Search NASA⌕ Search

Engineering topics

Lunga, Dalton

Publications and source records attributed to Lunga, Dalton.

At least 37 records · Page 2

SpaceNet 8 - The Detection of Flooded Roads and Buildings

The frequency and intensity of natural disasters (i.e. wildfires, storms, floods) has increased over recent decades. Extreme weather can often be linked to climate change, and human population expansion and urbanization have led to a growing risk. In particular floods due to large amounts of rainfall are of rising severity and are causing loss of life, destruction of buildings and infrastructure, erosion of arable land, and environmental hazards around the world. Expanding urbanization along rivers and creeks often includes opening flood plains for building construction and river straightening and dredging speeding up the flow of water. In a flood event, rapid response is essential which requires knowledge which buildings are susceptible to flooding and which roads are still accessible. To this aim, SpaceNet 8 is the first remote sensing machine learning training dataset combining building footprint detection, road network extraction, and flood detection covering 850km 2, including 32k buildings and 1,300km roads of which 13% and 15% are flooded, respectively.

Arndt, Jacob↗

Model Assumptions and Data Characteristics: Impacts on Domain Adaptation in Building Segmentation

Studies on domain adaptation (DA) for remote sensing (RS) imagery analysis lack consistency in selection and description of evaluation scenarios. Without properly characterizing datasets, model assumptions, and evaluation scenarios, it is difficult to objectively compare DA methods and reach conclusions about their suitability across different applications. With this motivation, this work seeks to empirically assess to which extent the interaction between data characteristics and model assumptions influences the effectiveness of DA methods. Using the widely explored task of building footprint segmentation as a case study, we perform a large-scale study across over 200 DA scenarios that include variations across view angles, areas observed, and sensors used for data acquisition. Rather than adopting different model architectures or optimization criteria, we contrast the performances of two DA methods based on adversarial learning that differ only in their assumptions about source and target domains. Informed by metadata and data characteristics unveiled using traditional computer vision (CV) techniques as well as pretrained deep models, we provide a detailed meta-analysis of experiments highlighting the importance of accurately considering data assumptions for DA in RS segmentation tasks. As demonstrated by a “cherry-picking” exercise, different claims regarding which model is best could be made by selecting different subsets of evaluation scenarios. While well-calibrated assumptions can be beneficial, mismatching assumptions can lead to negative biases in DA applications. Furthermore, this study intends to motivate the community toward more consistent evaluation protocols while providing recommendations and insights toward creating novel benchmark datasets, documenting data characteristics, application-specific knowledge, and model assumptions.

42 ENGINEERING↗

2021 GeoAI Workshop Report: The Trillion Pixel Challenge

The convergence of geospatial big data with advancements from artificial intelligence, cloud infrastructure, and high-performance computing continues to revolutionize mapping and analysis of Earth's surface in unprecedented detail. Rapid innovations in sensing technologies will soon collect geospatial data in even higher resolution and throughput. These developments offer the potential for breakthroughs in science, policy, and national security via end-to-end GeoAI systems that can provide fresh insights into how humans occupy and alter their environment over time. At the 2021 GeoAI Trillion Pixel workshop, international subject matter experts from government, academia, industry, and nonprofit organizations gathered virtually to discuss the Trillion Pixel GeoAI Challenge. The event focused on six major themes currently influencing scientific innovation and breakthroughs. Particular focus was paid to societal impacts. As an additional takeaway message, the gathering identified remaining application gaps and challenges that are in need of stronger community partnerships and collaborations.

58 GEOSCIENCES↗

Distributed Training for High Resolution Images: A Domain and Spatial Decomposition Approach

In this work we developed two Pytorch libraries using the PyTorch RPC interface for distributed deep learning approaches on high resolution images. The spatial decomposition library allows for distributed training on very large images, which otherwise wouldn’t be possible on a single GPU. The domain parallelism library allows for distributed training across multiple domain unlabeled data, by leveraging the domain separation architecture. Both of those libraries where tested on the Summit supercomputer at Oak Ridge National Laboratory at a moderate scale.

