arXiv subjects

Rahul Ghosh

Publications and source records attributed to Rahul Ghosh.

At least 37 records · Page 2Linked to original sources

arXiv2025

Spin-imbalance induced buried topological edge currents in Mott \& topological insulator heterostructures

We theoretically investigate the heterostructure between a ferrimagnetic Mott insulator and a time-reversal invariant topological band insulator on the two-dimensional Lieb lattice with periodic boundary conditions. Our Hartree-Fock and slave-rotor mean-field results incorporate long-range Coulomb interactions. We present charge and magnetic reconstructions at the two edges of the heterostructure and reveal how \textit{buried} topological edge modes adapt to these heterostructure edge reconstructions. In particular, we demonstrate that the interface magnetic field induces a spin imbalance in the edge modes while preserving their topological character and metallic nature. We show that this imbalance leads to topologically protected buried spin and charge currents. The inherent spin-momentum locking ensures that left and right movers contribute to the current at the two buried interfaces in opposite directions. We show that the magnitude of the spin-imbalance induced charge and spin current can be tuned by adjusting the spin-orbit coupling of the bulk topological insulator relative to the correlation strength of the bulk Mott insulator. Thus, our results demonstrate a controlled conversion of a spin Hall effect into an analog of a charge Hall effect driven by band topology and interaction effects. These topologically protected charge and spin currents pave the way for advances in low-energy electronics and spintronic devices.

cond-mat.mes-hall↗

arXiv2024

Signatures of topology in generic transport measurements for Rarita-Schwinger-Weyl semimetals

We investigate how the signatures of the topological properties of the bandstructures for nodal-point semimetals are embedded in the response coefficients, arising in two distinct experimental set-ups, by taking the Rarita-Schwinger-Weyl (RSW) semimetal as an example. The first scenario involves the computation of third-rank tensors representing second-order response coefficients, relating the charge/thermal current densities to the combined effects of the gradient of the chemical potential and an external electric field/temperature gradient. On the premises that internode scatterings can be ignored, the relaxation-time approximation leads to a quantized value for the nonvanishing components of each of these nonlinear response tensors, characterizing a single untilted RSW node. Furthermore, the final expressions turn out to be insensitive to the specific values of the chemical potential and the temperature. The second scenario involves computing the magnetoelectric conductivity under the action of collinear electric ($\mathbf E$) and magnetic ($\mathbf B$) fields, representing a planar Hall set-up. In particular, our focus is in bringing out the dependence of the linear-in-$|\mathbf B|$ parts of the conductivity tensor on the intrinsic topological properties of the bandstructure, which are nonvanishing only in the presence of a nonzero tilt in the energy spectrum.

cond-mat.mes-hall↗

arXiv2024

Linear response in planar Hall and thermal Hall setups for Rarita-Schwinger-Weyl semimetals

We investigate the nature of the linear-response tensors in planar Hall and planar thermal Hall setups, where we subject a Rarita-Schwinger-Weyl (RSW) semimetal to the combined influence of an electric field $\mathbf E $ (and/or temperature gradient $\nabla_{\mathbf r } T$) and a weak (i.e., nonquantizing) magnetic field $\mathbf B $. For computing the in-plane transport components, we have added an elastic deformation which gives rise to a chirality-dependent effective magnetic field $ \mathbf B^{\text{tot}} = \mathbf B + χ\, \mathbf B_5 $, where $χ$ is the chirality of an RSW node. We have included the effects of orbital magnetic moment (OMM), in conjunction with the Berry curvature (BC), both of which appear as a consequence of nontrivial topology of the bandstructure. Due to the presence of four bands, RSW semimetals provide a richer structure for obtaining the linear-response coefficients, compared to the Weyl semimetals. In particular, we have found that the OMM-contributed terms may oppose or add up to the BC-only parts, depending on which band we are considering. Last, but not the least, we have determined the out-of-plane response comprising the intrinsic anomalous-Hall and the Lorentz-force-contributed currents, whose nature corroborates the findings of some recent experimental results.

