The Final Frontier

Kothari, Vivek; Liberis, Edgar; Lane, Nicholas D.

doi:10.1145/3376897.3377864

Cited by 62 publications

(16 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some data reduction steps could be represented as layers and embedded in the network architecture itself. Recent developments (Kothari et al, 2020) suggest that neural networks inference can be done directly onboard the satellites, very much like it is done on modern smartphones. Our model is light-weight, therefore it can be embedded in the software of the future missions, providing an important but cheap telemetry-wise data product, which could be fully transferred to the ground.…”

Section: Discussionmentioning

confidence: 99%

Automated Classification of Plasma Regions Using 3D Particle Energy Distributions

et al. 2021

View full text Add to dashboard Cite

Over the recent decades, missions such as Cluster, THEMIS, and Magnetospheric Multiscale Mission (MMS), have provided the space physics community with an abundance of in situ measurements across the magnetosphere (MSP) and the solar wind. These regions contain internally distinct plasma and field characteristics, which correspond to important regions and boundaries (e.g., bow shock, magnetopause, foreshock) that are of high scientific interest. On many occasions, scientific investigations are centered explicitly on the physical processes operating at these regions/boundaries. However, before that, they must be manually identified in the data. The current state of available measurements encompasses decades of observations, and manually surveying these data and choosing regions of interest is labor-intensive and often ineffective. The combination of an improvement in the sophistication of machine learning techniques and the more immediately available computational resources, afford a means to classify and sort massive quantities of data. In this paper, we describe a machine learning methodology that can automatically identify separate plasma regions across the upstream solar wind and dayside MSP using MMS data.The principal objective of the MMS (Burch et al., 2016) is to understand the physical processes and the fundamental sequence of events causing magnetic reconnection since it is the central driver of space weather events at Earth and a fundamental plasma process across diverse plasma environments. However, MMS

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Classification of Plasma Regions Using 3D Particle Energy Distributions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Each image contains between 0 and 15 dust storms with a total of 14,974 logged storms. Dust storm centroid locations and their corresponding radius are annotated in a CSV file and the approximate storm area is given in km 2 . An example of the image with the annotated dust storms as an overlay is given in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

“…Matching the current trend on Earth, deep learning solutions are increasingly being utilized to solve problems in space. 2 Additionally, the challenges associated with machine learning on Mars are shared with those on Earth. 3 Of increasing interest is the move towards efficient solutions with little to no sacrifice in accuracy.…”

Section: Introductionmentioning

confidence: 99%

Efficient segmentation of Martian dust storms

Adams

Riley

Depoian

et al. 2023

Unmanned Systems Technology XXV

View full text Add to dashboard Cite

As one of the classic fields within the area of computer vision, image classification and segmentation solutions as topics have expanded exponentially in terms of accuracy and ease of use. On Mars, the atmospheric and surface conditions can lead to the sudden onset of a dust storm, or a more common dust devil, causing a multitude of issues for both equipment and crew. The ability to identify and locate area which should be avoided due to these storms is necessary for mission safety. Many current techniques are not practical due to being hefty and computationally expensive for specific tasks that require the ability for swift deployability onto systems with more stringent constraints. This paper proposes a novel approach to the problem of segmentation by marrying an efficient yet powerful Vision Transformer based model with traditional signal processing techniques to ensure peak performance. With the National Aeronautics and Space Administration (NASA) looking to land a team on Mars, this paper takes on the real time hurdle of classifying and segmenting dust storms within remote satellite equatorial photos, using a model designed to be integrated on any and all future systems, increasing overall mission success.

show abstract

“…DNNs have gained widespread adoption in various fields, encompassing diverse domains such as autonomous vehicles (AVs), healthcare, and space applications. Many of these applications are safety-critical [41][42][43], necessitating the utmost precision and reliability. Nevertheless, misclassification during inference remains a frequent issue in DNNs, and inherent algorithmic inaccuracies often persist throughout all DNN models.…”

Section: Motivationmentioning

confidence: 99%

Investigating the impact of transient hardware faults on deep learning neural network inference

Rahman,

Laskar,

2024

Software Testing Verif & Rel

View full text Add to dashboard Cite

SummarySafety‐critical applications, such as autonomous vehicles, healthcare, and space applications, have witnessed widespread deployment of deep neural networks (DNNs). Inherent algorithmic inaccuracies have consistently been a prevalent cause of misclassifications, even in modern DNNs. Simultaneously, with an ongoing effort to minimize the footprint of contemporary chip design, there is a continual rise in the likelihood of transient hardware faults in deployed DNN models. Consequently, researchers have wondered the extent to which these faults contribute to DNN misclassifications compared to algorithmic inaccuracies. This article delves into the impact of DNN misclassifications caused by transient hardware faults and intrinsic algorithmic inaccuracies in safety‐critical applications. Initially, we enhance a cutting‐edge fault injector, TensorFI, for TensorFlow applications to facilitate fault injections on modern DNN non‐sequential models in a scalable manner. Subsequently, we analyse the DNN‐inferred outcomes based on our defined safety‐critical metrics. Finally, we conduct extensive fault injection experiments and a comprehensive analysis to achieve the following objectives: (1) investigate the impact of different target class groupings on DNN failures and (2) pinpoint the most vulnerable bit locations within tensors, as well as DNN layers accountable for the majority of safety‐critical misclassifications. Our findings regarding different grouping formations reveal that failures induced by transient hardware faults can have a substantially greater impact (with a probability up to 4 higher) on safety‐critical applications compared to those resulting from algorithmic inaccuracies. Additionally, our investigation demonstrates that higher order bit positions in tensors, as well as initial and final layers of DNNs, necessitate prioritized protection compared to other regions.

show abstract

The Final Frontier

Cited by 62 publications

References 3 publications

Automated Classification of Plasma Regions Using 3D Particle Energy Distributions

Automated Classification of Plasma Regions Using 3D Particle Energy Distributions

Efficient segmentation of Martian dust storms

Investigating the impact of transient hardware faults on deep learning neural network inference

Contact Info

Product

Resources

About