skip to main content

Explore Research Products in the NSF-PAR

Title: From Images to Hydrologic Networks - Understanding the Arctic Landscape with Graphs
Remote sensing-based Earth Observation plays an important role in assessing environmental changes throughout our planet. As an image-heavy domain, the evaluation of the data strongly focuses on statistical and pixel-based spatial analysis methods. However, considering the complexity of our Earth system, there are some environmental structures and dependencies that are not possible to accurately describe with these traditional image analysis approaches. One example for such a limitation is the representation of (spatial) networks and their characteristics. In this study, we thus propose a computer vision approach that enables the representation of semantic information gained from images as graphs. As an example, we investigate digital terrain models of Arctic permafrost landscapes with its very characteristic polygonal patterned ground. These regular patterns, which are clearly visible in high-resolution image and elevation data, are formed by subsurface ice bodies that are very vulnerable to rising temperatures in a warming Arctic. Observing these networks’ topologies and metrics in space and time with graph analysis thus allows insights into the landscape’s complex geomorphology, hydrology, and ecology and therefore helps to quantify how they interact with climate change. We show that results extracted with this analytical and highly automated approach are in line with those gathered from other manual studies or from manual validation. Thus, with this approach, we introduce a method that, for the first time, enables upscaling of such terrain and network analysis to potentially pan-Arctic scales where collecting in-situ field data is strongly limited.  more » « less
Award ID(s):
1929170
NSF-PAR ID:
10351261
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
SSDBM 2022: 34th International Conference on Scientific and Statistical Database Management
Volume:
6
Page Range / eLocation ID:
1 to 10
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al ( , Remote Sensing)
    null (Ed.)
    Very high spatial resolution commercial satellite imagery can inform observation, mapping, and documentation of micro-topographic transitions across large tundra regions. The bridging of fine-scale field studies with pan-Arctic system assessments has until now been constrained by a lack of overlap in spatial resolution and geographical coverage. This likely introduced biases in climate impacts on, and feedback from the Arctic region to the global climate system. The central objective of this exploratory study is to develop an object-based image analysis workflow to automatically extract ice-wedge polygon troughs from very high spatial resolution commercial satellite imagery. We employed a systematic experiment to understand the degree of interoperability of knowledge-based workflows across distinct tundra vegetation units—sedge tundra and tussock tundra—focusing on the same semantic class. In our multi-scale trough modelling workflow, we coupled mathematical morphological filtering with a segmentation process to enhance the quality of image object candidates and classification accuracies. Employment of the master ruleset on sedge tundra reported classification accuracies of correctness of 0.99, completeness of 0.87, and F1 score of 0.92. When the master ruleset was applied to tussock tundra without any adaptations, classification accuracies remained promising while reporting correctness of 0.87, completeness of 0.77, and an F1 score of 0.81. Overall, results suggest that the object-based image analysis-based trough modelling workflow exhibits substantial interoperability across the terrain while producing promising classification accuracies. From an Arctic earth science perspective, the mapped troughs combined with the ArcticDEM can allow hydrological assessments of lateral connectivity of the rapidly changing Arctic tundra landscape, and repeated mapping can allow us to track fine-scale changes across large regions and that has potentially major implications on larger riverine systems. 
    more » « less
  2. ; ; ; ; ( , ACM Transactions on Intelligent Systems and Technology)
    Given earth imagery with spectral features on a terrain surface, this paper studies surface segmentation based on both explanatory features and surface topology. The problem is important in many spatial and spatiotemporal applications such as flood extent mapping in hydrology. The problem is uniquely challenging for several reasons: first, the size of earth imagery on a terrain surface is often much larger than the input of popular deep convolutional neural networks; second, there exists topological structure dependency between pixel classes on the surface, and such dependency can follow an unknown and non-linear distribution; third, there are often limited training labels. Existing methods for earth imagery segmentation often divide the imagery into patches and consider the elevation as an additional feature channel. These methods do not fully incorporate the spatial topological structural constraint within and across surface patches and thus often show poor results, especially when training labels are limited. Existing methods on semi-supervised and unsupervised learning for earth imagery often focus on learning representation without explicitly incorporating surface topology. In contrast, we propose a novel framework that explicitly models the topological skeleton of a terrain surface with a contour tree from computational topology, which is guided by the physical constraint (e.g., water flow direction on terrains). Our framework consists of two neural networks: a convolutional neural network (CNN) to learn spatial contextual features on a 2D image grid, and a graph neural network (GNN) to learn the statistical distribution of physics-guided spatial topological dependency on the contour tree. The two models are co-trained via variational EM. Evaluations on the real-world flood mapping datasets show that the proposed models outperform baseline methods in classification accuracy, especially when training labels are limited. 
    more » « less
  3. ; ( , Remote Sensing)
    ArcticDEM provides the public with an unprecedented opportunity to access very high-spatial resolution digital elevation models (DEMs) covering the pan-Arctic surfaces. As it is generated from stereo-pairs of optical satellite imagery, ArcticDEM represents a mixture of a digital surface model (DSM) over a non-ground areas and digital terrain model (DTM) at bare grounds. Reconstructing DTM from ArcticDEM is thus needed in studies requiring bare ground elevation, such as modeling hydrological processes, tracking surface change dynamics, and estimating vegetation canopy height and associated forest attributes. Here we proposed an automated approach for estimating DTM from ArcticDEM in two steps: (1) identifying ground pixels from WorldView-2 imagery using a Gaussian mixture model (GMM) with local refinement by morphological operation, and (2) generating a continuous DTM surface using ArcticDEMs at ground locations and spatial interpolation methods (ordinary kriging (OK) and natural neighbor (NN)). We evaluated our method at three forested study sites characterized by different canopy cover and topographic conditions in Livengood, Alaska, where airborne lidar data is available for validation. Our results demonstrate that (1) the proposed ground identification method can effectively identify ground pixels with much lower root mean square errors (RMSEs) (<0.35 m) to the reference data than the comparative state-of-the-art approaches; (2) NN performs more robustly in DTM interpolation than OK; (3) the DTMs generated from NN interpolation with GMM-based ground masks decrease the RMSEs of ArcticDEM to 0.648 m, 1.677 m, and 0.521 m for Site-1, Site-2, and Site-3, respectively. This study provides a viable means of deriving high-resolution DTM from ArcticDEM that will be of great value to studies focusing on the Arctic ecosystems, forest change dynamics, and earth surface processes. 
    more » « less
  4. ( , Proceeding of the 17th World Conference on Earthquake Engineering)
    null (Ed.)
    In the aftermath of earthquake events, reconnaissance teams are deployed to gather vast amounts of images, moving quickly to capture perishable data to document the performance of infrastructure before they are destroyed. Learning from such data enables engineers to gain new knowledge about the real-world performance of structures. This new knowledge, extracted from such visual data, is critical to mitigate the risks (e.g., damage and loss of life) associated with our built environment in future events. Currently, this learning process is entirely manual, requiring considerable time and expense. Thus, unfortunately, only a tiny portion of these images are shared, curated, and actually utilized. The power of computers and artificial intelligence enables a new approach to organize and catalog such visual data with minimal manual effort. Here we discuss the development and deployment of an organizational system to automate the analysis of large volumes of post-disaster visual data, images. Our application, named the Automated Reconnaissance Image Organizer (ARIO), allows a field engineer to rapidly and automatically categorize their reconnaissance images. ARIO exploits deep convolutional neural networks and trained classifiers, and yields a structured report combined with useful metadata. Classifiers are trained using our ground-truth visual database that includes over 140,000 images from past earthquake reconnaissance missions to study post-disaster buildings in the field. Here we discuss the novel deployment of the ARIO application within a cloud-based system that we named VISER (Visual Structural Expertise Replicator), a comprehensive cloud-based visual data analytics system with a novel Netflix-inspired technical search capability. Field engineers can exploit this research and our application to search an image repository for visual content. We anticipate that these tools will empower engineers to more rapidly learn new lessons from earthquakes using reconnaissance data. 
    more » « less
  5. ; ; ; ; ; ; ; ; ( , Global Change Biology)
    Abstract