cond-mat.mes-hall↗

arXiv2024

Electric, thermal, and thermoelectric magnetoconductivity for Weyl/multi-Weyl semimetals in planar Hall set-ups induced by the combined effects of topology and strain

We continue our investigation of the response tensors in planar Hall (or planar thermal Hall) configurations where a three-dimensional Weyl/multi-Weyl semimetal is subjected to the combined influence of an electric field $\mathbf E $ (and/or temperature gradient $\nabla_{\mathbf r } T$) and an effective magnetic field $\mathbf B_χ$, generalizing the considerations of Phys. Rev. B 108 (2023) 155132 and Physica E 159 (2024) 115914. The electromagnetic fields are oriented at a generic angle with respect to each other, thus leading to the possibility of having collinear components, which do not arise in a Hall set-up. The net effective magnetic field $\mathbf B_χ$ consists of two parts -- (a) an actual/physical magnetic field $\mathbf B $ applied externally; and (b) an emergent magnetic field $\mathbf B_5 $ which quantifies the elastic deformations of the sample. $\mathbf B_5 $ is an axial pseudomagnetic field because it couples to conjugate nodal points with opposite chiralities with opposite signs. Using a semiclassical Boltzmann formalism, we derive the generic expressions for the response tensors, including the effects of the Berry curvature (BC) and the orbital magnetic moment (OMM), which arise due to a nontrivial topology of the bandstructures. We elucidate the interplay of the BC-only and the OMM-dependent parts in the longitudinal and transverse (or Hall) components of the electric, thermal, and thermoelectric response tensors. Especially, for the co-planar transverse components of the response tensors, the OMM part acts exclusively in opposition (sync) with the BC-only part for the Weyl (multi-Weyl) semimetals.

cond-mat.mes-hall↗

arXiv2024

Hierarchical Conditional Multi-Task Learning for Streamflow Modeling

Streamflow, vital for water resource management, is governed by complex hydrological systems involving intermediate processes driven by meteorological forces. While deep learning models have achieved state-of-the-art results of streamflow prediction, their end-to-end single-task learning approach often fails to capture the causal relationships within these systems. To address this, we propose Hierarchical Conditional Multi-Task Learning (HCMTL), a hierarchical approach that jointly models soil water and snowpack processes based on their causal connections to streamflow. HCMTL utilizes task embeddings to connect network modules, enhancing flexibility and expressiveness while capturing unobserved processes beyond soil water and snowpack. It also incorporates the Conditional Mini-Batch strategy to improve long time series modeling. We compare HCMTL with five baselines on a global dataset. HCMTL's superior performance across hundreds of drainage basins over extended periods shows that integrating domain-specific causal knowledge into deep learning enhances both prediction accuracy and interpretability. This is essential for advancing our understanding of complex hydrological systems and supporting efficient water resource management to mitigate natural disasters like droughts and floods.

cs.LG↗

arXiv2024

Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems

We introduce TAM-RL (Task Aware Modulation using Representation Learning), a novel multimodal meta-learning framework for few-shot learning in heterogeneous systems, designed for science and engineering problems where entities share a common underlying forward model but exhibit heterogeneity due to entity-specific characteristics. TAM-RL leverages an amortized training process with a modulation network and a base network to learn task-specific modulation parameters, enabling efficient adaptation to new tasks with limited data. We evaluate TAM-RL on two real-world environmental datasets: Gross Primary Product (GPP) prediction and streamflow forecasting, demonstrating significant improvements over existing meta-learning methods. On the FLUXNET dataset, TAM-RL improves RMSE by 18.9\% over MMAML with just one month of few-shot data, while for streamflow prediction, it achieves an 8.21\% improvement with one year of data. Synthetic data experiments further validate TAM-RL's superior performance in heterogeneous task distributions, outperforming the baselines in the most heterogeneous setting. Notably, TAM-RL offers substantial computational efficiency, with at least 3x faster training times compared to gradient-based meta-learning approaches while being much simpler to train due to reduced complexity. Ablation studies highlight the importance of pretraining and adaptation mechanisms in TAM-RL's performance.

