GSGaurav Singh

Gaurav Singh

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

Gaurav Singh has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Framework for Visual-Mathematical Literacy in Applied Machine Learning: Why Representation Choices Shape What Models Can Learn

    by Gaurav Singh, Rahul Singh Dhari

    Machine learning (ML) is increasingly applied to physical and engineering systems, yet the translation of physical phenomena into model inputs has received limited systematic scrutiny. The upstream decisions that determine what the model can learn and how its outputs should be interpreted are typically treated as implementation details, but they embed inductive bias in the model. A review of 28 applied ML studies from materials, mechanics and computational materials science (2007–2025) found that all reported basic representation parameters, but only 21% systematically compared alternative representations; the pattern is indicative of a structural rather than merely incidental gap, with the transparency deficit persisting within the most mature and comparison-friendly class (CNN image pipelines). To address this gap, the paper introduces visual-mathematical literacy: a framework for reasoning about and evaluating representation choices, drawing on representation learning, inductive bias analysis, physics-informed ML, and design epistemology. A case study in auxetic metamaterial classification is developed in two phases: a retrospective analysis of six representation decisions across a three-stage pipeline, and a prospective audit executing each of the ten protocol questions end-to-end against a reproduction of the pipeline, showing which decisions the protocol corroborates, refines, and opens. The paper concludes with a protocol of ten audit questions paired with quantitative diagnostics.

  • Open Access

    TECHNO-ECONOMIC PATHWAYS MODELING AND NONLINEAR OPTIMIZED SEEA-ROI LONGITUDINAL DYNAMIC SIMULATION FOR DECARBONIZING AUSTRALIAN HEAVY TRANSPORTATION SYSTEMS

    by Gaurav Singh, Elizabeth Chang, Yeli̇z Karaca

    Techno-economic analysis resting on nonlinear systems theory provides a robust framework for decarbonizing commercial and public fleets. Standard linear models fail to capture the feedback loops, threshold effects and phase transitions inherent in freight electrification, minor perturbations may cascade into system-wide regime shifts. Accordingly, this study embeds five nonlinear mechanisms: Wright’s Law cost learning, logistic grid decarbonization, experience-curve hydrogen price decline, an electrification–grid feedback loop and tipping-point detection, within a techno-economic and optimized simulation for Australian heavy long-haul freight, which accounts for approximately 22% of transport emissions. The model provides three principal outputs, which are the identification of a sequencing problem for green hydrogen deployment, quantification of a persistent emissions–economics inversion across the scenario space and provision of a time-indexed decision framework that maps transition year, Heavy Fleet choice, technology scenario to ROI and cumulative emissions, which aims at serving as a quantitative procurement guide for operator capital planning across the 2025–2035 time period. In addition, the model evaluates cumulative lifecycle emissions, total cost of ownership and return on investment relative to diesel across 270 scenarios over a 25-year horizon, using SEEA-aligned Australian emission factors, NREL ATB 2024 vehicle costs and DCCEEW grid projections. Under nonlinear dynamics with Mid technology assumptions and a 10-year operating lifetime from 2025, battery-electric vehicles deliver emissions approximately 62% below diesel (ROI [ ]108% nonlinear versus [ ]96% linear) with Wright’s Law reducing the cost premium by AUD 33k; fuel-cell vehicles on gray hydrogen achieve ROI [ ]329% nonlinear with emissions 14% below diesel; and diesel hybrid recovers its capital premium within the first operating year. Fuel-cell vehicles on green hydrogen amplify emissions to 49% above diesel under a 2025 transition, a sequencing problem resolving later than linear projections suggest. Sensitivity analysis confirms diesel price, electricity price and annual utilization as dominant economic sensitivities, while the emissions–economics inversion is robust across all tested ranges. Tipping-point analysis identifies crossover years, providing a critical decision-support tool for fleet transitions aligned with Net Zero 2050. The novelty of this paper lies in the integration of the nonlinear SEEA-aligned Australian emission factors with fleet transition ROI analysis across multiple technology learning pathways and transition timing scenarios, which is an integration and model scheme which has been established and implemented in the Australian heavy freight context from longitudinal dynamic dimensions.


  • Automated detection of deformation mechanisms in re-entrant honeycomb auxetics using machine learning

    by Gaurav Singh, Rahul Singh Dhari, Zia Javanbakht

    The intricate geometrical configuration of an auxetic structure enables high energy dissipation capacity at the expense of a highly nonlinear mechanical response. Under external stimuli, complicated deformation mechanisms emerge which dictate the extent of energy dissipation. Recently, the new ‘plastic hinge tracing’ method (Dhari et al., 2021) was introduced to detect such deformation mechanisms for elastoplastic porous materials. This approach is however subjective and cumbersome since it requires monitoring several plastic regions in consecutive deformed configurations. The present study innovatively extends this method by implementing machine learning (ML) techniques for objective detection of deformation modes in auxetics. To this end, a logistic regression ML model was developed to classify the deformation modes of a re-entrant honeycomb structure. The proposed procedure could successfully detect four out of the six deformation modes (‘X’, distorted ‘X’, ‘V’, and ‘V + Z + V’) using the training datasets generated by the finite element analysis and image labels created by K-means clustering algorithm. The success of the proposed automated approach lays the foundation for identifying the deformation mechanisms of other auxetics and porous materials with plastic deformations.