Tsaris, Aristeidis (aris)↗

FAIR Interfaces for Geospatial Scientific Data Searches

Several factors must be considered in designing a highly accurate, reliable, scalable, and user-friendly geospatial data search interfaces. This paper examines four critical questions that ought to be considered during design phase: (1) Is the search interface or API that provides the search capability useable by both humans and machines? (2) Are the results consistent and reliable? (3) Is the output response format free to use, community-defined, and non-propriety? (4) Does the API clearly state the usage clauses? This paper discusses how certain data repositories at the US Department of Energy's Oak Ridge National Laboratory apply FAIR data principles to enable geospatial searches and address the above-mentioned questions.

Devarakonda, Ranjeet↗

Semi-automated Design of Artificial Intelligence Earth Systems Models

Prediction and observation of water cycles at various scales involve not only patterns isolated in space and time, but also modeling of complex spatio-temporal relationships across multiple domains. For instance, evapotranspiration (ET) and leaf area indexes (LAI) are two parameters that are needed to accurately model and understand land-atmosphere processes. Accurate assessments of ET and LAI are critical for understanding hydrological processes, deforestation, crop yield, and irrigation impacts. However, ET estimates for global simulations are available at very coarse spatial resolution. They are usually derived from satellite data based on broad plant functional types (PFTs), which fail to capture fine-scale variations because of changes in vegetation type across the globe. Similarly LAI estimates have typically been derived from vegetation indices at global scales or estimated locally using physical models, both of which suffer from a range of uncertainties that impact model sensitivity. The new era of AI model development for Earth systems (ES) calls for data-driven methods that provide domain scientists with uncertainty-aware estimations of biophysical parameters such as ET and LAI in a generalizable, interpretable, and discoverable manner.

54 ENVIRONMENTAL SCIENCES↗

Computer-aided Abnormality Detection in Chest Radiographs in a Clinical Setting via Domain-adaptation

Deep learning (DL) models are being deployed at medical centers to aid radiologists for diagnosis of lung conditions from chest radiographs. Such models are often trained on a large volume of publicly available labeled radiographs. These pre-trained DL models’ ability to generalize in clinical settings is poor because of the changes in data distributions between publicly available and privately held radiographs. In chest radiographs, the heterogeneity in distributions arises from the diverse conditions in X-ray equipment and their configurations used for generating the images. In the machine learning community, the challenges posed by the heterogeneity in the data generation source is known as domain shift, which is a mode shift in the generative model. In this work, we introduce a domain-shift detection and removal method to overcome this problem. Our experimental results show the proposed method’s effectiveness in deploying a pre-trained DL model for abnormality detection in chest radiographs in a clinical setting.

Dubey, Abhishek↗

Large-Scale Classification of Urban Structural Units From Remote Sensing Imagery

Remote sensing in combination with deep learning has become instrumental for efficiently and accurately classifying land-use and land-cover across large geographic areas. These technologies have also been successful in characterizing urban environments in terms of their structural units, structure types, or morphological regions. In these approaches, an urban area is partitioned into regions that exhibit homogeneous physical characteristics. However, existing approaches are typically limited to a single city, use inconsistent typologies, and lack scalability and generalization capacity. In this article, we propose an urban structural units categorization scheme and demonstrate its utility by applying it to 13 cities. Inspired by the lack of scalability and generalization capacity in urban structural units mapping, we extend the reach of deep learning and conduct a set of classification experiments in all 13 cities. These experiments offer insights into the strengths and limitations of deep neural networks for classifying urban structural units over diverse geographic regions and on heterogeneous collections of satellite imagery. The efficacy of the proposed deep learning approach is compared to a baseline method of multiscale image features and support vector machines. Our validation on five cities shows that better performance is achieved with deep neural networks. Additionally, we evaluate the impact of input size, model depth, and spatial pyramid pooling to assess the generalization capacity of deep neural networks.

