Abhinav Gupta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abhinav Gupta has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Usha Chouhan
Maulana Azad National Institute of Technology
3 shared publications Usha Chouhan
2 shared publicationsPragati Saraswat
1 shared publication- Rajat Kaushik
Regional Institute of Education, NCERT
1 shared publication Shanki Lawatre
1 shared publication- Sonu Kurmi
Maulana Azad National Institute of Technology (MANIT)
1 shared publication
Latest Publications
- 17 November 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (46) , 465204
AlphaNet7: a multi-head physics-informed neural network for latent parameter discovery in variable-order fractional systems
Solving high-dimensional inverse problems in variable-order fractional dynamical systems from sparse observations remains a major challenge in scientific machine learning. Standard physics-informed neural networks (PINNs) rely on soft residual penalties, which frequently induce gradient pathologies or encounter conservation discrepancies when applied to non-local fractional operators. To address this limitation, we propose AlphaNet7, a constrained multi-head PINN architecture for the simultaneous inverse identification of compartment-specific, time-varying fractional orders and transmission dynamics. The proposed architecture combines a shared feature-extraction backbone with eight independent prediction heads, jointly inferring multiple latent quantities while implicitly integrating the governing phenomenological equations through a custom autograd-compatible piecewise differentiable explicit fractional forward solver. AlphaNet7 is applied to a seven-compartment nonlinear epidemiological system governed by the non-singular Caputo–Fabrizio fractional operator. From two macroscopic surveillance streams, the network estimates a regularization-guided, constraint-dependent set of seven phenomenological effective fractional orders rather than genuine biological memory parameters. In the reference run, inferred compartment orders span α ≈ 0.688 – 0.864 (mean α ― ≈ 0.753 ), whereas a single-head global-order model achieves identical reconstruction error ( RMSE = 0.0028 ) and removing the diversity penalty contracts compartment means to between 0.740 and 0.774 ( RMSE = 0.0021 ). Under regularization-guided optimization, the multi-head model captures non-linear transitions in exposure and recovery alongside quasi-stationary institutional plateaus; this alignment reflects post hoc temporal coincidence with policy shifts rather than causality. Furthermore, the inferred regime yields a modest reduction of roughly 2 % – 3 % ( 1.38 → 1.35 ) in the definition-driven, phenomenological fractional reproduction metric. Because the explicit solver numerically constrains trajectories to the discretized governing dynamics, AlphaNet7 outperforms fixed-order baselines in calibration and out-of-sample forecasting, reducing forecast error by 30.2 % – 63.1 % across rolling hold-out splits under unified normalization. This provides a prior-constrained framework for effective parameter estimation in variable-order fractional systems.
- 17 November 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (46) , 465204
AlphaNet7: a multi-head physics-informed neural network for latent parameter discovery in variable-order fractional systems
Solving high-dimensional inverse problems in variable-order fractional dynamical systems from sparse observations remains a major challenge in scientific machine learning. Standard physics-informed neural networks (PINNs) rely on soft residual penalties, which frequently induce gradient pathologies or encounter conservation discrepancies when applied to non-local fractional operators. To address this limitation, we propose AlphaNet7, a constrained multi-head PINN architecture for the simultaneous inverse identification of compartment-specific, time-varying fractional orders and transmission dynamics. The proposed architecture combines a shared feature-extraction backbone with eight independent prediction heads, jointly inferring multiple latent quantities while implicitly integrating the governing phenomenological equations through a custom autograd-compatible piecewise differentiable explicit fractional forward solver. AlphaNet7 is applied to a seven-compartment nonlinear epidemiological system governed by the non-singular Caputo–Fabrizio fractional operator. From two macroscopic surveillance streams, the network estimates a regularization-guided, constraint-dependent set of seven phenomenological effective fractional orders rather than genuine biological memory parameters. In the reference run, inferred compartment orders span α ≈ 0.688 – 0.864 (mean α ― ≈ 0.753 ), whereas a single-head global-order model achieves identical reconstruction error ( RMSE = 0.0028 ) and removing the diversity penalty contracts compartment means to between 0.740 and 0.774 ( RMSE = 0.0021 ). Under regularization-guided optimization, the multi-head model captures non-linear transitions in exposure and recovery alongside quasi-stationary institutional plateaus; this alignment reflects post hoc temporal coincidence with policy shifts rather than causality. Furthermore, the inferred regime yields a modest reduction of roughly 2 % – 3 % ( 1.38 → 1.35 ) in the definition-driven, phenomenological fractional reproduction metric. Because the explicit solver numerically constrains trajectories to the discretized governing dynamics, AlphaNet7 outperforms fixed-order baselines in calibration and out-of-sample forecasting, reducing forecast error by 30.2 % – 63.1 % across rolling hold-out splits under unified normalization. This provides a prior-constrained framework for effective parameter estimation in variable-order fractional systems.
