ABAnurag Bajpai

Anurag Bajpai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Anurag Bajpai has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Coupled influence of structural relaxation and compositional complexity on deformation behavior and intermittent plasticity in Cu-Zr-based metallic glasses

    by Anurag Bajpai, Jaemin Wang, Barak Ratzker, Rebeca Miyar, Hendrik Holz, Nilesh P. Gurao, Krishanu Biswas, Dierk Raabe

  • Open Access

    Attention-enhanced variational learning for physically informed discovery of exceptionally hard multicomponent bulk metallic glasses

    by Anurag Bajpai, Jaemin Wang, Barak Ratzker, Bilgehan Murat ŞeșEn, Florian Kark, Dierk Raabe

    The discovery of high-performance multicomponent alloys is constrained by the vastness of composition space and the scarcity of experimentally validated data. We develop VIBANN, a variational information bottleneck-augmented attention-based neural network framework, for uncertainty-aware inverse design of exceptionally hard bulk multicomponent metallic glasses. The model learns chemically structured latent representations of alloy composition and indentation load to search the candidate space under constraints of chemical plausibility, novelty, and predictive uncertainty. Guided by this framework, we synthesize five B-Nb-Fe-W-Co/Hf/Ru/Zr-rich bulk multicomponent metallic glasses. All alloys form fully amorphous rods of 2 mm diameter and reach Vickers hardness values of about 2450 HV, among the highest reported for bulk metallic glasses under comparable conditions. Latent space analysis, attribution trends, and molecular dynamics-based atomistic simulations show that exceptional hardness in this compositional space arises from dense atomic packing, boron-enriched short-range environments and refractory-stabilized local rigidity. Together, we show that uncertainty-aware latent space learning can discover bulk metallic glasses that combine amorphous structure with exceptionally high hardness under limited data conditions.


  • Open Access

    Physics‐Constrained Constitutive Learning of Rate‐Limiting Timescales for Efficient Hydrogen‐Based Direct Reduction for Green Steel Making

    by Anurag Bajpai, Barak Ratzker, Pasquale Cavaliere, Dierk Raabe

    Hydrogen‐based direct‐reduction enables carbon‐neutral primary ironmaking, yet widespread industrial adoption is constrained by sluggish late‐stage kinetics, which lower production efficiency and increase energy and hydrogen consumption. Here, we develop a conversion‐resolved constitutive framework that infers effective reaction and transport timescales directly from measured reduction trajectories and maps their constitutive dependence on operating conditions, pellet architecture, and composition. The scientifically constrained additive model (SCAM) framework is then used to convert these trajectory‐inferred timescales into interpretable constitutive maps, symbolic laws, and regime boundaries across variations in processing conditions and pellet microstructure/composition. We find that internal diffusion accounts for most of the incremental reduction time at intermediate to high conversion percentages, and the reaction‐to‐diffusion control boundary shifts systematically with conversion progression and evolving porous microstructure. Temperature and hydrogen partial pressure mainly accelerate early‐stage conversion rates, whereas the late‐stage conversion rates are governed by the pellet‐to‐pore length scale, average porosity, and tortuosity. Pellet composition primarily affects the late‐stage diffusion‐controlled regime through its influence on pore‐morphology descriptors, while a residual effect persists in the reaction‐controlled regime. The resulting regime maps and symbolic laws yield experimentally anchored pellet‐scale constitutive relations to identify reduction‐stage‐specific rate‐limitations and guide industrial pellet design, thereby providing actionable guidelines for more efficient green steelmaking.

