Birendra Jha

Yash Gandhi, Kexin Zheng, Birendra Jha et al.

Forecasting oil production from oilfields with multiple wells is an important problem in petroleum and geothermal energy extraction, as well as energy storage technologies. The accuracy of oil forecasts is a critical determinant of economic projections, hydrocarbon reserves estimation, construction of fluid processing facilities, and energy price fluctuations. Leveraging generative AI techniques, we model time series forecasting of oil and water productions across four multi-well sites spanning four decades. Our goal is to effectively model uncertainties and make precise forecasts to inform decision-making processes at the field scale. We utilize an autoregressive model known as TimeGrad and a variant of a transformer architecture named Informer, tailored specifically for forecasting long sequence time series data. Predictions from both TimeGrad and Informer closely align with the ground truth data. The overall performance of the Informer stands out, demonstrating greater efficiency compared to TimeGrad in forecasting oil production rates across all sites.

Birendra Jha, Medha Atre, Ashwini Rao

Web-based phishing attacks nowadays exploit popular cloud web hosting services and apps such as Google Sites and Typeform for hosting their attacks. Since these attacks originate from reputable domains and IP addresses of the cloud services, traditional phishing detection methods such as IP reputation monitoring and blacklisting are not very effective. Here we investigate the effectiveness of deep learning models in detecting this class of cloud-based phishing attacks. Specifically, we evaluate deep learning models for three phishing detection methods--LSTM model for URL analysis, YOLOv2 model for logo analysis, and triplet network model for visual similarity analysis. We train the models using well-known datasets and test their performance on cloud-based phishing attacks in the wild. Our results qualitatively explain why the models succeed or fail. Furthermore, our results highlight how combining results from the individual models can improve the effectiveness of detecting cloud-based phishing attacks.

Ramdhan Wibawa, Birendra Jha

We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically unstable transport known as viscous fingering. AI-based modeling of flow with instabilities remains challenging because rapidly evolving, multiscale fingering patterns are difficult to resolve accurately. We identify solutions that appear visually realistic yet are physically implausible, analogous to hallucinations in large language models. These hallucinations manifest as spurious fluid interfaces and reverse diffusion that violate conservation laws. We show that their origin lies in the spectral bias of AI models, which becomes dominant at high flow rates and viscosity contrasts. Guided by this insight, we introduce DeepFingers, a new framework for AI-driven fluid dynamics that enforces balanced learning across the full spectrum of spatial modes by combining the Fourier Neural Operator with a Deep Operator Network to predict the spatiotemporal evolution of viscous fingers. By conditioning on both time and viscosity contrast, DeepFingers learns mappings between successive concentration fields across regimes. The framework accurately captures tip splitting, finger merging, and channel formation while preserving global metrics of mixing. The results open a new research direction to investigate fundamental limitations in AI models of physical systems.

Tharunsarathy, Wasim Niyaz Munshi, Chandrasekhar Annavarapu et al.

Predicting the initiation and propagation of cracks in heterogeneous wellbore systems under complex in-situ conditions remains challenging. We present a hybrid phase-field fracture framework to model crack growth in heterogeneous wellbore systems with weak interfaces. The framework is first validated against benchmark problems with available analytical and numerical solutions. Subsequently, numerical experiments are conducted to isolate the effects of interface strength and casing eccentricity on crack growth. The results show that casing eccentricity strongly influences both the pressure at crack initiation and the resulting crack paths, reducing the crack initiation pressure by up to 30% relative to the concentric configuration. Beyond a critical eccentricity threshold of 50%, localized shear stresses drive the nucleation of inclined cracks in the formation in addition to radial cracking -- a failure mode absent in concentric configurations. For sufficiently weak interfaces (i.e., interfaces with 30% of the strength of the surrounding bulk material), radially propagating cracks in the cement sheath are deflected along the interface rather than penetrating into the formation. This deflection delays stress relaxation within the sheath, promotes the nucleation of additional radial cracks, and increases the risk of sustained casing pressure and wellbore failure. Finally, a three-dimensional simulation reveals depth-dependent crack nucleation, stress-shadow effects that suppress full-depth crack growth and crack coalescence along the cement-formation interface -- phenomena that are fundamentally inaccessible under plane-strain assumptions - demonstrating the applicability of the framework to realistic heterogeneous wellbore systems.