As the prospect of exceeding global temperature targets set forth in the Paris Agreement becomes more likely, methods of climate intervention are increasingly being explored. With this increased interest there is a need for an assessment process to understand the range of impacts across different scenarios against a set of performance goals in order to support policy decisions. The methodology and tools developed for Performance Assessment (PA) for nuclear waste repositories shares many similarities with the needs and requirements for a framework for climate intervention. Using PA, we outline and test an evaluation framework for climate intervention, called Performance Assessment for Climate Intervention (PACI) with a focus on Stratospheric Aerosol Injection (SAI). We define a set of key technical components for the example PACI framework which include identifying performance goals, the extent of the system, and identifying which features, events, and processes are relevant and impactful to calculating model output for the system given the performance goals. Having identified a set of performance goals, the performance of the system, including uncertainty, can then be evaluated against these goals. Using the Geoengineering Large Ensemble (GLENS) scenario, we develop a set of performance goals for monthly temperature, precipitation, drought index, soil water, solar flux, and surface runoff. The assessment assumes that targets may be framed in the context of risk-risk via a risk ratio, or the ratio of the risk of exceeding the performance goal for the SAI scenario against the risk of exceeding the performance goal for the emissions scenario. From regional responses, across multiple climate variables, it is then possible to assess which pathway carries lower risk relative to the goals. The assessment is not comprehensive but rather a demonstration of the evaluation of an SAI scenario. Future work is needed to develop a more complete assessment that would provide additional simulations to cover parametric and aleatory uncertainty and enable a deeper understanding of impacts, informed scenario selection, and allow further refinements to the approach.
Disastrous consequences can result from defects in manufactured parts—particularly the high consequence parts developed at Sandia. Identifying flaws in as-built parts can be done with nondestructive means, such as X-ray Computed Tomography (CT). However, due to artifacts and complex imagery, the task of analyzing the CT images falls to humans. Human analysis is inherently unreproducible, unscalable, and can easily miss subtle flaws. We hypothesized that deep learning methods could improve defect identification, increase the number of parts that can effectively be analyzed, and do it in a reproducible manner. We pursued two methods: 1) generating a defect-free version of a scan and looking for differences (PandaNet), and 2) using pre-trained models to develop a statistical model of normality (Feature-based Anomaly Detection System: FADS). Both PandaNet and FADS provide good results, are scalable, and can identify anomalies in imagery. In particular, FADS enables zero-shot (training-free) identification of defects for minimal computational cost and expert time. It significantly outperforms prior approaches in computational cost while achieving comparable results. FADS’ core concept has also shown utility beyond anomaly detection by providing feature extraction for downstream tasks.
We propose a nonlinear manifold learning technique based on deep convolutional autoencoders that is appropriate for model order reduction of physical systems in complex geometries. Convolutional neural networks have proven to be highly advantageous for compressing data arising from systems demonstrating a slow-decaying Kolmogorov n-width. However, these networks are restricted to data on structured meshes. Unstructured meshes are often required for performing analyses of real systems with complex geometry. Our custom graph convolution operators based on the available differential operators for a given spatial discretization effectively extend the application space of deep convolutional autoencoders to systems with arbitrarily complex geometry that are typically discretized using unstructured meshes. We propose sets of convolution operators based on the spatial derivative operators for the underlying spatial discretization, making the method particularly well suited to data arising from the solution of partial differential equations. We demonstrate the method using examples from heat transfer and fluid mechanics and show better than an order of magnitude improvement in accuracy over linear methods.
We present a novel graph convolutional layer that is conceptually simple, fast, and provides high accuracy with reduced overfitting. Based on pseudo-differential operators, our layer operates on graphs with relative position information available for each pair of connected nodes. Our layer represents a generalization of parameterized differential operators (previously shown effective for shape correspondence, image segmentation, and dimensionality reduction tasks) to a larger class of graphs. We evaluate our method on a variety of supervised learning tasks, including 2D graph classification using the MNIST and CIFAR-100 datasets and 3D node correspondence using the FAUST dataset. We also introduce a superpixel graph version of the lesion classification task using the ISIC 2016 challenge dataset and evaluate our layer versus other state-of-the-art graph convolutional network architectures.The new layer outperforms multiple recent architectures on graph classification tasks using the MNIST and CIFAR-100 superpixel datasets. For the ISIC dataset, we outperform all other graph neural networks examined as well as all of the submissions to the original ISIC challenge despite the best of those models having more than 200 times as many parameters as our model.
Thermal sprayed metal coatings are used in many industrial applications, and characterizing the structure and performance of these materials is vital to understanding their behavior in the field. X-ray Computed Tomography (CT) machines enable volumetric, nondestructive imaging of these materials, but precise segmentation of this grayscale image data into discrete material phases is necessary to calculate quantities of interest related to material structure. In this work, we present a methodology to automate the CT segmentation process as well as quantify uncertainty in segmentations via deep learning. Neural networks (NNs) are shown to accurately segment full resolution CT scans of thermal sprayed materials and provide maps of uncertainty that conservatively bound the predicted geometry. These bounds are propagated through calculations of material properties such as porosity that may provide an understanding of anticipated behavior in the field.
Automatic detection of defects in as-built parts is a challenging task due to the large number of potential manufacturing flaws that can occur. X-Ray computed tomography (CT) can produce high-quality images of the parts in a non-destructive manner. The images, however, are grayscale valued, often have artifacts and noise, and require expert interpretation to spot flaws. In order for anomaly detection to be reproducible and cost effective, an automated method is needed to find potential defects. Traditional supervised machine learning techniques fail in the high reliability parts regime due to large class imbalance: there are often many more examples of well-built parts than there are defective parts. This, coupled with the time expense of obtaining labeled data, motivates research into unsupervised techniques. In particular, we build upon the AnoGAN and f-AnoGAN work by T. Schlegl et al. and created a new architecture called PandaNet. PandaNet learns an encoding function to a latent space of defect-free components and a decoding function to reconstruct the original image. We restrict the training data to defect-free components so that the encode-decode operation cannot learn to reproduce defects well. The difference between the reconstruction and the original image highlights anomalies that can be used for defect detection. In our work with CT images, PandaNet successfully identifies cracks, voids, and high z inclusions. Beyond CT, we demonstrate PandaNet working successfully with little to no modifications on a variety of common 2-D defect datasets both in color and grayscale.
Development of new materials and predictive capabilities of component performance hinges on the ability to accurately digitize "as-built" geometries. X-ray computed tomography (CT) offers a non-destructive method of capturing these details but current methodologies are unable to produce the required fidelity for critical component certification. This project focused on discovering the limitations of existing CT reconstruction algorithms and exploring machine learning (ML) methodologies to overcome these limitations. We found that existing CT reconstruction methods are insufficient for Sandia's critical component certification process and that ML algorithms are a viable path forward to improving the quality of CT images.