arXiv subjects

Vipin Kumar

Publications and source records attributed to Vipin Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2023

Bayesian Federated Learning: A Survey

Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FL-based BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.

cs.LG↗

arXiv2023

Exponential Lag Synchronization of Cohen-Grossberg Neural Networks with Discrete and Distributed Delays on Time Scales

In this article, we investigate exponential lag synchronization results for the Cohen-Grossberg neural networks (C-GNNs) with discrete and distributed delays on an arbitrary time domain by applying feedback control. We formulate the problem by using the time scales theory so that the results can be applied to any uniform or non-uniform time domains. Also, we provide a comparison of results that shows that obtained results are unified and generalize the existing results. Mainly, we use the unified matrix-measure theory and Halanay inequality to establish these results. In the last section, we provide two simulated examples for different time domains to show the effectiveness and generality of the obtained analytical results.

math.OC↗

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

Exploring the short-term variability of Hα and H\b{eta} emissions in a sample of M Dwarfs

Activities in M dwarfs show spectroscopic variability over various time scales ranging from a few seconds to several hours. The time scales of such variability can be related to internal dynamics of M dwarfs like magnetic activity, energetic flaring events, their rotation periods, etc. The time variability in the strengths of prominent emission lines (particularly Hα ) is mostly taken as a proxy of such dynamic behavior. In this study, we have performed the spectroscopic monitoring of 83 M dwarfs (M0-M6.5) to study the variations in Hα and H\b{eta} emissions on short-time scales. Low-resolution (resolution around 5.7 angstroms) spectral time series of 3-5 minutes cadence over 0.7-2.3 hours were obtained with MFOSC-P instrument on PRL 1.2m Mt. Abu telescope, covering H\b{eta} and Hα wavelengths. Coupled with the data available in the literature and archival photometric data from TESS and Kepler/K2 archives, various variability parameters are explored for any plausible systematics with respect to their spectral types, and rotation periods. Though about 64% of our sample shows statistically significant variability, it is not uniform across the spectral type and rotation period. Hα activity strength (LHα/Lbol) is also derived and explored for such distributions.

astro-ph.SR↗

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

Optical and X-ray studies of Be/X-ray binary 1A 0535+262 during its 2020 giant outburst

We report results obtained from the optical and X-ray studies of the Be/X-ray binary 1A 0535+262/HD 245770 during the 2020 October giant X-ray outburst, using the 1.2 m telescope at Mount Abu Infrared observatory and AstroSat, respectively. The peak flux of the outburst was recorded to be around 11 Crab in the 15-50 keV range, the highest ever observed from the pulsar. We performed optical observations in the 6000-7200 angstroms band before, during, and after the outburst to investigate the evolution of the circumstellar disc of the Be star between 2020 February and 2022 February. Our optical spectra exhibit prominent emission lines at 6563 angstroms (H I), 6678 angstroms (He I), and 7065 angstroms (He I). We found a significantly variable Halpha line in the spectra. The single-peaked line profile appeared asymmetric with broad red- & blue-wings in the data before and during the outburst. The post-outburst observations, however, resulted in a double-peaked profile with asymmetry in the blue-wing. Our observations before the outburst confirmed a larger Be disc that decreased in size as the outburst progressed. Furthermore, the observed variabilities in the Halpha line profile and parameters suggest the presence of a highly misaligned, precessing, and warped Be disc. AstroSat observation of the pulsar detected pulsations at around 103.55 s in the light curve up to 110 keV. We found strongly energy-dependent pulse profiles with increasing contribution of the pulsing component in hard X-rays. The broadband spectral fitting in the 0.7-90.0 keV range confirmed the presence of the known cyclotron resonance scattering feature at around 46.3 keV.

astro-ph.HE↗

arXiv2022

Incorporating Causal Effects into Deep Learning Predictions on EHR Data

Electronic Health Records (EHR) data analysis plays a crucial role in healthcare system quality. Because of its highly complex underlying causality and limited observable nature, causal inference on EHR is quite challenging. Deep Learning (DL) achieved great success among the advanced machine learning methodologies. Nevertheless, it is still obstructed by the inappropriately assumed causal conditions. This work proposed a novel method to quantify clinically well-defined causal effects as a generalized estimation vector that is simply utilizable for causal models. We incorporated it into DL models to achieve better predictive performance and result interpretation. Furthermore, we also proved the existence of causal information blink spots that regular DL models cannot reach.

