Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “HUMAN SETTLEMENT MAPPING”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Performance analysis and optimization for scalable deployment of deep learning models for country-scale settlement mapping on Titan supercomputer

Here, we present a scalable object detection workflow for detecting objects, such as settlements, from remotely sensed (RS) imagery. We have successfully deployed this workflow on Titan supercomputer and utilized it for the task of mapping human settlement at a country scale. The performance of various stages in the workflow was analyzed before making it operational. The workflow implemented various strategies to address issues such as suboptimal resource utilization and long-tail effects due to unbalanced image workload, data loss due to runtime failures, and maximum wall-time constraints imposed by Titan's job scheduling policy. A mean shift clustering–based static load balancing strategy was implemented, which partitions the image load such that each partition contained similar-sized images. Furthermore, a checkpoint-restart strategy was added in the workflow as a fault-tolerance mechanism to prevent the data losses due to unforeseen runtime failures. The performance of the above-mentioned strategies was observed in various scenarios, such as node failure, exceeding wall time, and successful completion. Using this workflow, we have examined an RS data set that has a spatial resolution of 0.31 m and is comprised of 685 675 km 2 of area of the Republic of Zambia in under six hours using 5426 nodes of the Titan supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Domain-Adapted Convolutional Networks for Satellite Image Classification: A Large-Scale Interactive Learning Workflow

Satellite imagery often exhibits large spatial extent areas that encompass object classes with considerable variability. This often limits large-scale model generalization with machine learning algorithms. Notably, acquisition conditions, including dates, sensor position, lighting condition, and sensor types, often translate into class distribution shifts introducing complex nonlinear factors and hamper the potential impact of machine learning classifiers. Here, this article investigates the challenge of exploiting satellite images using convolutional neural networks (CNN) for settlement classification where the class distribution shifts are significant. We present a large-scale human settlement mapping workflow based-off multiple modules to adapt a pretrained CNN to address the negative impact of distribution shift on classification performance. To extend a locally trained classifier onto large spatial extents areas we introduce several submodules: First, a human-in-the-loop element for relabeling of misclassified target domain samples to generate representative examples for model adaptation; second, an efficient hashing module to minimize redundancy and noisy samples from the mass-selected examples; and third, a novel relevance ranking module to minimize the dominance of source example on the target domain. The workflow presents a novel and practical approach to achieve large-scale domain adaptation with binary classifiers that are based-off CNN features. Experimental evaluations are conducted on areas of interest that encompass various image characteristics, including multisensors, multitemporal, and multiangular conditions. Domain adaptation is assessed on source–target pairs through the transfer loss and transfer ratio metrics to illustrate the utility of the workflow.

47 OTHER INSTRUMENTATION↗
DOE OSTI2019

The impact of seasonality on multi-scale feature extraction techniques

A key component in constructing a broad-scale, gridded population dataset is fine resolution geospatial data accurately depicting the extent of human activity. Analogous datasets are often developed using a wide range of methods and classification techniques, including the use of spatial features, spectral features, or the coupling of both to identify the presence of man-made structures from high-resolution satellite imagery. By using spatial and textural-based descriptors to generate high-resolution settlement layers for two dissimilar regions at the peak of seasonal disparity, this study attempts to quantify the influence of seasonality on the accuracy of a supervised, multi-scale, feature extraction framework for automated delineation of human settlement. Results generated by numerous models are evaluated against a reference dataset allowing for assessment of seasonal and feature differences in the context of accuracy. Global or regional mapping of human settlement requires the assemblage of high-resolution satellite images with variegated acquisition characteristics (season, sun elevation, off-nadir, etc.) to produce a cloud-free composite image from which features are extracted. Results of this study suggest an emphasis on imagery criteria, in particular acquisition date, could improve classification accuracy when mapping human settlement at scale.

58 GEOSCIENCES↗
DOE OSTI2019

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↗
NASA NTRS2017

HOTEX: An Approach for Global Mapping of Human Built-Up and Settlement Extent

Understanding the impacts of urbanization requires accurate and updatable urban extent maps. Here we present an algorithm for mapping urban extent at global scale using Landsat data. An innovative hierarchical object-based texture (HOTex) classification approach was designed to overcome spectral confusion between urban and nonurban land cover types. VIIRS nightlights data and MODIS vegetation index datasets are integrated as high-level features under an object-based framework. We applied the HOTex method to the GLS-2010 Landsat images to produce a global map of human built-up and settlement extent. As shown by visual assessments, our method could effectively map urban extent and generate consistent results using images with inconsistent acquisition time and vegetation phenology. Using scene-level cross validation for results in Europe, we assessed the performance of HOTex and achieved a kappa coefficient of 0.91, compared to 0.74 from a baseline method using per-pixel classification using spectral information.