cs.LG↗

arXiv2024

Refractive index profiles for a $\mathcal{PT}$-symmetric optical structure

By mapping the scalar Helmholtz equation (SHE) to the Schrodinger form we investigate the behaviour of $\mathcal{PT}$ optical structure when the refractive index distribution $n$ admits variation in the longitudinal direction only. Interpreting the Schrodinger equation in terms of a superpotential we determine the supersymmetric partners for $n$. We also obtain new analytical solutions for the refractive index profiles and provide graphical illustrations for them.

quant-ph↗

arXiv2024

Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles

Event coreference resolution (ECR) is the task of determining whether distinct mentions of events within a multi-document corpus are actually linked to the same underlying occurrence. Images of the events can help facilitate resolution when language is ambiguous. Here, we propose a multimodal cross-document event coreference resolution method that integrates visual and textual cues with a simple linear map between vision and language models. As existing ECR benchmark datasets rarely provide images for all event mentions, we augment the popular ECB+ dataset with event-centric images scraped from the internet and generated using image diffusion models. We establish three methods that incorporate images and text for coreference: 1) a standard fused model with finetuning, 2) a novel linear mapping method without finetuning and 3) an ensembling approach based on splitting mention pairs by semantic and discourse-level difficulty. We evaluate on 2 datasets: the augmented ECB+, and AIDA Phase 1. Our ensemble systems using cross-modal linear mapping establish an upper limit (91.9 CoNLL F1) on ECB+ ECR performance given the preprocessing assumptions used, and establish a novel baseline on AIDA Phase 1. Our results demonstrate the utility of multimodal information in ECR for certain challenging coreference problems, and highlight a need for more multimodal resources in the coreference resolution space.

cs.CL↗

arXiv2024

Combining Satellite and Weather Data for Crop Type Mapping: An Inverse Modelling Approach

Accurate and timely crop mapping is essential for yield estimation, insurance claims, and conservation efforts. Over the years, many successful machine learning models for crop mapping have been developed that use just the multi-spectral imagery from satellites to predict crop type over the area of interest. However, these traditional methods do not account for the physical processes that govern crop growth. At a high level, crop growth can be envisioned as physical parameters, such as weather and soil type, acting upon the plant leading to crop growth which can be observed via satellites. In this paper, we propose Weather-based Spatio-Temporal segmentation network with ATTention (WSTATT), a deep learning model that leverages this understanding of crop growth by formulating it as an inverse model that combines weather (Daymet) and satellite imagery (Sentinel-2) to generate accurate crop maps. We show that our approach provides significant improvements over existing algorithms that solely rely on spectral imagery by comparing segmentation maps and F1 classification scores. Furthermore, effective use of attention in WSTATT architecture enables detection of crop types earlier in the season (up to 5 months in advance), which is very useful for improving food supply projections. We finally discuss the impact of weather by correlating our results with crop phenology to show that WSTATT is able to capture physical properties of crop growth.

cs.CV↗

arXiv2024

New solutions of Isochronous potentials in terms of exceptional orthogonal polynomials in heterostructures

Point canonical transformation (PCT) has been used to find out new exactly solvable potentials in the position-dependent mass (PDM) framework. We solve $1$-D Schrödinger equation in the PDM framework by considering two different fairly generic position-dependent masses $ (i) M(x)=λg'(x)$ and $(ii) M(x) = c \left( {g'(x)} \right)^ν$, $ν=\frac{2η}{2η+1},$ with $η= 0,1,2\cdots $. In the first case, we find new exactly solvable potentials that depend on an integer parameter $m$, and the corresponding solutions are written in terms of $X_m$-Laguerre polynomials. In the latter case, we obtain a new one parameter $(ν)$ family of isochronous solvable potentials whose bound states are written in terms of $X_m$-Laguerre polynomials. Further, we show that the new potentials are shape invariant by using the supersymmetric approach in the framework of PDM.

quant-ph↗

arXiv2023

A BERT based Ensemble Approach for Sentiment Classification of Customer Reviews and its Application to Nudge Marketing in e-Commerce

