Search

Your search keyword '"Mehta, Piyush M."' showing total 6 results
Start Over Author "Mehta, Piyush M." Publication Year Range This year
6 results on '"Mehta, Piyush M."'

1. Neural-based Video Compression on Solar Dynamics Observatory Images

Author

Khoshkhahtinat, Atefeh, Zafari, Ali, Mehta, Piyush M., Nasrabadi, Nasser M., Thompson, Barbara J., Kirk, Michael S. F., and da Silva, Daniel

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Astrophysics - Instrumentation and Methods for Astrophysics, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Information Theory
Abstract

NASA's Solar Dynamics Observatory (SDO) mission collects extensive data to monitor the Sun's daily activity. In the realm of space mission design, data compression plays a crucial role in addressing the challenges posed by limited telemetry rates. The primary objective of data compression is to facilitate efficient data management and transmission to work within the constrained bandwidth, thereby ensuring that essential information is captured while optimizing the utilization of available resources. This paper introduces a neural video compression technique that achieves a high compression ratio for the SDO's image data collection. The proposed approach focuses on leveraging both temporal and spatial redundancies in the data, leading to a more efficient compression. In this work, we introduce an architecture based on the Transformer model, which is specifically designed to capture both local and global information from input images in an effective and efficient manner. Additionally, our network is equipped with an entropy model that can accurately model the probability distribution of the latent representations and improves the speed of the entropy decoding step. The entropy model leverages a channel-dependent approach and utilizes checkerboard-shaped local and global spatial contexts. By combining the Transformer-based video compression network with our entropy model, the proposed compression algorithm demonstrates superior performance over traditional video codecs like H.264 and H.265, as confirmed by our experimental results.

Published
2024

2. Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis

Author

Khoshkhahtinat, Atefeh, Zafari, Ali, Mehta, Piyush M., and Nasrabadi, Nasser M.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Information Theory, Computer Science - Machine Learning
Abstract

While replacing Gaussian decoders with a conditional diffusion model enhances the perceptual quality of reconstructions in neural image compression, their lack of inductive bias for image data restricts their ability to achieve state-of-the-art perceptual levels. To address this limitation, we adopt a non-isotropic diffusion model at the decoder side. This model imposes an inductive bias aimed at distinguishing between frequency contents, thereby facilitating the generation of high-quality images. Moreover, our framework is equipped with a novel entropy model that accurately models the probability distribution of latent representation by exploiting spatio-channel correlations in latent space, while accelerating the entropy decoding step. This channel-wise entropy model leverages both local and global spatial contexts within each channel chunk. The global spatial context is built upon the Transformer, which is specifically designed for image compression tasks. The designed Transformer employs a Laplacian-shaped positional encoding, the learnable parameters of which are adaptively adjusted for each channel cluster. Our experiments demonstrate that our proposed framework yields better perceptual quality compared to cutting-edge generative-based codecs, and the proposed entropy model contributes to notable bitrate savings., Comment: Accepted by CVPR2024

Published
2024

4. Reduced‐Order Probabilistic Emulation of Physics‐Based Ring Current Models: Application to RAM‐SCB Particle Flux.

Author

Cruz, Alfredo A., Siddalingappa, Rashmi, Mehta, Piyush M., Morley, Steven K., Godinez, Humberto C., and Jordanova, Vania K.

Subjects
SPACE environment, PRINCIPAL components analysis, SOLAR activity, COMPUTATIONAL physics, MAGNETIC fields
Abstract