Wang, Panshi↗
DOE OSTI2017

AN INDUCTIVE MAPPING WITH CONVOLUTIONAL REPRESENTATIONS FOR HUMAN SETTLEMENT DETECTION: PRELIMINARY RESULTS

Undoubtedly, deep convolutional learning methods continue to improve performance in image-level classification for computer vision and remote sensing applications. However, the spatio-temporal nature of remote sensing imagery offers other interesting challenges in multiscale image understanding. Emerging opportunities include seeking fine-grained and neighborhood mapping with overhead imagery. Limitations due to lack of relevant scale ground-truth often mandates that these challenges are pursued as disjoint. We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different image representation spaces, we demonstrate surprising potential on multiscale experiments that incorporate edge-level details up to semantic-level informationWe test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different image representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level informationWe test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different image representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.

Lunga, Dalton↗
DOE OSTI2015

LandScan HD

Research in geographic information science and technology at Oak Ridge National Laboratory is addressing the need for improved human settlement detection and characterization at the world scale.

58 GEOSCIENCES↗
NASA NTRS2021

Southern Bhutan Ecological Forecasting III: Utilizing NASA Earth Observations to Model Land Cover Change and Elephant Wildlife Corridors in Southern Bhutan

Habitat loss of the endangered Asian elephants (Elephas maximus) accompanied by rapid urbanization has contributed to the rising human-elephant conflict (HEC) crisis in southern Bhutan. This poses a serious threat to the survival of Asian elephants, a keystone wildlife species essential for maintaining Bhutan’s forest ecosystems and rich biodiversity. With expanding urban areas, HECs present challenges to conservation efforts in the region. The team partnered with the Bhutan Foundation, the Bhutan Tiger Center, and Bhutan Ecological Society to help mitigate this issue using remote sensing technology and NASA Earth observations. The team refined Land Use and Land Cover (LULC) maps for 2010–2019 generated in previous terms and elephant corridor maps to include information on human settlements using Landsat 5 Thematic Mapper (TM) and Landsat 8 Operational Land Imager (OLI) data. We generated LULC change maps and forecasted the LULC to 2030 using TerrSet Land Change Modeler, providing insights into future elephant habitat suitability in southern Bhutan. The results indicated that built-up areas increased approximately 688.9% from 2010 to 2019 and the forecasted 2030 LULC also predicted an increase in built-up areas compared to 2019. Suitable corridors in Gelephu intersect cultivated and built-up areas, indicating close proximity of elephants to humans and a need to research alternative corridor strategies. The end products from this project will aid partner organizations in decision-making processes in urban planning and future conservation strategies that include the refined placement of biological corridors to aid elephant movement and reduce the risk of HECs.

Thinley Yidzin Wangden↗
NASA NTRSDate not supplied

Predicting the Likelihood of Human-Elephant Conflict and Assessing Patterns in Elephant Movements Over Varying Habitat Conditions in the Kavango-Zambezi Area

In the Kavango-Zambezi area of southern Africa, three million people live within areas frequently traveled by free-ranging elephants. As the region continues to develop rapidly, urban and agricultural settlements further encroach upon the land that these elephants use. As elephants come into more frequent contact with urban and agricultural areas, human populations face financial loss through crop damage and the potential for injury from direct conflict with elephants. Elephant populations are also at risk of injuries from conflict as well as illness related to the consumption of waste. In order to implement human-elephant conflict mitigation strategies, local conservation groups need to be informed on best practices for coexistence. This project aided The Ecoexist Project and Connected Conservation in understanding the ecological factors that drive elephant movement into human settlements and provided Earth observation data to support conflict management in the future. The team used Landsat 5 Thematic Mapper (TM), Landsat 8 Operational Land Imager (OLI) data to create land use land cover maps and calculate vegetation indices, and used TerraClimate data to analyze drought conditions. These classified maps allowed us to display a time series of human settlement from 1990 to the present and were made explorable alongside other environmental variables in an updated Google Earth Engine (GEE) tool. This project also provided heat maps that show the risk of human-elephant conflict based on historical data of HEC locations. This analysis will provide support for conservation experts in determining best practices for future mitigation and prevention of human-elephant conflict.