According to the literature, Product reviews are an important source of information for customers to support their buying decision. Product reviews improve customer trust and loyalty. Reviews help customers in understanding what other customers think about a particular product and helps in driving purchase decisions. Therefore, for an e-commerce platform it is important to understand the sentiments in customer reviews to understand their products and services, and it also allows them to potentially create positive consumer interaction as well as long lasting relationships. Reviews also provide innovative ways to market the products for an ecommerce company. One such approach is Nudge Marketing. Nudge marketing is a subtle way for an ecommerce company to help their customers make better decisions without hesitation.

cs.CL↗

arXiv2023

Uncertainty Quantification in Inverse Models in Hydrology

In hydrology, modeling streamflow remains a challenging task due to the limited availability of basin characteristics information such as soil geology and geomorphology. These characteristics may be noisy due to measurement errors or may be missing altogether. To overcome this challenge, we propose a knowledge-guided, probabilistic inverse modeling method for recovering physical characteristics from streamflow and weather data, which are more readily available. We compare our framework with state-of-the-art inverse models for estimating river basin characteristics. We also show that these estimates offer improvement in streamflow modeling as opposed to using the original basin characteristic values. Our inverse model offers 3\% improvement in R$^2$ for the inverse model (basin characteristic estimation) and 6\% for the forward model (streamflow prediction). Our framework also offers improved explainability since it can quantify uncertainty in both the inverse and the forward model. Uncertainty quantification plays a pivotal role in improving the explainability of machine learning models by providing additional insights into the reliability and limitations of model predictions. In our analysis, we assess the quality of the uncertainty estimates. Compared to baseline uncertainty quantification methods, our framework offers 10\% improvement in the dispersion of epistemic uncertainty and 13\% improvement in coverage rate. This information can help stakeholders understand the level of uncertainty associated with the predictions and provide a more comprehensive view of the potential outcomes.

cs.LG↗

arXiv2023

Koopman Invertible Autoencoder: Leveraging Forward and Backward Dynamics for Temporal Modeling

Accurate long-term predictions are the foundations for many machine learning applications and decision-making processes. However, building accurate long-term prediction models remains challenging due to the limitations of existing temporal models like recurrent neural networks (RNNs), as they capture only the statistical connections in the training data and may fail to learn the underlying dynamics of the target system. To tackle this challenge, we propose a novel machine learning model based on Koopman operator theory, which we call Koopman Invertible Autoencoders (KIA), that captures the inherent characteristic of the system by modeling both forward and backward dynamics in the infinite-dimensional Hilbert space. This enables us to efficiently learn low-dimensional representations, resulting in more accurate predictions of long-term system behavior. Moreover, our method's invertibility design guarantees reversibility and consistency in both forward and inverse operations. We illustrate the utility of KIA on pendulum and climate datasets, demonstrating 300% improvements in long-term prediction capability for pendulum while maintaining robustness against noise. Additionally, our method excels in long-term climate prediction, further validating our method's effectiveness.

cs.LG↗

arXiv2023

Analogue Hawking radiation as a tunneling in a two-level $\mathcal{PT}$-symmetric system

In the light of a general scenario of a two-level non-Hermitian $\mathcal{PT}$-symmetric Hamiltonian we apply the tetrad-based method to analyze the possibility of analogue Hawking radiation. It is done by making use of the conventional null-geodesic approach wherein the associated Hawking radiation is described as a quantum tunneling process across a classically forbidden barrier which the event horizon imposes. An interesting aspect of our result is that our estimate for the tunneling probability is independent of the non-Hermitian parameter that defines the guiding Hamiltonian.