    The terrestrial carbon (C) cycle has been commonly represented by a series of C balance equations to track C influxes into and effluxes out of individual pools in earth system models (ESMs). This representation matches our understanding of C cycle processes well but makes it difficult to track model behaviors. It is also computationally expensive, limiting the ability to conduct comprehensive parametric sensitivity analyses. To overcome these challenges, we have developed a matrix approach, which reorganizes the C balance equations in the originalESMinto one matrix equation without changing any modeled C cycle processes and mechanisms. We applied the matrix approach to the Community Land Model (CLM4.5) with vertically‐resolved biogeochemistry. The matrix equation exactly reproduces litter and soil organic carbon (SOC) dynamics of the standardCLM4.5 across different spatial‐temporal scales. The matrix approach enables effective diagnosis of system properties such as C residence time and attribution of global change impacts to relevant processes. We illustrated, for example, the impacts ofCO2fertilization on litter andSOCdynamics can be easily decomposed into the relative contributions from C input, allocation of external C into different C pools, nitrogen regulation, altered soil environmental conditions, and vertical mixing along the soil profile. In addition, the matrix tool can accelerate model spin‐up, permit thorough parametric sensitivity tests, enable pool‐based data assimilation, and facilitate tracking and benchmarking of model behaviors. Overall, the matrix approach can make a broad range of future modeling activities more efficient and effective.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email