47 OTHER INSTRUMENTATION↗

Mapping Human Dynamics

Researchers at Oak Ridge National Laboratory are mapping the global footprints of human activity with unprecedented spatiotemporal resolution. With a global population now approaching 8 billion people, this herculean effort demands advanced machine learning, artificial intelligence, and one of the world’s fastest supercomputers.

Rose, Amy↗

Learning to Count Grave Sites for Cemetery Observation Models With Satellite Imagery

Understanding how people occupy open spaces is important for research in support of population modeling, policy, national security, emergency response, and sustainability. For the past decade, there has been an increase in research toward capturing and reporting population dynamics and patterns of life at the building level and in some open public spaces such as cemeteries and parks. This is done through observation models developed from local sociocultural information acquired at various spatiotemporal scales to inform night, day, and episodic population occupancy estimates (people/1000 sq ft). Sociocultural information for cemeteries and parks is scarcely available and often collected manually. The process is not only marred by inconsistencies but is laborious and time consuming. In this study, we leverage convolutional neural networks (CNNs) and satellite imagery to derive grave site counts as proxy variables to support scalable and accurate sociocultural data required in a population observation model. Through a hybrid workflow (weak localization plus regression model), we characterize a large scale automation process to counting of grave sites. We evaluate and demonstrate the efficacy of proposed workflow using out-of-data set large satellite imagery and establish its broader impact on cemetery observation models.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Sampling Subjective Polygons for Patch-Based Deep Learning Land-Use Classification in Satellite Images

Model generalization remains a key challenge in the analysis of large amounts of heterogeneous satellite image data. One major limiting factor in developing generalizable models, in the context of supervised learning, is the lack of high quality training datasets. A model's capacity to perform well on new data is often inhibited by imbalance and bias in the data that was used for training. This is especially a problem when using convolutional neural networks to classify urban land-use in satellite images. Notable dataset imbalance issues in this application include land-use type imbalance and image scene imbalance. To begin understanding these dataset imbalance problems in more detail, we develop and test a number of sampling methods for generating training image datasets from subjective training polygons for urban land-use classification. We investigate sampling at different point densities as a means to reduce content repetition and therefore content imbalance and bias in the training image dataset.

Arndt, Jacob↗

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗

Accounting for Training Data Error in Machine Learning Applied to Earth Observations

Remote sensing, or Earth Observation (EO), is increasingly used to understand Earth system dynamics and create continuous and categorical maps of biophysical properties and land cover, especially based on recent advances in machine learning (ML). ML models typically require large, spatially explicit training datasets to make accurate predictions. Training data (TD) are typically generated by digitizing polygons on high spatial-resolution imagery, by collecting in situ data, or by using pre-existing datasets. TD are often assumed to accurately represent the truth, but in practice almost always have error, stemming from (1) sample design, and (2) sample collection errors. The latter is particularly relevant for image-interpreted TD, an increasingly commonly used method due to its practicality and the increasing training sample size requirements of modern ML algorithms. TD errors can cause substantial errors in the maps created using ML algorithms, which may impact map use and interpretation. Despite these potential errors and their real-world consequences for map-based decisions, TD error is often not accounted for or reported in EO research. Here we review the current practices for collecting and handling TD. We identify the sources of TD error, and illustrate their impacts using several case studies representing different EO applications (infrastructure mapping, global surface flux estimates, and agricultural monitoring), and provide guidelines for minimizing and accounting for TD errors. To harmonize terminology, we distinguish TD from three other classes of data that should be used to create and assess ML models: training reference data, used to assess the quality of TD during data generation; validation data, used to iteratively improve models; and map reference data, used only for final accuracy assessment. We focus primarily on TD, but our advice is generally applicable to all four classes, and we ground our review in established best practices for map accuracy assessment literature. EO researchers should start by determining the tolerable levels of map error and appropriate error metrics. Next, TD error should be minimized during sample design by choosing a representative spatio-temporal collection strategy, by using spatially and temporally relevant imagery and ancillary data sources during TD creation, and by selecting a set of legend definitions supported by the data. Furthermore, TD error can be minimized during the collection of individual samples by using consensus-based collection strategies, by directly comparing interpreted training observations against expert-generated training reference data to derive TD error metrics, and by providing image interpreters with thorough application-specific training. We strongly advise that TD error is incorporated in model outputs, either directly in bias and variance estimates or, at a minimum, by documenting the sources and implications of error. TD should be fully documented and made available via an open TD repository, allowing others to replicate and assess its use. To guide researchers in this process, we propose three tiers of TD error accounting standards. Finally, we advise researchers to clearly communicate the magnitude and impacts of TD error on map outputs, with specific consideration given to the likely map audience.

