An official website of the United States government
Risk assessment of infrastructure exposed to ice-rich permafrost hazards is essential for climate change adaptation in the Arctic. As this process requires up-to-date, comprehensive, high-resolution maps of human-built infrastructure, gaps in such geospatial information and knowledge of the applications required to produce it must be addressed. Therefore, this study highlights the ongoing development of a deep learning approach to efficiently map the Arctic built environment by detecting nine different types of structures (detached houses, row houses, multi-story blocks, non-residential buildings, roads, runways, gravel pads, pipelines, and storage tanks) from recently-acquired Maxar commercial satellite imagery (<1 m resolution). We conducted a multi-objective comparison, focusing on generalization performance and computational cost, of nine different semantic segmentation architectures. K-fold cross validation was used to estimate the average F1-score of each architecture and the Friedman Aligned Ranks test with the Bergmann-Hommel posthoc procedure was applied to test for significant differences in generalization performance. ResNet-50-UNet++ performs significantly better than five out of the other eight candidate architectures; no significant difference was found in the pairwise comparisons of ResNet-50-UNet++ to ResNet-50-MANet, ResNet-101-MANet, and ResNet-101-UNet++. We then conducted a high-performance computing scaling experiment to compare the number of service units and runtime required for model inferencing on a hypothetical pan- Arctic scale dataset. We found that the ResNet-50-UNet++ model could save up to ~ 54% on service unit expenditure, or ~ 18% on runtime, when considering operational deployment of our mapping approach. Our results suggest that ResNet-50-UNet++ could be the most suitable architecture (out of the nine that were examined) for deep learning-enabled Arctic infrastructure mapping efforts. Overall, our findings regarding the differences between the examined CNN architectures and our methodological framework for multi-objective architecture comparison can provide a foundation that may propel future pan-Arctic GeoAI mapping efforts of infrastructure.
more »
« less
Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields?
We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (Keff) of a binary K grid. A deep learning algorithm (UNET) can infer Keff with extremely high accuracy (R2 > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained directly on this information. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems.
more »
« less
- Award ID(s):
- 1740858
- PAR ID:
- 10294761
- Date Published:
- Journal Name:
- Water
- Volume:
- 13
- Issue:
- 12
- ISSN:
- 2073-4441
- Page Range / eLocation ID:
- 1668
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In this paper, we present a technique for estimating the geometry and reflectance of objects using only a camera, flashlight, and optionally a tripod. We propose a simple data capture technique in which the user goes around the object, illuminating it with a flashlight and capturing only a few images. Our main technical contribution is the introduction of a recursive neural architecture, which can predict geometry and reflectance at 2 k ×2 k resolution given an input image at 2 k ×2 k and estimated geometry and reflectance from the previous step at 2 k−1 ×2 k−1 . This recursive architecture, termed RecNet, is trained with 256×256 resolution but can easily operate on 1024×1024 images during inference. We show that our method produces more accurate surface normal and albedo, especially in regions of specular highlights and cast shadows, compared to previous approaches, given three or fewer input images.more » « less
-
Abstract Objective. UNet-based deep-learning (DL) architectures are promising dose engines for traditional linear accelerator (Linac) models. Current UNet-based engines, however, were designed differently with various strategies, making it challenging to fairly compare the results from different studies. The objective of this study is to thoroughly evaluate the performance of UNet-based models on magnetic-resonance (MR)-Linac-based intensity-modulated radiation therapy (IMRT) dose calculations.Approach. The UNet-based models, including the standard-UNet, cascaded-UNet, dense-dilated-UNet, residual-UNet, HD-UNet, and attention-aware-UNet, were implemented. The model input is patient CT and IMRT field dose in water, and the output is patient dose calculated by DL model. The reference dose was calculated by the Monaco Monte Carlo module. Twenty training and ten test cases of prostate patients were included. The accuracy of the DL-calculated doses was measured using gamma analysis, and the calculation efficiency was evaluated by inference time.Results. All the studied models effectively corrected low-accuracy doses in water to high-accuracy patient doses in a magnetic field. The gamma passing rates between reference and DL-calculated doses were over 86% (1%/1 mm), 98% (2%/2 mm), and 99% (3%/3 mm) for all the models. The inference times ranged from 0.03 (graphics processing unit) to 7.5 (central processing unit) seconds. Each model demonstrated different strengths in calculation accuracy and efficiency; Res-UNet achieved the highest accuracy, HD-UNet offered high accuracy with the fewest parameters but the longest inference, dense-dilated-UNet was consistently accurate regardless of model levels, standard-UNet had the shortest inference but relatively lower accuracy, and the others showed average performance. Therefore, the best-performing model would depend on the specific clinical needs and available computational resources.Significance. The feasibility of using common UNet-based models for MR-Linac-based dose calculations has been explored in this study. By using the same model input type, patient training data, and computing environment, a fair assessment of the models’ performance was present.more » « less
-
Spatial interpolation techniques play an important role in hydrology, as many point observations need to be interpolated to create continuous surfaces. Despite the availability of several tools and methods for interpolating data, not all of them work consistently for hydrologic applications. One of the techniques, the Laplace Equation, which is used in hydrology for creating flownets, has rarely been used for data interpolation. The objective of this study is to examine the efficiency of Laplace formulation (LF) in interpolating data used in hydrologic applications (hydrologic data) and compare it with other widely used methods such as inverse distance weighting (IDW), natural neighbor, and ordinary kriging. The performance of LF interpolation with other methods is evaluated using quantitative measures, including root mean squared error (RMSE) and coefficient of determination (R2) for accuracy, visual assessment for surface quality, and computational cost for operational efficiency and speed. Data related to surface elevation, river bathymetry, precipitation, temperature, and soil moisture are used for different areas in the United States. RMSE and R2 results show that LF is comparable to other methods for accuracy. LF is easy to use as it requires fewer input parameters compared to inverse distance weighting (IDW) and Kriging. Computationally, LF is faster than other methods in terms of speed when the datasets are not large. Overall, LF offers a robust alternative to existing methods for interpolating various hydrologic data. Further work is required to improve its computational efficiency.more » « less
-
Abstract Magnetized turbulence is ubiquitous in many astrophysical and terrestrial plasmas but no universal theory exists. Even the detailed energy dynamics in magnetohydrodynamic (MHD) turbulence are still not well understood. We present a suite of subsonic, super-Alfvénic, high plasma beta MHD turbulence simulations that only vary in their dynamical range, i.e., in their separation between the large-scale forcing and dissipation scales, and their dissipation mechanism (implicit large eddy simulation, ILES, and direct numerical simulation (DNS)). Using an energy transfer analysis framework we calculate the effective numerical viscosities and resistivities, and demonstrate that all ILES calculations of MHD turbulence are resolved and correspond to an equivalent visco-resistive MHD turbulence calculation. Increasing the number of grid points used in an ILES corresponds to lowering the dissipation coefficients, i.e., larger (kinetic and magnetic) Reynolds numbers for a constant forcing scale. Independently, we use this same framework to demonstrate that—contrary to hydrodynamic turbulence—the cross-scale energy fluxes are not constant in MHD turbulence. This applies both to different mediators (such as cascade processes or magnetic tension) for a given dynamical range as well as to a dependence on the dynamical range itself, which determines the physical properties of the flow. We do not observe any indication of convergence even at the highest resolution (largest Reynolds numbers) simulation at 20483cells, calling into question whether an asymptotic regime in MHD turbulence exists, and, if so, what it looks like.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/w13121668