  • Open Access

    Compositional complexity buffers free-volume sensitivity and serrated flow in metallic glasses

    by Anurag Bajpai, Jaemin Wang, Dierk Raabe

    Processing history imprints metallic glasses (MGs), yet whether compositional complexity desensitizes structure and mechanics to quench rate remains unresolved. We use large-scale molecular dynamics along a controlled Cu-Zr complexity ladder, Cu 50 Zr 50 , Cu 47.5 Zr 47.5 Al 5 , and Cu 45 Zr 45 Al 5 Ti 5 , vitrified over 10 11 –10 15 K·s −1 and probed by spherical nanoindentation. Additionally, composition-resolved Cu x Zr 100− x sweep ( x = 40–65 at.%) and a microalloying series Cu 50- z /2 Zr 50- z /2 Al z , ( z = 1–5 at.%) disentangle configurational entropy-driven effects from enthalpic and structural covariates. Atomic free volume is obtained from radical-Voronoi tessellation; non-affine rearrangements are quantified by Falk–Langer $${D}_{\min }^{2}$$ D min 2 field and clustered in three dimensions. Three quantitative descriptors capture the dispersion of free volume and its quench rate sensitivity as a function of compositional complexity. Increasing compositional complexity narrows free-volume distributions across quench rates and systematically reduces the fast-slow disparity. A two-axis reconciliation emerges: within binary Cu-Zr, configurational entropy peaks near equiatomic and minimizes rate sensitivity, whereas across alloy families (binary→ternary→quaternary), increased species diversity and size/enthalpy mismatch further suppress sensitivity. Structure-property co-variation is consistent: at fixed rate, hardness, modulus and elastic recovery increase, while serration density, STZ number density, and plastic-zone volume decrease. Radial-distribution metrics and indentation-induced icosahedral losses corroborate enhanced short/medium-range stability. Compositional complexity thus provides a quantitative lever for processing-tolerant, high-performance Cu-Zr-based MGs.


  • Open Access

    Attention-Enhanced Variational Learning for Physically Informed Design of Ultra-hard Multicomponent Metallic Glasses

    by Dierk Raabe, Anurag Bajpai

    The discovery of ultra-hard multicomponent metallic glasses (MMGs) remains challenging due to the vast compositional complexity and the absence of physically grounded inverse design frameworks. Here, we present VIBANN—a novel AI-driven approach that synergistically combines Variational Information Bottleneck with Attention based Neural Networks, enabling interpretable and uncertainty-aware design of MMGs with record-level hardness. VIBANN compresses composition–mechanical load inputs into a disentangled latent space that captures chemically meaningful structure–property relationships, while attention layers identify critical elemental contributors to hardness. We integrate Monte Carlo dropout for calibrated uncertainty estimation and use Gaussian Mixture Models with latent-space gradient optimization to generate new alloy compositions autonomously. Experimental validation of five inverse-designed B–Co–Fe–Re–W–(Ni/Cr/V) glasses predicted by VIBANN yields bulk amorphous alloys with Vickers hardness exceeding 2200 HV, surpassing most known MMGs. SHAP analysis and latent traversals further expose smooth, interpretable hardness design directions, revealing compositional pathways with equivalent performance. In essence, VIBANN establishes a fully autonomous, interpretable, and experimentally validated inverse design loop, bridging deep learning with metallurgical insight and setting a new benchmark in data-driven alloy design.


  • Emerging Sustainable Waste Management Technologies

    by Anurag Bajpai

    The present chapter thoroughly examines emerging and innovative sustainable approaches aimed at effectively managing diverse technological waste streams. The discourse commences with scrutinising the fundamental tenets of sustainable waste management, subsequently delving into sophisticated methodologies pertaining to distinct technological waste categories. The scientific ideas behind these strategies are explicated, and empirical case studies illustrate their efficacy. The chapter further examines several nascent technologies and strategies employed in technological waste management, emphasising their capacity to fundamentally transform waste management practices. Moreover, the discussion explores several cutting-edge physico-chemical methodologies, such as bio and plasma remediation and nanotechnology, which provide novel strategies for waste management. In a nutshell, the chapter offers a comprehensive examination of the dynamic field of technological waste management, with a particular focus on sustainable and ecologically conscious approaches to address the complexities associated with technological waste and its various streams.