Ariel Calle↗
DOE OSTI2017

Hashed Binary Search Sampling for Convolutional Network Training with Large Overhead Image Patches

Very large overhead imagery associated with ground truth maps has the potential to generate billions of training image patches for machine learning algorithms. However, random sampling selection criteria often leads to redundant and noisy-image patches for model training. With minimal research efforts behind this challenge, the current status spells missed opportunities to develop supervised learning algorithms that generalize over wide geographical scenes. In addition, much of the computational cycles for large scale machine learning are poorly spent crunching through noisy and redundant image patches. We demonstrate a potential framework to address these challenges specifically, while evaluating a human settlement detection task. A novel binary search tree sampling scheme is fused with a kernel based hashing procedure that maps image patches into hash-buckets using binary codes generated from image content. The framework exploits inherent redundancy within billions of image patches to promote mostly high variance preserving samples for accelerating algorithmic training and increasing model generalization.

Lunga, Dalton↗
DOE OSTI2026

Satellite Embedding-Based Population Imputation for Areas with Missing Building Footprint Data: A Computer Vision-Based Approach

High-resolution population modeling is important for supporting effective decision-making across diverse sectors. LandScan Mosaic generates population estimates at the level of individual buildings and aggregates them to 3 arc-second grids, and this approach performs well in regions where building footprint data are comprehensive and reliable. However, large portions of the globe still suffer from incomplete, sparse, or entirely missing building stock datasets, creating a structural limitation for strictly building-based population models. To address this research gap, this study proposes a computer vision-based framework that employs Google Earth Engine satellite embeddings and UNet, which allows us to directly impute grid-level population estimates in building-data-deficient areas. Applied to Taiwan as a case study, the framework achieved strong predictive performance with R$^{2}$ of 0.89, RMSE of 18.70, and MAE of 8.41, outperforming traditional machine learning approaches. Notably, the proposed framework effectively addressed building false-positive errors inherent in Global Human Settlement Layer (GHSL) data, correctly identifying uninhabited areas that were erroneously classified as populated. The framework also offers significant advantages for global population mapping, particularly in terms of scalability and temporal consistency, thereby extending the coverage and accuracy of high-resolution population products in data-scarce regions worldwide. Urban planners, decision makers, and related stakeholders can obtain granular population distributions to support more accurate and targeted infrastructure investment, service delivery, resource allocation, and risk assessment decisions.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

HydroSAR: A Cloud-based SAR Data Analysis Service to Monitor Hydrological Disasters and their Impact on Population and Agriculture

Weather-related hazards are ubiquitous around the world including: 1) hurricane storm surges, 2) rapid snowmelt and heavy rainfall, 3) severe weather leading to flash floods, and 4) seasonal freeze and thaw of rivers that may lead to ice jams. Each of these hazards affects human settlements and has the potential to impact agricultural productivity. In each setting, end-users in disaster management need access to data processing tools helpful in mapping past and current disasters. Analysis of past events supports risk mitigation by understanding what has already occurred and how to alleviate those impacts in the future. Having capabilities to generate the same products in a response setting means that lessons learned from risk analysis will carry forward to event response. Synthetic aperture radar (SAR) data are particularly useful for these activities due to their all-weather 24/7 monitoring capabilities. In this effort we present HydroSAR, a cloud-based SAR data analysis service for the mapping of meteorological and hydrological disasters as well as their impact on population and agriculture. As part of this project we have developed a series of SAR-based value added products for the monitoring of surface hydrology (image time series, change detection, flood extent, flood depth) and the assessment of impacts on population (flood depth) and agriculture (active agriculture, inundated agriculture, flood duration). We also developed a cloud-based platform for generating these products over affected areas and are working with end-users to integrate derived product into decision-making workflows The paper will briefly introduce the SAR-based products that were developed for this effort. We describe the cloud-based production pipeline that was built to automatically generate these products in near-real time over extended regions. The integration of SAR-based information into hazard preparation and response activities is described for a number of recent disasters including the 2019 forest fires in Alaska, 2019 flooding in the U.S. Midwest, the 2020 U.S. severe weather easter outbreak, 2020 tropical storm Christobal, 2020 cyclone Amphan, 2020, Alaska Spring breakup flooding, and the 2020 flood season in Eastern India, Bangladesh, and Nepal.

Franz Josef Meyer↗
NASA NTRS2004

Remote Sensing Assessment of Lunar Resources: We Know Where to Go to Find What We Need

The utilization of space resources is necessary to not only foster the growth of human activities in space, but is essential to the President s vision of a "sustained and affordable human and robotic program to explore the solar system and beyond." The distribution of resources will shape planning permanent settlements by affecting decisions about where to locate a settlement. Mapping the location of such resources, however, is not the limiting factor in selecting a site for a lunar base. It is indecision about which resources to use that leaves the location uncertain. A wealth of remotely sensed data exists that can be used to identify targets for future detailed exploration. Thus, the future of space resource utilization pre-dominantly rests upon developing a strategy for resource exploration and efficient methods of extraction.