58 GEOSCIENCES↗

Evolving Larger Convolutional Layer Kernel Sizes for a Settlement Detection Deep-Learner on Summit

Deep-learner hyper-parameters, such as kernel sizes, batch sizes, and learning rates, can significantly influence the quality of trained models. The state of the art for finding optimal hyper-parameters generally uses a brute force, grid search approach, random search, or Bayesian-based optimization among other techniques. We applied an evolutionary algorithm to optimize kernel sizes for a convolutional neural network used to detect settlements in satellite imagery. Usually convolutional layer kernel sizes are small - typically one, three, or five - but we found that the system converged at, or near, kernel sizes of nine for the last convolutional layer, and that this occurred for multiple runs using two different datasets. Moreover, the larger kernel sizes had fewer false positives than the 3x3 kernel sizes found as optimal via a brute force uniform grid search. This suggests that this large kernel size may be leveraging patterns found in larger areal features in the source imagery, and that this may be generalized as possible guidance for similar remote sensing deep-learning tasks.

Coletti, Mark↗

High Performance Geocomputation for Assessing Human Dynamics at Planet Scale

Settlements are key indicators of human presence on the landscape. Large scale mapping of human settlements and their morphology from very high-resolution satellite images is a critical step towards developing an interpretative understanding of population distribution and the sociocultural attributes of the built environment they live in. Convolutional neural network (CNN) based Deep Learning experiments indicates that such computations can be scaled to some of the largest high-performance computing (HPC) architectures. While early results are encouraging for developing settlement and corresponding population maps at unprecedented speed and spatial resolutions, characterizing human dynamics at planet scale with high temporal resolution will require the community to develop novel geocomputational infrastructures and ecosystems.

Bhaduri, Budhu↗

Multiscale Based Characterization and Classification of Urban Land-Use

Machine learning and deep learning provide a means for generating urban land-use maps with relatively little human effort compared to manually digitizing images. This is especially important for supporting global and regional initiatives focused on sustainability, planning, health, pro-poor policy, infrastructure, and population distribution estimates. Many of these initiatives work in areas where geospatial data is scarce, such as the global south, and often use land-use maps to help achieve their goals. In this study, we develop a typology for automated labeling of urban land-use data that captures the variation in structural patterns within cities. A comparison of classification accuracy between convolutional neural networks (CNNs) and support vector machines (SVMs) coupled with handcrafted features is conducted. Through experimental validation on two highly dense cities in Africa, we report on new insights and the potential benefits offered by both multiscale handcrafted features and multiscale-CNNs even with limited training data.

Arndt, Jacob↗

Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning

Most current state-of-the-art methods for semantic segmentation on remote sensing imagery require large labeled data, which is scarcely available. Due to the distribution shifting phenomenon inherent in remote sensing imagery, the reuse of pre-trained models on new areas of interest rarely yield satisfactory results. In this paper, we approach this problem from an adversarial learning perspective toward unsupervised domain adaptation. The core concept is to infuse fully convolutional neural networks and adversarial networks for semantic segmentation assuming the structures in the scene and objects of interest are similar in two set of images. Models are trained on a source dataset where ground truth is available and adapted to new target dataset iteratively via a adversarial loss on unlabeled samples. We use two real large scale datasets to validate the framework: 1) cross city road extraction and 2) cross country building extraction. The preliminary results show the usefulness of considering adversarial learning for indirect re-use of the pre-trained models. Experimental validation suggests significant benefits over models without adaptation.

Deng, Xueqing↗