|   | 
Details
   web
Records
Author Yeh, C.; Perez, A.; Driscoll, A.; Azzari, G.; Tang, Z.; Lobell, D.; Ermon, S.; Burke, M.
Title (down) Using publicly available satellite imagery and deep learning to understand economic well-being in Africa Type Journal Article
Year 2020 Publication Nature Communications Abbreviated Journal Nat Commun
Volume 11 Issue 1 Pages 2583
Keywords Remote Sensing
Abstract Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa's most populous country.
Address National Bureau of Economic Research, 1050 Massachusetts Avenue, Cambridge, MA, 02138-5398, USA. mburke@stanford.edu
Corporate Author Thesis
Publisher Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2041-1723 ISBN Medium
Area Expedition Conference
Notes PMID:32444658 Approved no
Call Number GFZ @ kyba @ Serial 2939
Permanent link to this record
 

 
Author Ghosh, T.; Anderson, S.; Elvidge, C.; Sutton, P.
Title (down) Using Nighttime Satellite Imagery as a Proxy Measure of Human Well-Being Type Journal Article
Year 2013 Publication Sustainability Abbreviated Journal Sustainability
Volume 5 Issue 12 Pages 4988-5019
Keywords Remote Sensing
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2071-1050 ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number LoNNe @ kagoburian @ Serial 941
Permanent link to this record
 

 
Author Imhoff, M.
Title (down) Using nighttime DMSP/OLS images of city lights to estimate the impact of urban land use on soil resources in the United States Type Journal Article
Year 1997 Publication Remote Sensing of Environment Abbreviated Journal Remote Sensing of Environment
Volume 59 Issue 1 Pages 105-117
Keywords Remote Sensing
Abstract Nightime “city light” footprints derived from DMSP/OLS satellite images were merged with census data and a digital soils map in a continental-scale test of a remote sensing and geographic information system methodology for approximating the extent of built-up land and its potential impact on soil resources in the United States. Using image processing techniques and census data, we generated maps where the “city lights” class represented mean population densities of 947 persons km−2 and 392 housing units km−2, areas clearly not available to agriculture. By our analysis, such “city lights” representing urban areas accounted for 2.7% of the surface area in the United States, an area approximately equal to the State of Minnesota or one half the size of California. Using the UN/FAO Fertility Capability Classification System to rank soils, results for the United States show that development appears to be following soil resources, with the better agricultural soils being the most urbanized. Some unique soil types appear to be on the verge of being entirely coopted by “urban sprawl.” Urban area figures derived from the DMSP/OLS imagery compare well to those derived from statistical sources. Further testing and refinement of the methodology remain but the technique shows promise for possible extension to global evaluations of urbanization, population and even global productivity.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0034-4257 ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number LoNNe @ christopher.kyba @ Serial 496
Permanent link to this record
 

 
Author Weidmann, N.; Schutte, S.
Title (down) Using night light emissions for the prediction of local wealth Type Journal Article
Year 2016 Publication Journal of Peace Research Abbreviated Journal J Peace Res
Volume Issue Pages 0022343316630359
Keywords Economics; remote sensing; night lights; spatial prediction
Abstract Nighttime illumination can serve as a proxy for economic variables in particular in developing countries, where data are often not available or of poor quality. Existing research has demonstrated this for coarse levels of analytical resolution, such as countries, administrative units or large grid cells. In this article, we conduct the first fine-grained analysis of night lights and wealth in developing countries. The use of large-scale, geo-referenced data from the Demographic and Health Surveys allows us to cover 39 less developed, mostly non-democratic countries with a total sample of more than 34,000 observations at the level of villages or neighborhoods. We show that light emissions are highly accurate predictors of economic wealth estimates even with simple statistical models, both when predicting new locations in a known country and when generating predictions for previously unobserved countries.
Address Department of Politics and Public Administration, University of Konstanz, Germany; nils.weidmann(at)uni-konstanz.de
Corporate Author Thesis
Publisher SAGE Place of Publication Editor
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number IDA @ john @ Serial 1474
Permanent link to this record
 

 
Author Rybnikova, N.A.; Portnov, B.A.
Title (down) Using light-at-night (LAN) satellite data for identifying clusters of economic activities in Europe Type Journal Article
Year 2015 Publication Letters in Spatial and Resource Sciences Abbreviated Journal Lett. Spatial & Resource Sci.
Volume 8 Issue 3 Pages 307–334
Keywords Remote Sensing; Economic activities; Clusters; Satellite photometry; Light-at-night; Europe; Nomenclature of Territorial Units for Statistics; C13; C38; O52; Economics
Abstract Enterprises organized in clusters are often efficient in stimulating urban development, productivity and profit outflows. Identifying the clusters of economic activities thus becomes an important step in devising regional development policies, aimed at the formation of clusters of economic activities in geographic areas in which this objective is desirable. However, a major problem with the identification of such clusters stems from limited reporting by individual countries and administrative entities on the regional distribution of specific economic activities, especially for small regional subdivisions. In this study, we test a possibility that missing data on geographic concentrations of economic activities in the European NUTS3 regions can be reconstructed using light-at-night satellite measurements, and that such reconstructed data can then be used for cluster identification. The matter is that light-at-night, captured by satellite sensors, is characterized by different intensity, depending on its source—production facilities, services, etc. As a result, light-at-night can become a marker of different types of economic activities, a hypothesis that the present study confirms. In particular, as the present analysis indicates, average light-at-night intensities emitted from NUTS3 regions help to explain up to 94 % variance in the areal density of several types of economic activities, performing especially well for professional, scientific and technical services (R^2=0.742−0.939), public administration (R^2=0.642−0.934), as well as for arts, entertainment and recreation (R^2=0.718−0.934). As a result, clusters of these economic activities can be identified using light-at-night data, thus helping to supplement missing information and assist regional analysis.
Address Department of Natural Resources and Environmental Management, Faculty of Management, University of Haifa, 31805, Mt. Carmel, Israel; Portnov@research.haifa.ac.il
Corporate Author Thesis
Publisher Springer Place of Publication Editor
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes Approved no
Call Number IDA @ john @ Serial 1148
Permanent link to this record