Search NASA⌕ Search

Engineering topics

Weaver, Jeanette E.

Publications and source records attributed to Weaver, Jeanette E..

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↗

Electricity consumption patterns within cities: application of a data-driven settlement characterization method

Urban areas presently consume around 75% of global primary energy supply, which is expected to significantly increase in the future due to urban growth. Having sustainable, universal energy access is a pressing challenge for most parts of the globe. Understanding urban energy consumption patterns may help to address the challenges to urban sustainability and energy security. However, urban energy analyses are severely limited by the lack of urban energy data. Such datasets are virtually non-existent for the developing countries. As per current projections, most of the new urban growth is bound to occur in these data-starved regions. Hence, there is an urgent need of research methods for monitoring and quantifying urban energy utilization patterns. Here, we apply a data-driven approach to characterize urban settlements based on their formality, which is then used to assess intra-urban urban energy consumption in Johannesburg, South Africa; Sana’a, Yemen; and Ndola, Zambia. Electricity is the fastest growing energy fuel. By analyzing the relationship between the settlement types and the corresponding nighttime light emission, a proxy of electricity consumption, we assess the differential electricity consumption patterns. Our study presents a simple and scalable solution to fill the present data void to understand intra-city electricity consumption patterns.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Exploiting deep learning and volunteered geographic information for mapping buildings in Kano, Nigeria

Buildings in the developing world are inadequately mapped. Lack of such critical geospatial data adds unnecessary challenges to locating and reaching a large segment of the world’s most vulnerable population, impeding sustainability goals ranging from disaster relief to poverty reduction. Use of volunteered geographic information (VGI) has emerged as a widely accepted source to fill such voids. Despite its promise, availability of building maps for developing countries significantly lags behind demand. We present a new approach, coupling deep convolutional neural networks (CNNs) with VGI for automating building map generation from high-resolution satellite images for Kano state, Nigeria. Specifically, we trained a CNN with VGI building outlines of limited quality and quantity and generated building maps for a 50,000 km 2 area. Resulting maps are in strong agreement with existing settlement maps and require a fraction of the manual input needed for the latter. The VGI-based maps will provide support across multiple facets of socioeconomic development in Kano state, and demonstrates potential advancements in current mapping capabilities in resource constrained countries.

99 GENERAL AND MISCELLANEOUS↗

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↗

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↗