Gregory F. Snyder

Aleksandra Ćiprijanović, Diana Kafkes, Gregory Snyder et al.

With increased adoption of supervised deep learning methods for processing and analysis of cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: 1) increased observational noise as represented by higher levels of Poisson noise and 2) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness. Without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy by 23% on data with higher observational noise. Domain adaptation also increases by a factor of ~2.3 the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations.

Gregory Snyder, Sachin Shriwastav, Dylan Morrison-Fogel et al.

Coverage of an inaccessible or challenging region with potential health and safety hazards, such as in a volcanic region, is difficult yet crucial from scientific and meteorological perspectives. Areas contained within the region often provide valuable information of varying importance. We present an algorithm to optimally cover a volcanic region in Hawai`i with an unmanned aerial vehicle (UAV). The target region is assigned with a nonuniform coverage importance score distribution. For a specified battery capacity of the UAV, the optimization problem seeks the path that maximizes the total coverage area and the accumulated importance score while penalizing the revisiting of the same area. Trajectories are generated offline for the UAV based on the available power and coverage information map. The optimal trajectory minimizes the unspent battery power while enforcing that the UAV returns to its starting location. This multi-objective optimization problem is solved by using sequential quadratic programming. The details of the competitive optimization problem are discussed along with the analysis and simulation results to demonstrate the applicability of the proposed algorithm.

Sachin Shriwastav, Gregory Snyder, Zhuoyuan Song

Large-scale environmental sensing with a finite number of mobile sensors is a challenging task that requires a lot of resources and time. This is especially true when features in the environment are spatiotemporally changing with unknown or partially known dynamics. Fortunately, these dynamic features often evolve in a low-dimensional space, making it possible to capture their dynamics sufficiently well with only one or several properly planned mobile sensors. This paper investigates the problem of dynamic compressed sensing of an unsteady flow field, which takes advantage of the inherently low dimensionality of the underlying flow dynamics to reduce number of waypoints for a mobile sensing robot. The optimal sensing waypoints are identified by an iterative compressed sensing algorithm that optimizes the flow reconstruction based on the proper orthogonal decomposition modes. An optimal sampling trajectory is then found to traverse these waypoints while minimizing the energy consumption, time, and flow reconstruction error. Simulation results in an unsteady double gyre flow field is presented to demonstrate the efficacy of the proposed algorithms. Experimental results with an indoor quadcopter are presented to show the feasibility of the resulting trajectory.

Gregory Snyder, Zhuoyuan Song

The Koopman operator is a linear operator that describes the evolution of scalar observables (i.e., measurement functions of the states) in an infinitedimensional Hilbert space. This operator theoretic point of view lifts the dynamics of a finite-dimensional nonlinear system to an infinite-dimensional function space where the evolution of the original system becomes linear. In this paper, we provide a brief summary of the Koopman operator theorem for nonlinear dynamics modeling and focus on analyzing several data-driven implementations using dynamical mode decomposition (DMD) for autonomous and controlled canonical problems. We apply the extended dynamic mode decomposition (EDMD) to identify the leading Koopman eigenfunctions and approximate a finite-dimensional representation of the discovered linear dynamics. This allows us to apply linear control approaches towards nonlinear systems without linearization approximations around fixed points. We can then examine the fidelity of using a linear controller based on a Koopman operator approximated system on under-actuated systems with basic maneuvers. We demonstrate the effectiveness of this theory through numerical simulation on two classic dynamical systems are used to show DMD methods of evaluating and approximating the Koopman operator and its effectiveness at linearizing these systems.

A. Ćiprijanović, D. Kafkes, K. Downey et al.

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques$-$ Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)$-$ and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ${\sim}20\%$. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

A. Ćiprijanović, G. F. Snyder, B. Nord et al.

We investigate and demonstrate the use of convolutional neural networks (CNNs) for the task of distinguishing between merging and non-merging galaxies in simulated images, and for the first time at high redshifts (i.e. $z=2$). We extract images of merging and non-merging galaxies from the Illustris-1 cosmological simulation and apply observational and experimental noise that mimics that from the Hubble Space Telescope; the data without noise form a "pristine" data set and that with noise form a "noisy" data set. The test set classification accuracy of the CNN is $79\%$ for pristine and $76\%$ for noisy. The CNN outperforms a Random Forest classifier, which was shown to be superior to conventional one- or two-dimensional statistical methods (Concentration, Asymmetry, the Gini, $M_{20}$ statistics etc.), which are commonly used when classifying merging galaxies. We also investigate the selection effects of the classifier with respect to merger state and star formation rate, finding no bias. Finally, we extract Grad-CAMs (Gradient-weighted Class Activation Mapping) from the results to further assess and interrogate the fidelity of the classification model.