cs.LG↗

arXiv2022

Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets

Creating separable representations via representation learning and clustering is critical in analyzing large unstructured datasets with only a few labels. Separable representations can lead to supervised models with better classification capabilities and additionally aid in generating new labeled samples. Most unsupervised and semisupervised methods to analyze large datasets do not leverage the existing small amounts of labels to get better representations. In this paper, we propose a spatiotemporal clustering paradigm that uses spatial and temporal features combined with a constrained loss to produce separable representations. We show the working of this method on the newly published dataset ReaLSAT, a dataset of surface water dynamics for over 680,000 lakes across the world, making it an essential dataset in terms of ecology and sustainability. Using this large unlabelled dataset, we first show how a spatiotemporal representation is better compared to just spatial or temporal representation. We then show how we can learn even better representation using a constrained loss with few labels. We conclude by showing how our method, using few labels, can pick out new labeled samples from the unlabeled data, which can be used to augment supervised methods leading to better classification.

cs.LG↗

arXiv2022

Probabilistic Inverse Modeling: An Application in Hydrology

The astounding success of these methods has made it imperative to obtain more explainable and trustworthy estimates from these models. In hydrology, basin characteristics can be noisy or missing, impacting streamflow prediction. For solving inverse problems in such applications, ensuring explainability is pivotal for tackling issues relating to data bias and large search space. We propose a probabilistic inverse model framework that can reconstruct robust hydrology basin characteristics from dynamic input weather driver and streamflow response data. We address two aspects of building more explainable inverse models, uncertainty estimation and robustness. This can help improve the trust of water managers, handling of noisy data and reduce costs. We propose uncertainty based learning method that offers 6\% improvement in $R^2$ for streamflow prediction (forward modeling) from inverse model inferred basin characteristic estimates, 17\% reduction in uncertainty (40\% in presence of noise) and 4\% higher coverage rate for basin characteristics.

cs.LG↗

arXiv2022

Quantification of Pollen Viability in Lantana camara By Digital Holographic Microscopy

Pollen grains represent the male gametes of seed plants and their viability is critical for efficient sexual reproduction in the plant life cycle. Pollen analysis is used in diverse research thematics to address a range of botanical, ecological and geological questions. More recently it has been recognized that pollen may also be a vector for transgene escape from genetically modified crops, and the importance of pollen viability in invasion biology has also been emphasized. In this work, we analyse and report an efficient visual method for assessing the viability of pollen using digital holographic microscopy (DHM). We test this method on pollen grains of the invasive Lantana camara, a well known plant invader known to most of the tropical world. We image pollen grains and show that the quantitative phase information provided by the DHM technique can be readily related to the chromatin content of the individual cells and thereby to pollen viability. Our results offer a new technique for pollen viability assessment that does not require staining, and can be applied to a number of emerging areas in plant science.

eess.IV↗

arXiv2022

Investigating star-formation activity towards the southern HII region RCW 42

The star-forming activity in the HII region RCW 42 is investigated using multiple wavebands, from near-infrared to radio wavelengths. Located at a distance of 5.8 kpc, this southern region has a bolometric luminosity of 1.8 $\times$ 10$^6$ L$_{\odot}$. The ionized gas emission has been imaged at low radio frequencies of 610 and 1280 MHz using the Giant Metrewave Radio Telescope, India and shows a large expanse of the HII region, spanning $20\times 15$ pc$^2$. The average electron number density in the region is estimated to be $\sim70$ cm$^{-3}$, which suggests an average ionization fraction of the cloud to be $11\%$. An extended green object EGO G274.0649-01.1460 and several young stellar objects have been identified in the region using data from the 2MASS and Spitzer surveys. The dust emission from the associated molecular cloud is probed using Herschel Space Telescope, which reveals the presence of 5 clumps, C1-C5, in this region. Two millimetre emission cores of masses 380 and 390 M$_{\odot}$ towards the radio emission peak have been identified towards C1 from the ALMA map at 1.4 mm. The clumps are investigated for their evolutionary stages based on association with various star-formation tracers, and we find that all the clumps are in active/evolved stage.

astro-ph.GA↗

arXiv2022

Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology

Machine Learning is beginning to provide state-of-the-art performance in a range of environmental applications such as streamflow prediction in a hydrologic basin. However, building accurate broad-scale models for streamflow remains challenging in practice due to the variability in the dominant hydrologic processes, which are best captured by sets of process-related basin characteristics. Existing basin characteristics suffer from noise and uncertainty, among many other things, which adversely impact model performance. To tackle the above challenges, in this paper, we propose a novel Knowledge-guided Self-Supervised Learning (KGSSL) inverse framework to extract system characteristics from driver and response data. This first-of-its-kind framework achieves robust performance even when characteristics are corrupted. We show that KGSSL achieves state-of-the-art results for streamflow modeling for CAMELS (Catchment Attributes and MEteorology for Large-sample Studies) which is a widely used hydrology benchmark dataset. Specifically, KGSSL outperforms other methods by up to 16 \% in reconstructing characteristics. Furthermore, we show that KGSSL is relatively more robust to distortion than baseline methods, and outperforms the baseline model by 35\% when plugging in KGSSL inferred characteristics.

