structural features. We find a structural descriptor n_a(r_a/E_na - r_b), where n_a is the valence of the a-site ion, r_a is the radius of the a-site ion, E_na is the electronegativity of the a-site ion, and r_b is the radius of the b-site ion. It accelerates the screening of defect-free oxide perovskites in advance of density functional theory (DFT) calculations and experimental characterization. Our results demonstrate the potential of symbolic classification for accelerating the data-driven design and discovery of materials with improved properties.

Investigation of Opto-Electronic Properties and Stability of Mixed-Cation Mixed-Halide Perovskite Materials with Machine-Learning Implementation

The feasibility of mixed-cation mixed-halogen perovskites of formula AxA’1−xPbXyX’zX”3−y−z is analyzed from the perspective of structural stability, opto-electronic properties and possible degradation mechanisms. Using density functional theory (DFT) calculations aided by machine-learning (ML) methods, the structurally stable compositions are further evaluated for the highest absorption and optimal stability. Here, the role of the halogen mixtures is demonstrated in tuning the contrasting trends of optical absorption and stability. Similarly, binary organic cation mixtures are found to significantly influence the degradation, while they have a lesser, but still visible effect on the opto-electronic properties. The combined framework of high-throughput calculations and ML techniques such as the linear regression methods, random forests and artificial neural networks offers the necessary grounds for an efficient exploration of multi-dimensional compositional spaces.

Artificial Intelligence in Chemistry: Current Trends and Future Directions

The application of artificial intelligence (AI) to chemistry has grown tremendously in recent years. In this Review, we studied the growth and distribution of AI-related chemistry publications in the last two decades using the CAS Content Collection. The volume of both journal and patent publications have increased dramatically, especially since 2015. Study of the distribution of publications over various chemistry research areas revealed that analytical chemistry and biochemistry are integrating AI to the greatest extent and with the highest growth rates. We also investigated trends in interdisciplinary research and identified frequently occurring combinations of research areas in publications. Furthermore, topic analyses were conducted for journal and patent publications to illustrate emerging associations of AI with certain chemistry research topics. Notable publications in various chemistry disciplines were then evaluated and presented to highlight emerging use cases. Finally, the occurrence of different classes of substances and their roles in AI-related chemistry research were quantified, further detailing the popularity of AI adoption in the life sciences and analytical chemistry. In summary, this Review offers a broad overview of how AI has progressed in various fields of chemistry and aims to provide an understanding of its future directions.