arXiv subjects

Xinlin Li

Publications and source records attributed to Xinlin Li.

26 records · Page 2Linked to original sources

arXiv2021

Relativistic electron flux model in the outer radiation belt using a neural network approach

We present a machine-learning-based model of relativistic electron fluxes >1.8 MeV using a neural network approach in the Earth's outer radiation belt. The Outer RadIation belt Electron Neural net model for Relativistic electrons (ORIENT-R) uses only solar wind conditions and geomagnetic indices as input. For the first time, we show that the state of the outer radiation belt can be determined using only solar wind conditions and geomagnetic indices, without any initial and boundary conditions. The most important features for determining outer radiation belt dynamics are found to be AL, solar wind flow speed and density, and SYM-H indices. ORIENT-R reproduces out-of-sample relativistic electron fluxes with a correlation coefficient of 0.95 and an uncertainty factor of ~2. ORIENT-R reproduces radiation belt dynamics during an out-of-sample geomagnetic storm with good agreement to the observations. In addition, ORIENT-R was run for a completely out-of-sample period between March 2018 and October 2019 when the AL index ended and was replaced with the predicted AL index (lasp.colorado.edu/~lix). It reproduces electron fluxes with a correlation coefficient of 0.92 and an out-of-sample uncertainty factor of ~3. Furthermore, ORIENT-R captured the trend in the electron fluxes from low-earth-orbit (LEO) SAMPEX, which is a completely out-of-sample dataset both temporally and spatially. In sum, the ORIENT-R model can reproduce transport, acceleration, decay, and dropouts of the outer radiation belt anywhere from short timescales (i.e., geomagnetic storms) and very long timescales (i.e., solar cycle) variations.

physics.space-ph↗

arXiv2021

A Causal Direction Test for Heterogeneous Populations

A probabilistic expert system emulates the decision-making ability of a human expert through a directional graphical model. The first step in building such systems is to understand data generation mechanism. To this end, one may try to decompose a multivariate distribution into product of several conditionals, and evolving a blackbox machine learning predictive models towards transparent cause-and-effect discovery. Most causal models assume a single homogeneous population, an assumption that may fail to hold in many applications. We show that when the homogeneity assumption is violated, causal models developed based on such assumption can fail to identify the correct causal direction. We propose an adjustment to a commonly used causal direction test statistic by using a $k$-means type clustering algorithm where both the labels and the number of components are estimated from the collected data to adjust the test statistic. Our simulation result show that the proposed adjustment significantly improves the performance of the causal direction test statistic for heterogeneous data. We study large sample behaviour of our proposed test statistic and demonstrate the application of the proposed method using real data.

stat.ME↗

arXiv2020

Long-term variations of quasi-trapped and trapped electrons in the inner radiation belt observed by DEMETER and SAMPEX

Electrons in the Earth's radiation belts can be categorized into three populations: precipitating, quasi-trapped and trapped. We use data from the DEMETER and SAMPEX missions and from ground-based neutron monitors (NM) and sunspot observations to investigate the long-term variation of quasi-trapped and trapped sub-MeV electrons on different L shells in the inner belt. DEMETER and SAMPEX measurements span over 17 years and show that at $L \leq 1.14$ the electron flux is anti-correlated with sunspot number, but proportional to the cosmic ray intensity represented by NM count rates, which suggests that electrons at the inner edge of the inner belt are produced by Cosmic Ray Albedo Neutron Decay (CRAND). The solar cycle variation of cosmic rays increased the electron flux at $L \leq 1.14$ by a factor of two from solar maximum at 2001 to solar minimum at 2009. At $L \ge 1.2$, both quasi-trapped and trapped electrons are enhanced during geomagnetic storms and decay to a background level during extended quiet times. At $L>2$, quasi-trapped electrons resemble trapped electrons, with correlation coefficients as high as 0.97, indicating that pitch angle scattering is the dominant process in this region.

physics.space-ph↗

arXiv2020

Tensor train decompositions on recurrent networks

Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily live tasks such as speech, language, video, and multimodal learning. The shift from cloud to edge computation intensifies the need to contain the growth of RNN parameters. Current research on RNN shows that despite the performance obtained on convolutional neural networks (CNN), keeping a good performance in compressed RNNs is still a challenge. Most of the literature on compression focuses on CNNs using matrix product (MPO) operator tensor trains. However, matrix product state (MPS) tensor trains have more attractive features than MPOs, in terms of storage reduction and computing time at inference. We show that MPS tensor trains should be at the forefront of LSTM network compression through a theoretical analysis and practical experiments on NLP task.