  • Technological Waste Management

    by Anurag Bajpai

    This chapter presents a thorough examination of technological waste management, with a particular focus on the significance of including waste management hierarchies to ensure responsible waste processing. The chapter moreover addresses the technical complexities associated with the management of several forms of technological waste, including mining waste, electronic waste, plastics, and nuclear waste. Material scientists play a pivotal role in tackling these difficulties by employing new and advanced scientific methodologies with the objective of enhancing waste stability, recovery, and recycling efficiency. The chapter emphasises the importance of maintaining a careful equilibrium between the protection of the environment and the advancement of technical waste management. This necessitates taking into account several aspects, such as indigenous rights, traditional knowledge, and the difficulties associated with adhering to global standards and regulatory frameworks. The chapter highlights the complex relationship between scientific advancements, the responsible management of the environment, and the regulatory systems that influence the handling of technological waste in our present-day society.

  • Beneficiation and Management of Technological Waste

    by Anurag Bajpai, Arunabh Meshram, Krishanu Biswas

    This book focuses on the present and future trends, technologies, as well as regulations for the reduction, reuse, and recycling of technological waste globally from the perspective of environmental, social, and economic elements of the different connected systems. It also analyses specific technological waste producing materials and product streams in-depth and investigates the future of technological waste and its management considering better end-of-lifecycle designs, legislation, and sustainability perspectives. Key Features: Provides comprehensive review of beneficiation and management of technological waste. Discusses sustainability in waste management and beneficiation. Covers current practices, policies, and solutions governing the existing supply of discarded or waste technological products and by-products. Reviews material-centric waste disposal and beneficiation Includes case studies from industry on technological waste generation and handling. This book is aimed at graduate students and researchers in materials science and engineering, extractive metallurgy, and sustainable and environmental engineering.


  • Categorisation of Technological Waste

    by Anurag Bajpai

    The dependence of the contemporary era on technology has resulted in severe environmental and health issues, including the introduction of a new type of waste known as “Technological waste.” This chapter investigates the essential topic of technological waste categorisation, addressing the critical need for integrated waste classification and management solutions. It evaluates the various types of technological waste, their perilous effects on the ecosystem and humans, as well as their categorisation, focusing on source-based classification. The worldwide picture depicts frightening levels of illegally disposed electronic, metallurgical, radioactive, and chemical waste, resulting in environmental damage and health dangers from dangerous chemicals. Implementing rigorous classification can help governments and industry develop focused regulations and processes for safe and sustainable waste management, as well as investigate resource recovery methods. Society may maximise constrained resources and encourage environmentally conscious habits by taking a systematic approach to waste management.


  • Open Access

    Active learning strategies for the design of sustainable alloys

    by Ziyuan Rao, Anurag Bajpai, Hongbin Zhang

    Active learning comprises machine learning-based approaches that integrate surrogate model inference, exploitation and exploration strategies with active experimental feedback into a closed-loop framework. This approach aims at describing and predicting specific material properties, without requiring lengthy, expensive or repetitive experiments. Recently, active learning has shown potential as an approach for the design of sustainable materials, such as scrap-compatible alloys, and for enhancing the longevity of metallic materials. However, in-depth investigations into suited best-practice strategies of active learning for sustainable materials science are still scarce. This study aims to present and discuss active learning strategies for developing and improving sustainable alloys, addressing single-objective and multi-objective learning and modelling scenarios. As model cases, we discuss active learning strategies for optimizing Invar and magnetic alloys, representing single-objective scenarios, and more general steel design approaches, exemplifying multi-objective optimization. We discuss the significance of finding the right balance between exploitation and exploration strategies in active learning and suggest strategies to reduce the number of iterations across diverse scenarios. This kind of research aims to find metrics for a more effective application of active learning and is used here to advance the field of sustainable alloy design. This article is part of the discussion meeting issue ‘Sustainable metals: science and systems’.