2018· International Journal of Modern Research in Science & Engineering· 0 citations
Abstract
The discovery of advanced alloys capable of withstanding extreme environmental conditions such as high temperatures, intense radiation, corrosive atmospheres, and mechanical stress is critical for applications in aerospace, nuclear energy, deep-sea exploration, and space missions. Traditional experimental and computational approaches to alloy design are often time-consuming and resource-intensive. Recent advances in artificial intelligence (AI) and machine learning (ML) offer powerful tools to accelerate the discovery process by enabling high-throughput screening, property prediction, and design optimization. This paper presents a comprehensive review and methodology for AI-assisted alloy discovery, focusing on the integration of data-driven models with physical principles, high-fidelity simulations, and experimental validation. We highlight successful case studies, discuss the challenges of data scarcity and model interpretability, and propose a framework for closed-loop design that incorporates generative models and active learning. This AI-driven approach represents a paradigm shift toward faster, more cost-effective discovery of next-generation materials for extreme environments.
The increasing demand for sustainable, high-performance materials has accelerated the adoption of Artificial Intelligence (AI) in materials discovery. Traditional material development relies on time-consuming experiments and computationally intensive simulations, limiting scalability and innovation. AI-driven materials discovery integrates machine learning, deep learning, data analytics, and computational materials science to rapidly predict, optimize, and design advanced materials with improved mechanical, thermal, electrical, and environmental performance. The proposed framework combines data preprocessing, feature engineering, predictive modeling, optimization, and sustainability assessment to identify materials that satisfy both engineering and environmental requirements. Advanced algorithms, including Random Forest, Support Vector Machines, Neural Networks, and Gradient Boosting, accurately predict material properties, while generative AI enables inverse design of novel, recyclable, and energy-efficient materials. Sustainability metrics such as life-cycle assessment and carbon footprint guide multi-objective optimization. Despite challenges in data quality and validation, emerging technologies including federated learning, physics-informed neural networks, digital twins, and autonomous laboratories are expected to further advance AI-enabled sustainable materials discovery for Industry 5.0 and resource-efficient engineering.
Iyengar P.K· International Journal of Mod...· 0 citations
The rapid advancement of autonomous materials research requires data-efficient frameworks that can integrate artificial intelligence (AI) with experimental knowledge and human intuition. In the context of sodium-ion batteries (SIBs), where compositional and processing complexity spans an immense design space, conventional high-throughput experiments still face bottlenecks in data utilization and decision-making efficiency. To address this challenge, we developed an AI-guided, uncertainty-aware workflow that couples high-throughput synthesis and characterization [1-3] with machine learning (ML) surrogate modeling and probabilistic deep learning.
Specifically, we established Monte Carlo (MC) Dropout–based multilayer perceptron (MLP) models to predict key electrochemical metrics such as initial capacity and long-term retention from high-dimensional descriptors encompassing composition, structure, and processing features. The MC-MLP provides not only accurate property predictions but also calibrated uncertainty estimates that quantify model confidence and guide active learning. These models are integrated with gradient boosting regression (GBR) surrogate mappings that link intermediate feature spaces to improve physical interpretability and reduce data sparsity. Tail-focused loss functions and temperature-balanced sampling further enhance sensitivity toward high-performance outliers, accelerating the identification of promising chemistries within limited datasets. By combining these ML strategies with automated synthesis and characterization workflows, we demonstrate an iterative human-AI loop: experimental data continuously refines the surrogate landscape, while uncertainty-driven candidate selection prioritizes new experiments. This approach achieved >3× improvement in data efficiency and enabled Pareto-optimized discovery of Na–Ni–Mn–based layered cathodes with enhanced air stability and electrochemical performance.
Moreover, the framework is transferable across chemical systems, synthesis conditions, and multidimensional battery characterization data, enabling mechanistic understanding and accelerated discovery of novel electrode materials. Overall, this work highlights how integrating MC-Dropout deep learning, surrogate modeling, and domain knowledge from real lab-generated data can transform high-throughput experimentation into a self-improving, autonomous discovery framework—paving the way toward truly intelligent, data-efficient materials research.
References
[1] Jia, Shipeng, et al. "High-throughput design of Na–Fe–Mn–O cathodes for Na-ion batteries." Journal of Materials Chemistry A 10.1 (2022): 251-265.
[2] Jia, Shipeng, et al. "Chemical speed dating: the impact of 52 dopants in Na–Mn–O cathodes." Chemistry of Materials 34.24 (2022): 11047-11061.