Gillis, J. J.↗
NASA NTRSDate not supplied

Assessing Land Cover Change Dynamics in the Peruvian Amazon to Map Outbreak Risk and Inform Public Health Interventions for Zoonotic Disease Prevention

Dengue fever and leishmaniasis are two tropical diseases prevalent in Madre de Dios Region of Peru and have been associated with urbanization and road construction. Rapid land use changes such as mining, timber harvesting, and hydroelectric dam development lead to denser human presence in previously sparsely-populated areas which increases the proximity of human settlements to zoonotic disease vectors. In partnership with the Peruvian Ministries of Health (MINSA), the Environment (MINAM), and other in-country collaborators, a NASA DEVELOP team examined Land Use Land Cover (LULC) changes and reported dengue and leishmaniasis incidence in the Madre de Dios region. This sought to help MINSA and MINAM understand the spatial relationship between land use change and zoonotic disease incidence. We created a LULC classification script using Google Earth Engine (GEE) with Landsat 5 Thematic Mapper (TM) and Landsat 8 Operational Land Imager (OLI) imagery to classify land cover in 2010, 2015, and 2020 and evaluate changes over this time period. The team then compared the quantified results of the LULC assessment in conjunction with reported disease cases to evaluate disease incidence and key land cover changes across Madre de Dios’s 11 districts. Follow on work will use these products to develop more detailed outbreak risk maps. These products will allow MINSA, MINAM, and other partners to understand hotspots of land cover change in Peru and the relationship with outbreaks to inform public health decision makers and environmental policy.

Nataly Chacon-Buitrago↗
DOE OSTI2018

A Comparison of Machine Learning Techniques to Extract Human Settlements from High Resolution Imagery

Two machine learning techniques were developed to extract human settlements from very high resolution (VHR) satellite images of 3 provinces in Afghanistan: Logar, Panjsher, and Wardak. The results were then compared with analyst verified reference data information known as the LandScan Settlement Layer (LandScan SL).[1] This study attempts to compare settlement mapping results from a support vector machine (SVM) classifier specifically integrated in a current settlement mapping framework and a deep learner utilizing a convolutional neural network (CNN) approach. By comparing the results from the SVM and the CNN to the reference data information we demonstrate that the CNN yields more accurate results overall, in terms of overall pixel cells, and the SVM performs more accurately in omission, based on derived statistics against the reference data information.

Weaver, Jeanette E↗
NASA NTRS2018

TPSAS-NF1676L-31995-DND

The Osa Peninsula, located in the southern region of Costa Rica’s Pacific Coast, is one of the most biologically-diverse places on Earth and is a popular ecotourism destination. However, the area faces watershed degradation and loss of biodiversity due to deforestation, pollution from agriculture, and human settlement. The NASA DEVELOP National Program worked with Osa Conservation to analyze land use and land cover change in the Osa Peninsula to better understand threats to river water quality and mangrove health. This project used Landsat 5 Thematic Mapper (TM), Landsat 8 Operational Land Imager (OLI), and Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) to create a land cover time series map from 1987 to 2017. These time series data were used to compare land use over time, as well as patterns in water quality, mangrove health, erosion, and deforestation. The time series also helped to identify the impact of the creation of protected areas and the 1996 Forest Law 7575, which aimed to support reforestation and riparian health. Osa Conservation will use and distribute results to the National System of Conservation Areas (SINAC), Ministry of Environment and Energy (MINAE), and local communities to inform land management decisions, policy enforcement, education and outreach initiatives, and watershed restoration and monitoring.

Suravi Shrestha↗
NASA NTRS2022

A High Voltage Tethered Power System for Planetary Surface Applications

In the pursuit of human and robotic expansion of theLunar surface and other planetary bodies, power conversionand transmission over long distances has emerged as a distinctneed. The ability to transmit power over kilometers at highefficiency enables human settlement, in-situ resource utilization,and extreme terrain robotic exploration, through the ability toreach previously unreachable places. The critical buildingblocks of such a system are being developed by the TetheredPower System for Lunar Mobility and Power Transmission(TYMPO) project, a NASA project aimed at reaching flightreadiness by 2024. This paper presents an architectural andrequirements overview of the TYMPO project, along withtechnology discussions on the GaN-based multilevel DCXconverters, dual fiber optics and power-line communicationssystem, and high-voltage tether. Finally, a set of proposed futuremissions will be presented, mapping the capabilities of theTYMPO system to missions that may soon explore planetarysurfaces throughout the solar system.

Yang, Summer↗