arXiv subjects

Sumanta Roy

Publications and source records attributed to Sumanta Roy.

7 recordsLinked to original sources

arXiv2026

$\phi-$DeepONet: A Discontinuity Capturing Neural Operator

We present $\phi-$DeepONet, a physics-informed neural operator designed to learn mappings between function spaces that may contain discontinuities or exhibit non-smooth behavior. Classical neural operators are based on the universal approximation theorem which assumes that both the operator and the functions it acts on are continuous. However, many scientific and engineering problems involve naturally discontinuous input fields as well as strong and weak discontinuities in the output fields caused by material interfaces. In $\phi$-DeepONet, discontinuities in the input are handled using multiple branch networks, while discontinuities in the output are learned through a nonlinear latent embedding of the interface. This embedding is constructed from a {\it one-hot} representation of the domain decomposition that is combined with the spatial coordinates in a modified trunk network. The outputs of the branch and trunk networks are then combined through a dot product to produce the final solution, which is trained using a physics- and interface-informed loss function. We evaluate $\phi$-DeepONet on several one- and two-dimensional benchmark problems and demonstrate that it delivers accurate and stable predictions even in the presence of strong interface-driven discontinuities.

cs.CE↗

arXiv2026

Hard-constrained Physics-informed Neural Networks for Interface Problems

Physics-informed neural networks (PINNs) have emerged as a flexible framework for solving partial differential equations, but their performance on interface problems remains challenging because continuity and flux conditions are typically imposed through soft penalty terms. The standard soft-constraint formulation leads to imperfect interface enforcement and degraded accuracy near interfaces. We introduce two ansatz-based hard-constrained PINN formulations for interface problems that embed the interface physics into the solution representation and thereby decouple interface enforcement from PDE residual minimization. The first, termed the windowing approach, constructs the trial space from compactly supported windowed subnetworks so that interface continuity and flux balance are satisfied by design. The second, called the buffer approach, augments unrestricted subnetworks with auxiliary buffer functions that enforce boundary and interface constraints at discrete points through a lightweight correction. We study these formulations on one- and two-dimensional elliptic interface benchmarks and compare them with soft-constrained baselines. In one-dimensional problems, hard constraints consistently improve interface fidelity and remove the need for loss-weight tuning; the windowing approach attains very high accuracy (as low as $O(10^{-9})$) on simple structured cases, whereas the buffer approach remains accurate ($\sim O(10^{-5})$) across a wider range of source terms and interface configurations. In two dimensions, the buffer formulation is shown to be more robust because it enforces constraints through a discrete buffer correction, as the windowing construction becomes more sensitive to overlap and corner effects and over-constrains the problem. This positions the buffer method as a straightforward and geometrically flexible approach to complex interface problems.

math.NA↗

arXiv2025

A Physics-informed Multi-resolution Neural Operator

The predictive accuracy of operator learning frameworks depends on the quality and quantity of available training data (input-output function pairs), often requiring substantial amounts of high-fidelity data, which can be challenging to obtain in some real-world engineering applications. These datasets may be unevenly discretized from one realization to another, with the grid resolution varying across samples. In this study, we introduce a physics-informed operator learning approach by extending the Resolution Independent Neural Operator (RINO) framework to a fully data-free setup, addressing both challenges simultaneously. Here, the arbitrarily (but sufficiently finely) discretized input functions are projected onto a latent embedding space (i.e., a vector space of finite dimensions), using pre-trained basis functions. The operator associated with the underlying partial differential equations (PDEs) is then approximated by a simple multi-layer perceptron (MLP), which takes as input a latent code along with spatiotemporal coordinates to produce the solution in the physical space. The PDEs are enforced via a finite difference solver in the physical space. The validation and performance of the proposed method are benchmarked on several numerical examples with multi-resolution data, where input functions are sampled at varying resolutions, including both coarse and fine discretizations.

cs.LG↗

arXiv2024

Interpreting the suction stress profiles under steady-state conditions considering the independence of van Genuchten SWCC parameters