gr-qc↗

arXiv2023

Entity Aware Modelling: A Survey

Personalized prediction of responses for individual entities caused by external drivers is vital across many disciplines. Recent machine learning (ML) advances have led to new state-of-the-art response prediction models. Models built at a population level often lead to sub-optimal performance in many personalized prediction settings due to heterogeneity in data across entities (tasks). In personalized prediction, the goal is to incorporate inherent characteristics of different entities to improve prediction performance. In this survey, we focus on the recent developments in the ML community for such entity-aware modeling approaches. ML algorithms often modulate the network using these entity characteristics when they are readily available. However, these entity characteristics are not readily available in many real-world scenarios, and different ML methods have been proposed to infer these characteristics from the data. In this survey, we have organized the current literature on entity-aware modeling based on the availability of these characteristics as well as the amount of training data. We highlight how recent innovations in other disciplines, such as uncertainty quantification, fairness, and knowledge-guided machine learning, can improve entity-aware modeling.

cs.LG↗

arXiv2023

Mini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications

In many environmental applications, recurrent neural networks (RNNs) are often used to model physical variables with long temporal dependencies. However, due to mini-batch training, temporal relationships between training segments within the batch (intra-batch) as well as between batches (inter-batch) are not considered, which can lead to limited performance. Stateful RNNs aim to address this issue by passing hidden states between batches. Since Stateful RNNs ignore intra-batch temporal dependency, there exists a trade-off between training stability and capturing temporal dependency. In this paper, we provide a quantitative comparison of different Stateful RNN modeling strategies, and propose two strategies to enforce both intra- and inter-batch temporal dependency. First, we extend Stateful RNNs by defining a batch as a temporally ordered set of training segments, which enables intra-batch sharing of temporal information. While this approach significantly improves the performance, it leads to much larger training times due to highly sequential training. To address this issue, we further propose a new strategy which augments a training segment with an initial value of the target variable from the timestep right before the starting of the training segment. In other words, we provide an initial value of the target variable as additional input so that the network can focus on learning changes relative to that initial value. By using this strategy, samples can be passed in any order (mini-batch training) which significantly reduces the training time while maintaining the performance. In demonstrating our approach in hydrological modeling, we observe that the most significant gains in predictive accuracy occur when these methods are applied to state variables whose values change more slowly, such as soil water and snowpack, rather than continuously moving flux variables such as streamflow.

cs.LG↗

arXiv2023

Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin

Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has nearly 200,000 smallholder cashew growers contributing 15% of the country's national export earnings. However, a lack of information on where and how cashew trees grow across the country hinders decision-making that could support increased cashew production and poverty alleviation. By leveraging 2.4-m Planet Basemaps and 0.5-m aerial imagery, newly developed deep learning algorithms, and large-scale ground truth datasets, we successfully produced the first national map of cashew in Benin and characterized the expansion of cashew plantations between 2015 and 2021. In particular, we developed a SpatioTemporal Classification with Attention (STCA) model to map the distribution of cashew plantations, which can fully capture texture information from discriminative time steps during a growing season. We further developed a Clustering Augmented Self-supervised Temporal Classification (CASTC) model to distinguish high-density versus low-density cashew plantations by automatic feature extraction and optimized clustering. Results show that the STCA model has an overall accuracy over 85% and the CASTC model achieved an overall accuracy of 76%. We found that the cashew area in Benin almost doubled from 2015 to 2021 with 60% of new plantation development coming from cropland or fallow land, while encroachment of cashew plantations into protected areas has increased by 55%. Only half of cashew plantations were high-density in 2021, suggesting high potential for intensification. Our study illustrates the power of combining high-resolution remote sensing imagery and state-of-the-art deep learning algorithms to better understand tree crops in the heterogeneous smallholder landscape.

cs.CV↗

arXiv2022

Non-hermitian Dirac Hamiltonian in the presence of local Fermi velocity

We present a new approach to study a class of non-Hermitian (1+1)-dimensional Dirac Hamiltonian in the presence of local Fermi velocity. We apply the well known Nikiforov-Uvarov method to solve such a system. We discuss applications and explore the solvability of both $\mathcal{PT}$-symmetric and non-$\mathcal{PT}$ symmetric classes of potentials. In the former case we obtain the solution of a harmonic oscillator in the presence of a linear vector potential while in the latter case we solve the shifted harmonic oscillator problem.

quant-ph↗