arXiv subjects

Vipin Kumar

Publications and source records attributed to Vipin Kumar.

At least 73 records · Page 4Linked to original sources

arXiv2021

Land Cover Mapping in Limited Labels Scenario: A Survey

Land cover mapping is essential for monitoring global environmental change and managing natural resources. Unfortunately, traditional classification models are plagued by limited training data available in existing land cover products and data heterogeneity over space and time. In this survey, we provide a structured and comprehensive overview of challenges in land cover mapping and machine learning methods used to address these problems. We also discuss the gaps and opportunities that exist for advancing research in this promising direction.

cs.LG↗

arXiv2021

Clustering augmented Self-Supervised Learning: Anapplication to Land Cover Mapping

Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of pre-training the Deep Neural Networks (DNN) on freely available large datasets, cannot be used for Remote Sensing due to the unavailability of such large-scale labeled datasets and the heterogeneity of data sources caused by the varying spatial and spectral resolution of different sensors. Self-supervised learning is an alternative approach that learns feature representation from unlabeled images without using any human annotations. In this paper, we introduce a new method for land cover mapping by using a clustering based pretext task for self-supervised learning. We demonstrate the effectiveness of the method on two societally relevant applications from the aspect of segmentation performance, discriminative feature representation learning and the underlying cluster structure. We also show the effectiveness of the active sampling using the clusters obtained from our method in improving the mapping accuracy given a limited budget of annotating.

cs.CV↗

arXiv2021

Weakly Supervised Classification Using Group-Level Labels

In many applications, finding adequate labeled data to train predictive models is a major challenge. In this work, we propose methods to use group-level binary labels as weak supervision to train instance-level binary classification models. Aggregate labels are common in several domains where annotating on a group-level might be cheaper or might be the only way to provide annotated data without infringing on privacy. We model group-level labels as Class Conditional Noisy (CCN) labels for individual instances and use the noisy labels to regularize predictions of the model trained on the strongly-labeled instances. Our experiments on real-world application of land cover mapping shows the utility of the proposed method in leveraging group-level labels, both in the presence and absence of class imbalance.

cs.LG↗

arXiv2021

Remotely $c$-almost periodic type functions in ${\mathbb R}^{n}$

In this paper, we relate the notions of remote almost periodicity and quasi-asymptotical almost periodicity; in actual fact, we observe that a remotely almost periodic function is nothing else but a bounded, uniformly continuous quasi-asymptotically almost periodic function. We introduce and analyze several new classes of remotely $c$-almost periodic functions in ${\mathbb R}^{n},$ slowly oscillating functions in ${\mathbb R}^{n},$ and further analyze the recently introduced class of quasi-asymptotically $c$-almost periodic functions in ${\mathbb R}^{n}.$ We provide certain applications of our theoretical results to the abstract Volterra integro-differential equations and the ordinary differential equations.

math.CA↗

arXiv2021

Phase Retrieval using Single-Instance Deep Generative Prior

Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.

cs.LG↗

arXiv2021

Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning

Most environmental data come from a minority of well-monitored sites. An ongoing challenge in the environmental sciences is transferring knowledge from monitored sites to unmonitored sites. Here, we demonstrate a novel transfer learning framework that accurately predicts depth-specific temperature in unmonitored lakes (targets) by borrowing models from well-monitored lakes (sources). This method, Meta Transfer Learning (MTL), builds a meta-learning model to predict transfer performance from candidate source models to targets using lake attributes and candidates' past performance. We constructed source models at 145 well-monitored lakes using calibrated process-based modeling (PB) and a recently developed approach called process-guided deep learning (PGDL). We applied MTL to either PB or PGDL source models (PB-MTL or PGDL-MTL, respectively) to predict temperatures in 305 target lakes treated as unmonitored in the Upper Midwestern United States. We show significantly improved performance relative to the uncalibrated process-based General Lake Model, where the median RMSE for the target lakes is $2.52^{\circ}C$. PB-MTL yielded a median RMSE of $2.43^{\circ}C$; PGDL-MTL yielded $2.16^{\circ}C$; and a PGDL-MTL ensemble of nine sources per target yielded $1.88^{\circ}C$. For sparsely monitored target lakes, PGDL-MTL often outperformed PGDL models trained on the target lakes themselves. Differences in maximum depth between the source and target were consistently the most important predictors. Our approach readily scales to thousands of lakes in the Midwestern United States, demonstrating that MTL with meaningful predictor variables and high-quality source models is a promising approach for many kinds of unmonitored systems and environmental variables.

cs.LG↗

arXiv2021

Design and Development of Mt. Abu Faint Object Spectrograph and Camera -- Pathfinder (MFOSC-P) for PRL 1.2m Mt. Abu Telescope

