Crystalline materials exhibit long-range ordered lattice unit, within which resides nonperiodic structural features called defects. These crystallographic defects play a vital role in determining the physical and mechanical properties of a wide range of material systems. While computer vision has demonstrated success in recognizing feature patterns in images with well-defined contrast, automated identification of nanometer scale crystallographic defects in electron micrographs governed by complex contrast mechanisms is still a challenging task. Here, building upon an advanced defect imaging mode that offers high feature clarity, we introduce DefectSegNet - a new convolutional neural network (CNN) architecture that performs semantic segmentation of three common crystallographic defects in structural alloys: dislocation lines, precipitates and voids. Results from supervised training on a small set of high-quality defect images of steels show high pixel-wise accuracy across all three types of defects: 91.60 ± 1.77% on dislocations, 93.39 ± 1.00% on precipitates, and 98.85 ± 0.56% on voids. We discuss the sources of uncertainties in CNN prediction and the training data in terms of feature density, representation and homogeneity and their effects on deep learning performance. Further defect quantification using DefectSegNet prediction outperforms human expert average, presenting a promising new workflow for fast and statistically meaningful quantification of materials defects.
A novel deep architecture, the tensor deep stacking network (T-DSN), is presented. The T-DSN consists of multiple, stacked blocks, where each block contains a bilinear mapping from two hidden layers to the output layer, using a weight tensor to incorporate higher order statistics of the hidden binary (([0,1])) features. A learning algorithm for the T-DSN's weight matrices and tensors is developed and described in which the main parameter estimation burden is shifted to a convex subproblem with a closed-form solution. Using an efficient and scalable parallel implementation for CPU clusters, we train sets of T-DSNs in three popular tasks in increasing order of the data size: handwritten digit recognition using MNIST (60k), isolated state/phone classification and continuous phone recognition using TIMIT (1.1 m), and isolated phone classification using WSJ0 (5.2 m). Experimental results in all three tasks demonstrate the effectiveness of the T-DSN and the associated learning methods in a consistent manner. In particular, a sufficient depth of the T-DSN, a symmetry in the two hidden layers structure in each T-DSN block, our model parameter learning algorithm, and a softmax layer on top of T-DSN are shown to have all contributed to the low error rates observed in the experiments for all three tasks.
We train a convolutional neural network, APOGEE Net, to predict Teff, , and, for some stars, [Fe/H], based on the APOGEE spectra. This is the first pipeline adapted for these data that is capable of estimating these parameters in a self-consistent manner not only for low-mass stars, (such as main-sequence dwarfs, pre-main-sequence stars, and red giants), but also high-mass stars with Teff in excess of 50,000 K, including hot dwarfs and blue supergiants. The catalog of ∼650,000 stars presented in this paper allows for a detailed investigation of the star-forming history of not just the Milky Way, but also of the Magellanic clouds, as different type of objects tracing different parts of these galaxies can be more cleanly selected through their distinct placement in Teff– parameter space than in previous APOGEE catalogs produced through different pipelines.
A reliable census of pre-main-sequence stars with known ages is critical to our understanding of early stellar evolution, but historically there has been difficulty in separating such stars from the field. We present a trained neural network model, Sagitta, that relies on Gaia DR2 and 2 Micron All-Sky Survey photometry to identify pre-main-sequence stars and to derive their age estimates. Our model successfully recovers populations and stellar properties associated with known star-forming regions up to five kpc. Furthermore, it allows for a detailed look at the star-forming history of the solar neighborhood, particularly at age ranges to which we were not previously sensitive. In particular, we observe several bubbles in the distribution of stars, the most notable of which is a ring of stars associated with the Local Bubble, which may have common origins with Gould’s Belt.
17 October 2024 in Journal of Advances in Modeling Earth Systems
Earth system models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low‐cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low‐cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio‐temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.