[3] Jia, Shipeng, et al. "Stabilization of Na‐Ion Cathode Surfaces: Combinatorial Experiments with Insights from Machine Learning Models." Advanced Energy and Sustainability Research (2024): 2400051
Shipeng Jia, I. Abate· ECS Meeting Abstracts· 0 citations
The incorporation of artificial intelligence (AI) into energy systems has become a transformative strategy for tackling global energy related challenges, particularly energy vulnerability (EVI). This work examines how AI contributes to mitigating EVI by evaluating its influence across several dimensions, including energy availability, operational efficiency, consumption patterns, renewable energy integration, and overall energy security. Based on insights derived from machine learning (ML) enabled developments in catalytic materials and CO2 capture technologies, this study demonstrates how data-centric approaches expedite material discovery, refine energy processes, and strengthen system resilience. ML methodologies, including artificial neural networks (ANN), support vector regression (SVR), and ensemble learning techniques, exhibit strong predictive performance in estimating activation energies, adsorption properties, and catalytic efficiencies. These methods substantially decrease reliance on computationally intensive density functional theory (DFT) simulations, thereby enabling rapid identification of high-performance catalyst. Moreover, ML-assisted framework supports the detection of active catalytic sites, these optimization of electrocatalytic processes, and the design of materials for hydrogen evolution, CO2 reduction, and ammonia synthesis. Simultaneously, ML applications in CO2 capture systems particularly in metal-organic frameworks (MOFs) facilitate high throughput screening and predictive evaluation of adsorption capacity and structural behaviour. Through the application of quantitative structure-property relationships and feature importance analyses, ML models identify key variables governing CO2 capture performance, thus lowering computational demands and accelerating material development. The study highlights the rise of integrated, closed-loop systems that combine ML, theoretically modelling, and automated experimentation to streamline catalyst development and carbon capture process. Collectively, the results indicate that AI-driven methodologies substantially improve the efficiency, sustainability, and scalability of advanced energy technologies. These developments not only help mitigate energy vulnerability but also promote the global shift toward low-carbon, resilient energy systems.
Sai Kumar Punna, Suvarshitha Pusuluru, Madhumita Ravikumar et al.· Frontiers in Chemistry· 1 citation
Artificial intelligence (AI) has emerged as a fruitful tool in materials science, enabling accelerated discovery, characterization, and optimization of functional materials. Among ferroelectrics, fluorite‐doped hafnium oxide attracts exceptional attention due to its CMOS compatibility, scalability, and robust ferroelectricity at a few nanometers in thickness. However, understanding and optimizing the relationships between metastable ferroelectric phase formation and property‐processing remain challenging due to the multidimensional parameter space governing its synthesis and performance. This review examines how AI methodologies, ranging from machine learning‐assisted first‐principles simulations to deep‐learning analysis of experimental data, are reshaping the study of HfO
2
‐based ferroelectrics. While such approaches have advanced understanding of structure‐property relationships, AI‐driven synthesis process optimization, and closed‐loop synthesis remain underexplored. We outline current achievements, identify critical gaps, and propose next steps that integrate multimodal data fusion, active learning, and combinatorial synthesis to enable predictive design and autonomous optimization of next‐generation hafnia‐based ferroelectrics.
Faizan Ali, D. Lehninger, F. Sánchez et al.· Advanced Electronic Material...· 0 citations
The design and optimization of heterogeneous functional materials for energy conversion and storage devices is a complex challenge that requires a deep understanding of material properties across multiple scales. Recent advancements in artificial intelligence (AI) and computational simulations are providing new avenues for designing these materials with unprecedented precision and performance. This presentation will explore the integration of AI-driven methods and advanced simulation techniques to accelerate the development of high-performance heterogeneous functional materials. AI-based approaches, including machine learning algorithms and optimization techniques, are increasingly used to analyze vast datasets from material properties, design strategies, and experimental results to identify new material combinations and predict their behavior in electrochemical applications.
I will highlight novel AI-driven models that can predict the emergent properties of materials. Additionally, I will discuss the integration of simulation techniques like molecular dynamics, density functional theory (DFT), and continuum modeling to simulate the behavior of materials at different length scales, from atomic to macro. These simulations, when coupled with AI-driven optimization algorithms, enable the design of materials that enhance performance and efficiency in energy conversion and storage applications.
I will conclude by discussing the future directions of AI and simulation integration in the design of heterogeneous functional materials, focusing on their potential to enable the development of next-generation devices with high efficiency, scalability, and durability.
This work will present the current work on inverse material design, where AI methods—particularly generative pretrained transformers—are used to predict new material candidates based on desired properties, pushing the boundaries of materials innovation.
I. Gonzales, R. Ullberg, Andrew H Salij et al.· ECS Meeting Abstracts· 0 citations