- 7 October 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (40) , 405206
A deterministic framework for epidemic dynamics with abrupt intervention: indicator-based switching and phase-dependent thresholds
Mathematical models of epidemiology frequently assume time-invariant parameters, failing to capture the abrupt systemic shifts triggered by delayed medical interventions. In this study, we formulate a deterministic susceptible-infectious-recovered framework incorporating an abrupt, time-triggered intervention mechanism, modulated by a time-dependent indicator function, 1 A ( t ) , to explicitly simulate the sudden formulation and deployment of an antidote at a critical time, t 1 . This approach partitions the epidemic timeline, yielding a phase-dependent basic reproduction number ( R 0 ). The intervention time t 1 determines when the system transitions from the pre-intervention reproduction regime to the post-intervention regime. We rigorously establish the positivity and boundedness of the system and derive the phase-dependent disease-free and endemic equilibria. Utilizing the next generation matrix and the Routh–Hurwitz criterion, we prove the local and global asymptotic stability of these states, identifying that the post-antidote autonomous subsystem undergoes a forward transcritical bifurcation at R 0 post = 1 . To translate these analytical theorems into mathematical intervention insights, we conduct comprehensive numerical and sensitivity analyses. Phase portraits and bifurcation diagrams illustrate the resulting global stability regimes and threshold boundaries. Furthermore, a two-dimensional synergistic parameter analysis of therapeutic curing and prophylactic vaccination demonstrates the nonlinear trade-offs in resource allocation. Crucially, by tracking cumulative disease-induced mortality density and varying the intervention delay ( t 1 ), we mathematically quantify the nonlinear cost of delayed intervention. Our findings demonstrate that the synergistic and timely deployment of an antidote is critical for controlling highly infectious viral diseases and preventing persistent endemic transmission.
- 7 October 2026
- Published by IOP Publishing in Physica Scripta
- Vol. 101 (40) , 405206
A deterministic framework for epidemic dynamics with abrupt intervention: indicator-based switching and phase-dependent thresholds
Mathematical models of epidemiology frequently assume time-invariant parameters, failing to capture the abrupt systemic shifts triggered by delayed medical interventions. In this study, we formulate a deterministic susceptible-infectious-recovered framework incorporating an abrupt, time-triggered intervention mechanism, modulated by a time-dependent indicator function, 1 A ( t ) , to explicitly simulate the sudden formulation and deployment of an antidote at a critical time, t 1 . This approach partitions the epidemic timeline, yielding a phase-dependent basic reproduction number ( R 0 ). The intervention time t 1 determines when the system transitions from the pre-intervention reproduction regime to the post-intervention regime. We rigorously establish the positivity and boundedness of the system and derive the phase-dependent disease-free and endemic equilibria. Utilizing the next generation matrix and the Routh–Hurwitz criterion, we prove the local and global asymptotic stability of these states, identifying that the post-antidote autonomous subsystem undergoes a forward transcritical bifurcation at R 0 post = 1 . To translate these analytical theorems into mathematical intervention insights, we conduct comprehensive numerical and sensitivity analyses. Phase portraits and bifurcation diagrams illustrate the resulting global stability regimes and threshold boundaries. Furthermore, a two-dimensional synergistic parameter analysis of therapeutic curing and prophylactic vaccination demonstrates the nonlinear trade-offs in resource allocation. Crucially, by tracking cumulative disease-induced mortality density and varying the intervention delay ( t 1 ), we mathematically quantify the nonlinear cost of delayed intervention. Our findings demonstrate that the synergistic and timely deployment of an antidote is critical for controlling highly infectious viral diseases and preventing persistent endemic transmission.
- 2 July 2026
- Published by Springer Nature
- p. 265-286
Safeguarding Delta Waterscapes: An Operational Modelling Framework for Pathogen Control and Reuse
- 2 July 2026
- Published by Springer Nature
- p. 265-286
Safeguarding Delta Waterscapes: An Operational Modelling Framework for Pathogen Control and Reuse
- 2 July 2026
- Published by Springer Nature
- p. 287-315
Digital Twins for Delta Resilience: Smart Wastewater Operations in the Ganges–Brahmaputra Basin
- 2 July 2026
- Published by Springer Nature
- p. 287-315
Digital Twins for Delta Resilience: Smart Wastewater Operations in the Ganges–Brahmaputra Basin