In this work, we address the computational challenge of large‐scale physics‐based simulation models for the ring current. Reduced computational cost allows for significantly faster than real‐time forecasting, enhancing our ability to predict and respond to dynamic changes in the ring current, valuable for space weather monitoring and mitigation efforts. Additionally, it can also be used for a comprehensive investigation of the system. Thus, we aim to create an emulator for the Ring current‐Atmosphere interactions Model with Self‐Consistent magnetic field (RAM‐SCB) particle flux that not only improves efficiency but also facilitates forecasting with reliable estimates of prediction uncertainties. The probabilistic emulator is built upon the methodology developed by Licata and Mehta (2023), https://doi.org/10.1029/2022sw003345. A novel discrete sampling is used to identify 30 simulation periods over 20 years of solar and geomagnetic activity. Focusing on a subset of particle flux, we use Principal Component Analysis for dimensionality reduction and Long Short‐Term Memory (LSTM) neural networks to perform dynamic modeling. Hyperparameter space was explored extensively resulting in about 5% median symmetric accuracy across all data sets for one‐step dynamic prediction. Using a hierarchical ensemble of LSTMs, we have developed a reduced‐order probabilistic emulator (ROPE) tailored for time‐series forecasting of particle flux in the ring current. This ROPE offers accurate predictions of omnidirectional flux at a single energy with no pitch angle information, providing robust predictions on the test set with an error score below 11% and calibration scores under 8% with bias under 2% providing a significant speed up as compared to the full RAM‐SCB run. Plain Language Summary: Our study tackles the challenges of simulating the ring current in space and time, using a model called RAM‐SCB. By making our simulations faster, we can predict changes in the ring current faster than in real time. This is crucial for monitoring space weather and taking actions to protect satellites and other space assets. Our goal is to create a computer program (emulator) that is efficient, can forecast changes accurately, and gives reliable estimates of its predictions. We follow a method developed by Licata and Mehta (2023), https://doi.org/10.1029/2022sw003345 and extend it to the ring current. Discrete sampling is used to pick specific periods for our simulations. We focus on a part of the simulation data and use an advanced method, a hierarchical ensemble of Long Short‐Term Memory (LSTM) to build our emulator. This is called a ROPE, that can predict the ring current's behavior by providing forecasts with errors below 11% and calibration scores under 8% (how aligned the predictions are with the actual). Key Points: A probabilistic emulator for the ring current‐atmosphere interactions model with self‐consistent magnetic field (RAM‐SCB) particle flux is designed with a focus on reducing computational resources of time and spaceAn ensemble of long‐short term memory captures temporal variations and provides a probabilistic emulatorThe emulator makes a week‐long prediction for single energy flux in ∼20 s providing a significant speed‐up over the full RAM‐SCB run [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

6. Neural-Based Compression Scheme for Solar Image Data

Author

Zafari, Ali, Khoshkhahtinat, Atefeh, Grajeda, Jeremy A., Mehta, Piyush M., Nasrabadi, Nasser M., Boucheron, Laura E., Thompson, Barbara J., Kirk, Michael S. F., and da Silva, Daniel E.

Abstract

Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold decision to make. Stronger compression methods, by distorting the data, can increase data throughput at the cost of accuracy, which could affect scientific analysis of the data. On the other hand, preserving subtle details in the compressed data requires a high amount of data to be transferred, reducing the desired gains from compression. In this work, we propose a neural network-based lossy compression method to be used in NASA's data-intensive imagery missions. We chose NASA's Solar Dynamics Observatory (SDO) mission, which transmits 1.4 TB of data each day as a proof of concept for the proposed algorithm. In this work, we propose an adversarially trained neural network, equipped with local and nonlocal attention modules to capture both the local and global structure of the image resulting in a better tradeoff in rate-distortion (RD) compared with conventional hand-engineered codecs. The RD variational autoencoder used in this work is jointly trained with a channel-dependent entropy model as a shared prior between the analysis and synthesis transforms to make the entropy coding of the latent code more effective. We also studied how optimizing perceptual losses could help our neural compressor to preserve high-frequency details of the data in the reconstructed compressed image. Our neural image compression algorithm outperforms currently-in-use and state-of-the-art codecs, such as JPEG and JPEG-2000, in terms of the RD performance when compressing extreme-ultraviolet (EUV) data. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole detection using our compressed images, and generated consistent segmentations, even at a compression rate of $\sim\! 0.1$ bits per pixel (compared with 8 bits per pixel on the original data) using EUV data from SDO.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results