Mt. Abu Faint Object Spectrograph and Camera - Pathfinder (MFOSC-P) is an imager-spectrograph developed for the Physical Research Laboratory (PRL) 1.2m telescope at Gurushikhar, Mt. Abu, India. MFOSC-P is based on a focal reducer concept and provides seeing limited imaging (with a sampling of 3.3 pixels per arc-second) in Bessell's B, V, R, I and narrow-band H-$α$ filters. The instrument uses three plane reflection gratings, covering the spectral range of 4500-8500$Å$, with three different resolutions of 500, 1000, and 2000 around their central wavelengths. MFOSC-P was conceived as a pathfinder instrument for a next-generation instrument on the PRL's 2.5m telescope which is coming up at Mt. Abu. The instrument was developed during 2015-2019 and successfully commissioned on the PRL 1.2m telescope in February 2019. The designed performance has been verified with laboratory characterization tests and on-sky commissioning observations. Different science programs covering a range of objects are being executed with MFOSC-P since then, e.g., spectroscopy of M-dwarfs, novae $\&$ symbiotic systems, and detection of H-$α$ emission in star-forming regions. MFOSC-P presents a novel design and cost-effective way to develop a FOSC (Faint Object Spectrograph and Camera) type of instrument on a shorter time-scale of development. The design and development methodology presented here is most suitable in helping the small aperture telescope community develop such a versatile instrument, thereby diversifying the science programs of such observatories.

astro-ph.IM↗

arXiv2020

Physics-Guided Recurrent Graph Networks for Predicting Flow and Temperature in River Networks

This paper proposes a physics-guided machine learning approach that combines advanced machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we present a pre-training technique which transfers knowledge from physics-based models to initialize the machine learning model and learn the physics of streamflow and thermodynamics. We also propose a new loss function that balances the performance over different river segments. We demonstrate the effectiveness of the proposed method in predicting temperature and streamflow in a subset of the Delaware River Basin. In particular, we show that the proposed method brings a 33\%/14\% improvement over the state-of-the-art physics-based model and 24\%/14\% over traditional machine learning models (e.g., Long-Short Term Memory Neural Network) in temperature/streamflow prediction using very sparse (0.1\%) observation data for training. The proposed method has also been shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.

physics.geo-ph↗

arXiv2020

Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles

Physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While-state-of-the-art machine learning models can sometimes outperform physics-based models given ample amount of training data, they can produce results that are physically inconsistent. This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improves the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models, while generating outputs consistent with physical laws. An important aspect of our PGRNN approach lies in its ability to incorporate the knowledge encoded in physics-based models. This allows training the PGRNN model using very few true observed data while also ensuring high prediction accuracy. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where physics-based (also known as mechanistic) models are used, e.g., climate science, materials science, computational chemistry, and biomedicine.

cs.LG↗

arXiv2020

UV spectroscopy confirms SU Lyn to be a symbiotic star

SU Lyn, a star that ostensibly appears to be an unremarkable late M type giant, has recently been proposed to be a symbiotic star largely based on its hard X-ray properties. The star does not display, in low-resolution optical spectra, the high excitation lines typically seen in the spectra of symbiotic stars. In the present work, UV, optical, and near-infrared observations are presented, aimed at exploring and strengthening the proposed symbiotic classification for this star. Our Far-UV 1300-1800$Å$ spectrum of SU Lyn, obtained with the ASTROSAT mission's UVIT payload, shows emission lines of Si IV, C IV, OIII and N III in a spectrum typical of symbiotic stars. The UV spectrum robustly confirms SU Lyn's symbiotic nature. The detection of high excitation lines in a high-resolution optical spectrum further consolidates its symbiotic nature. As is being recognized, the potential existence of other similar symbiotic systems could significantly impact the census of symbiotic stars in the galaxy.

astro-ph.SR↗

arXiv2020

Inverse Problems, Deep Learning, and Symmetry Breaking

In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output. When inverting such systems, i.e., solving the associated inverse problems, there is no unique solution. This causes fundamental difficulties for deploying the emerging end-to-end deep learning approach. Using the generalized phase retrieval problem as an illustrative example, we show that careful symmetry breaking on the training data can help get rid of the difficulties and significantly improve the learning performance. We also extract and highlight the underlying mathematical principle of the proposed solution, which is directly applicable to other inverse problems.

cs.LG↗

arXiv2020

First Results from MFOSC-P : Low Resolution Optical Spectroscopy of a Sample of M dwarfs within 100 parsecs