cs.LG↗

arXiv2020

Importance of Data Loading Pipeline in Training Deep Neural Networks

Training large-scale deep neural networks is a long, time-consuming operation, often requiring many GPUs to accelerate. In large models, the time spent loading data takes a significant portion of model training time. As GPU servers are typically expensive, tricks that can save training time are valuable.Slow training is observed especially on real-world applications where exhaustive data augmentation operations are required. Data augmentation techniques include: padding, rotation, adding noise, down sampling, up sampling, etc. These additional operations increase the need to build an efficient data loading pipeline, and to explore existing tools to speed up training time. We focus on the comparison of two main tools designed for this task, namely binary data format to accelerate data reading, and NVIDIA DALI to accelerate data augmentation. Our study shows improvement on the order of 20% to 40% if such dedicated tools are used.

cs.CV↗

arXiv2020

Random Bias Initialization Improves Quantized Training

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this accuracy drop exists and call for a better understanding of binary network geometry. We start with analyzing full-precision neural networks with ReLU activation and compare it with its binarized version. This comparison suggests to initialize networks with random bias, a counter-intuitive remedy.

cs.LG↗

arXiv2017

MinXSS-1 CubeSat On-Orbit Pointing and Power Performance: The First Flight of the Blue Canyon Technologies XACT 3-axis Attitude Determination and Control System

The Miniature X-ray Solar Spectrometer (MinXSS) is a 3 Unit (3U) CubeSat designed for a 3-month mission to study solar soft X-ray spectral irradiance. The first of the two flight models was deployed from the International Space Station in 2016 May and operated for one year before its natural deorbiting. This was the first flight of the Blue Canyon Technologies XACT 3-axis attitude determination and control system -- a commercially available, high-precision pointing system. We characterized the performance of the pointing system on orbit including performance at low altitudes where drag torque builds up. We found that the pointing accuracy was 0.0042\degree\ - 0.0117\degree\ (15$''$ - 42$''$, 3$σ$, axis dependent) consistently from 190 km - 410 km, slightly better than the specification sheet states. Peak-to-peak jitter was estimated to be 0.0073\degree\ (10 s$^{-1}$) - 0.0183\degree\ (10 s$^{-1}$) (26$''$ (10 s$^{-1}$) - 66$''$ (10 s$^{-1}$), 3$σ$). The system was capable of dumping momentum until an altitude of 185 km. We found small amounts of sensor degradation in the star tracker and coarse sun sensor. Our mission profile did not require high-agility maneuvers so we are unable to characterize this metric. Without a GPS receiver, it was necessary to periodically upload ephemeris information to update the orbit propagation model and maintain pointing. At 400 km, these uploads were required once every other week. At $\sim$270 km, they were required every day. We also characterized the power performance of our electric power system, which includes a novel pseudo-peak power tracker -- a resistor that limited the current draw from the battery on the solar panels. With 19 30\% efficient solar cells and an 8 W system load, the power balance had 65\% of margin on orbit. We present several recommendations to other CubeSat programs throughout.

astro-ph.IM↗

arXiv2015

Miniature X-Ray Solar Spectrometer (MinXSS) - A Science-Oriented, University 3U CubeSat

The Miniature X-ray Solar Spectrometer (MinXSS) is a 3-Unit (3U) CubeSat developed at the Laboratory for Atmospheric and Space Physics (LASP) at the University of Colorado, Boulder (CU). Over 40 students contributed to the project with professional mentorship and technical contributions from professors in the Aerospace Engineering Sciences Department at CU and from LASP scientists and engineers. The scientific objective of MinXSS is to study processes in the dynamic Sun, from quiet-Sun to solar flares, and to further understand how these changes in the Sun influence the Earth's atmosphere by providing unique spectral measurements of solar soft x-rays (SXRs). The enabling technology providing the advanced solar SXR spectral measurements is the Amptek X123, a commercial-off-the-shelf (COTS) silicon drift detector (SDD). The Amptek X123 has a low mass (~324 g after modification), modest power consumption (~2.50 W), and small volume (6.86 cm x 9.91 cm x 2.54 cm), making it ideal for a CubeSat. This paper provides an overview of the MinXSS mission: the science objectives, project history, subsystems, and lessons learned that can be useful for the small-satellite community.

astro-ph.IM↗