cs.LG↗

arXiv2022

Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems

There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques. This paper provides a structured overview of such techniques. Application-centric objective areas for which these approaches have been applied are summarized, and then classes of methodologies used to construct physics-guided ML models and hybrid physics-ML frameworks are described. We then provide a taxonomy of these existing techniques, which uncovers knowledge gaps and potential crossovers of methods between disciplines that can serve as ideas for future research.

physics.comp-ph↗

arXiv2021

Optical and near-infrared spectroscopy of Nova V2891 Cygni: evidence for shock-induced dust formation

We present multi-epoch optical and near-infrared observations of the highly reddened, \pion{Fe}{ii} class slow nova V2891 Cygni. The observations span 15 months since its discovery. The initial rapid brightening from quiescence, and the presence of a $\sim$35 day long pre-maximum halt, is well documented. The evidence that the current outburst of V2891 Cyg has undergone several distinct episodes of mass ejection is seen through time-varying P Cygni profiles of the O\,{\sc i} 7773\,$Å$ line. A highlight is the occurrence of a dust formation event centred around $\sim$+273d, which coincides with a phase of coronal line emission. The dust mass is found to be $\sim0.83-1.25 \times 10^{-10} M_{\odot}$. There is strong evidence to suggest that the coronal lines are created by shock heating rather than by photoionization. The simultaneous occurrence of the dust and coronal lines (with varying velocity shifts) supports the possibility that dust formation is shock-induced. Such a route for dust formation has not previously been seen in a nova, although the mechanism has been proposed for dust formation in some core-collapse supernovae. Analysis of the coronal lines indicates a gas mass and temperature of 8.35--8.42$\times10^{-7}$ M$_\odot$ and $\sim(4.8-9.1)\times10^{5}$~K respectively, and an overabundance of aluminium and silicon. A Case B analysis of the hydrogen lines yields a mass of the ionized gas of ($8.60\pm1.73)\times10^{-5}$ M$_{\odot}$. The reddening and distance to the nova are estimated to be $E(B-V)$ = 2.21$\pm$0.15 and $d$ = 5.50 kpc respectively.

astro-ph.SR↗

arXiv2021

Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling

This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling setup to generate predictions using a neural network architecture. Further, this framework uses physics-based loss functions in the learning objective of neural networks to ensure that the model predictions not only show lower errors on the training set but are also scientifically consistent with the known physics on the unlabeled set. We illustrate the effectiveness of PGNN for the problem of lake temperature modeling, where physical relationships between the temperature, density, and depth of water are used to design a physics-based loss function. By using scientific knowledge to guide the construction and learning of neural networks, we are able to show that the proposed framework ensures better generalizability as well as scientific consistency of results. All the code and datasets used in this study have been made available on this link \url{https://github.com/arkadaw9/PGNN}.

cs.LG↗

arXiv2021

Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping

The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, noisy data, and the lack of proper labels. Also, each land cover class typically has its own unique temporal pattern and can be identified only during certain periods. In this article, we introduce a novel architecture that incorporates the UNet structure with Bidirectional LSTM and Attention mechanism to jointly exploit the spatial and temporal nature of satellite data and to better identify the unique temporal patterns of each land cover. We evaluate this method for mapping crops in multiple regions over the world. We compare our method with other state-of-the-art methods both quantitatively and qualitatively on two real-world datasets which involve multiple land cover classes. We also visualise the attention weights to study its effectiveness in mitigating noise and identifying discriminative time period.

cs.CV↗

arXiv2021

CalCROP21: A Georeferenced multi-spectral dataset of Satellite Imagery and Crop Labels

Mapping and monitoring crops is a key step towards sustainable intensification of agriculture and addressing global food security. A dataset like ImageNet that revolutionized computer vision applications can accelerate development of novel crop mapping techniques. Currently, the United States Department of Agriculture (USDA) annually releases the Cropland Data Layer (CDL) which contains crop labels at 30m resolution for the entire United States of America. While CDL is state of the art and is widely used for a number of agricultural applications, it has a number of limitations (e.g., pixelated errors, labels carried over from previous errors and absence of input imagery along with class labels). In this work, we create a new semantic segmentation benchmark dataset, which we call CalCROP21, for the diverse crops in the Central Valley region of California at 10m spatial resolution using a Google Earth Engine based robust image processing pipeline and a novel attention based spatio-temporal semantic segmentation algorithm STATT. STATT uses re-sampled (interpolated) CDL labels for training, but is able to generate a better prediction than CDL by leveraging spatial and temporal patterns in Sentinel2 multi-spectral image series to effectively capture phenologic differences amongst crops and uses attention to reduce the impact of clouds and other atmospheric disturbances. We also present a comprehensive evaluation to show that STATT has significantly better results when compared to the resampled CDL labels. We have released the dataset and the processing pipeline code for generating the benchmark dataset.

cs.CV↗