Suction stress is a fundamental component for applying the effective stress principle in unsaturated geotechnical engineering problems. The present paper aims to understand how the suction stress profiles get influenced if the $m$ and $n$ parameter of the van-Genuchten SWCC model is completely independent. Through the analysis, it is well noted that for constant air entry value, if the $m$ and $n$ relationships are varied, not only the number and the spread of the characteristic regimes get influenced, but the nature and the trend of the suction stress profiles associated with the regimes also alter significantly. A suggestion of selecting the m and n relationships is proposed for obtaining conservative solutions for geotechnical stability problems. The relevance of considering the unconstrained m parameter is established by computing the tensile crack depth of the clayey slope under steady-state infiltration conditions.

physics.geo-ph↗

arXiv2024

Analysis of Unsaturated Slope Stability under Seismic and Surcharge Loading by Upper Bound Rigid Block Method

Failure of earthen slopes is a very recurrent phenomenon, credited mainly due to the excess rainfall and application of surfeit surcharge. However, most of the analyses regarding slope stability were performed without considering the unsaturated state of the soil. The prime purpose of the present manuscript is to address the stability of unsaturated homogeneous slopes subjected to surcharge load and pseudo-static seismic forces under different climatic conditions. The upper bound limit analysis technique was used based on the log-spiral failure mechanism. The suction stress-based effective stress approach was used to capture the effect of the unsaturated zone of the slope. The suction stress is modelled using Gardner's one-parameter hydraulic conductivity function and van-Genuchten's soil water characteristics curve. An extensive parametric study is carried out to assess the combined effect of slope geometry, soil-strength parameters, hydro-mechanical parameters, depth of water table, various flow conditions, surcharge load, and seismic loading. A few stability charts are proposed to show the impact of surcharge load and seismic load separately on unsaturated homogeneous slopes subjected to various climatic conditions. The present computed solutions match quite well with the available solutions prescribed in the literature.

physics.geo-ph↗

arXiv2024

Physics-informed Neural Networks for Heterogeneous Poroelastic Media

This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The approach introduces a composite neural network (CoNN) where separate neural networks predict displacement and pressure variables for each material. While sharing identical activation functions, these networks are independently trained for all other parameters. To address challenges posed by heterogeneous material interfaces, the CoNN is integrated with the Interface-PINNs or I-PINNs framework (Sarma et al. 2024, https://dx.doi.org/10.1016/j.cma.2024.117135), allowing different activation functions across material interfaces. This ensures accurate approximation of discontinuous solution fields and gradients. Performance and accuracy of this combined architecture were evaluated against the conventional PINNs approach, a single neural network (SNN) architecture, and the eXtended PINNs (XPINNs) framework through two one-dimensional benchmark examples with discontinuous material properties. The results show that the proposed CoNN with I-PINNs architecture achieves an RMSE that is two orders of magnitude better than the conventional PINNs approach and is at least 40 times faster than the SNN framework. Compared to XPINNs, the proposed method achieves an RMSE at least one order of magnitude better and is 40% faster.

eess.SY↗

arXiv2024

Adaptive Interface-PINNs (AdaI-PINNs): An Efficient Physics-informed Neural Networks Framework for Interface Problems

We present an efficient physics-informed neural networks (PINNs) framework, termed Adaptive Interface-PINNs (AdaI-PINNs), to improve the modeling of interface problems with discontinuous coefficients and/or interfacial jumps. This framework is an enhanced version of its predecessor, Interface PINNs or I-PINNs (Sarma et al.; https://dx.doi.org/10.2139/ssrn.4766623), which involves domain decomposition and assignment of different predefined activation functions to the neural networks in each subdomain across a sharp interface, while keeping all other parameters of the neural networks identical. In AdaI-PINNs, the activation functions vary solely in their slopes, which are trained along with the other parameters of the neural networks. This makes the AdaI-PINNs framework fully automated without requiring preset activation functions. Comparative studies on one-dimensional, two-dimensional, and three-dimensional benchmark elliptic interface problems reveal that AdaI-PINNs outperform I-PINNs, reducing computational costs by 2-6 times while producing similar or better accuracy.

cs.LG↗