Mt. Abu Faint Object Spectrograph and Camera (MFOSC-P) is an in-house developed instrument for Physical Research Laboratory (PRL) 1.2m telescope at Mt. Abu India, commissioned in February 2019. Here we present the first science results derived from the low resolution spectroscopy program of a sample of M Dwarfs carried out during the commissioning run of MFOSC-P between February-June 2019. M dwarfs carry great significance for exoplanets searches in habitable zone and are among the promising candidates for the observatory's several ongoing observational campaigns. Determination of their accurate atmospheric properties and fundamental parameters is essential to constrain both their atmospheric and evolutionary models. In this study, we provide a low resolution (R$\sim$500) spectroscopic catalogue of 80 bright M dwarfs (J$<$10) and classify them using their optical spectra. We have also performed the spectral synthesis and $χ^2$ minimisation techniques to determine their fundamental parameters viz. effective temperature and surface gravity by comparing the observed spectra with the most recent BT-Settl synthetic spectra. Spectral type of M dwarfs in our sample ranges from M0 to M5. The derived effective temperature and surface gravity are ranging from 4000 K to 3000 K and 4.5 to 5.5 dex, respectively. In most of the cases, the derived spectral types are in good agreement with previously assigned photometric classification.

astro-ph.SR↗

arXiv2020

Semi-supervised Classification using Attention-based Regularization on Coarse-resolution Data

Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are desired at fine resolutions but available training data is scarce. In this paper, we propose classification algorithms that leverage supervision from coarser resolutions to help train models on finer resolutions. The different resolutions are modeled as different views of the data in a multi-view framework that exploits the complementarity of features across different views to improve models on both views. Unlike traditional multi-view learning problems, the key challenge in our case is that there is no one-to-one correspondence between instances across different views in our case, which requires explicit modeling of the correspondence of instances across resolutions. We propose to use the features of instances at different resolutions to learn the correspondence between instances across resolutions using an attention mechanism.Experiments on the real-world application of mapping urban areas using satellite observations and sentiment classification on text data show the effectiveness of the proposed methods.

cs.LG↗

arXiv2019

A Fast-Optimal Guaranteed Algorithm For Learning Sub-Interval Relationships in Time Series

Traditional approaches focus on finding relationships between two entire time series, however, many interesting relationships exist in small sub-intervals of time and remain feeble during other sub-intervals. We define the notion of a sub-interval relationship (SIR) to capture such interactions that are prominent only in certain sub-intervals of time. To that end, we propose a fast-optimal guaranteed algorithm to find most interesting SIR relationship in a pair of time series. Lastly, we demonstrate the utility of our method in climate science domain based on a real-world dataset along with its scalability scope and obtain useful domain insights.

cs.LG↗

arXiv2019

Mining Novel Multivariate Relationships in Time Series Data Using Correlation Networks

In many domains, there is significant interest in capturing novel relationships between time series that represent activities recorded at different nodes of a highly complex system. In this paper, we introduce multipoles, a novel class of linear relationships between more than two time series. A multipole is a set of time series that have strong linear dependence among themselves, with the requirement that each time series makes a significant contribution to the linear dependence. We demonstrate that most interesting multipoles can be identified as cliques of negative correlations in a correlation network. Such cliques are typically rare in a real-world correlation network, which allows us to find almost all multipoles efficiently using a clique-enumeration approach. Using our proposed framework, we demonstrate the utility of multipoles in discovering new physical phenomena in two scientific domains: climate science and neuroscience. In particular, we discovered several multipole relationships that are reproducible in multiple other independent datasets and lead to novel domain insights.

cs.LG↗

arXiv2019

Automated Monitoring Cropland Using Remote Sensing Data: Challenges and Opportunities for Machine Learning

This paper provides an overview of how recent advances in machine learning and the availability of data from earth observing satellites can dramatically improve our ability to automatically map croplands over long period and over large regions. It discusses three applications in the domain of crop monitoring where ML approaches are beginning to show great promise. For each application, it highlights machine learning challenges, proposed approaches, and recent results. The paper concludes with discussion of major challenges that need to be addressed before ML approaches will reach their full potential for this problem of great societal relevance.

cs.CV↗

arXiv2019

Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles

This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability. Standard RNNs, even when producing superior prediction accuracy, often produce physically inconsistent results and lack generalizability. We further enhance this approach by using a pre-training method that leverages the simulated data from a physics-based model to address the scarcity of observed data. The PGRNN has the flexibility to incorporate additional physical constraints and we incorporate a density-depth relationship. Both enhancements further improve PGRNN performance. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where mechanistic (also known as process-based) models are used, e.g., power engineering, climate science, materials science, computational chemistry, and biomedicine.

physics.comp-ph↗

arXiv2018

Physics Guided Recurrent Neural Networks For Modeling Dynamical Systems: Application to Monitoring Water Temperature And Quality In Lakes

In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems. We will first describe the use of outputs from physics-based models in learning a hybrid-physics-data model. Then, we further incorporate physical knowledge in real-world dynamical systems as additional constraints for training recurrent neural networks. We will apply this approach on modeling lake temperature and quality where we take into account the physical constraints along both the depth dimension and time dimension. By using scientific knowledge to guide the construction and learning the data-driven model, we demonstrate that this method can achieve better prediction accuracy as well as scientific consistency of results.

cs.LG↗