Identifying residential neighbourhood types from settlement points in a machine learning approach
In: Computers, Environment and Urban Systems, Band 69, S. 104-113
26 Ergebnisse
Sortierung:
In: Computers, Environment and Urban Systems, Band 69, S. 104-113
In: Population: revue bimestrielle de l'Institut National d'Etudes Démographiques. French edition, Band 77, Heft 3, S. 467-494
ISSN: 0718-6568, 1957-7966
Le dénombrement de la population, dénominateur de nombreux indicateurs statistiques, est crucial pour les politiques publiques d'un pays. Il est du ressort des instituts nationaux de statistique d'en organiser la collecte, le plus souvent par le biais d'un recensement. Que se passe-t-il lorsqu'une partie du territoire n'est pas accessible aux agents recenseurs ? Actuellement, les données spatiales, telles qu'extraites de l'imagerie satellite, offrent une information géographique complète et de haute résolution, qui représente, lorsque combinée à un dénombrement partiel de la population, une opportunité sans précédent pour estimer les effectifs des territoires manquants. Leur précision spatiale rend également possible une estimation carroyée de la population en haute résolution, un format de données innovant à la croisée de la géographie et de la démographie. À partir du cas du Burkina Faso, cet article analyse comment le découpage du pays en carreaux de 100m sur 100m permet dans un premier temps de développer un modèle pour estimer, par le biais d'une approche hiérarchique bayésienne, la population des zones caractérisées par des problèmes sécuritaires n'ayant pas pu être dénombrées lors du dernier recensement de 2019. Ce découpage permet dans un second temps de désagréger les effectifs obtenus, par le biais d'un modèle d'apprentissage statistique pour obtenir une précision spatiale d'estimation de la population inégalée.
In: Migration studies, Band 3, Heft 1, S. 89-110
ISSN: 2049-5846
Background: Millions of Somali have been deprived of basic health services due to the unstable political situation of their country. Attempts are being made to reconstruct the health sector, in particular to estimate the extent of infectious disease burden. However, any approach that requires the use of modelled disease rates requires reasonable information on population distribution. In a low-income country such as Somalia, population data are lacking, are of poor quality, or become outdated rapidly. Modelling methods are therefore needed for the production of contemporary and spatially detailed population data.Results: Here land cover information derived from satellite imagery and existing settlement point datasets were used for the spatial reallocation of populations within census units. We used simple and semi-automated methods that can be implemented with free image processing software to produce an easily updatable gridded population dataset at 100 × 100 meters spatial resolution. The 2010 population dataset was matched to administrative population totals projected by the UN. Comparison tests between the new dataset and existing population datasets revealed important differences in population size distributions, and in population at risk of malaria estimates. These differences are particularly important in more densely populated areas and strongly depend on the settlement data used in the modelling approach.Conclusions: The results show that it is possible to produce detailed, contemporary and easily updatable settlement and population distribution datasets of Somalia using existing data. The 2010 population dataset produced is freely available as a product of the AfriPop Project and can be downloaded from: http://www.afripop.org. © 2010 Linard et al; licensee BioMed Central Ltd. ; SCOPUS: ar.j ; info:eu-repo/semantics/published
BASE
Population estimates are critical for government services, development projects, and public health campaigns. Such data are typically obtained through a national population and housing census. However, population estimates can quickly become inaccurate in localized areas, particularly where migration or displacement has occurred. Some conflict-affected and resource-poor countries have not conducted a census in over 10 y. We developed a hierarchical Bayesian model to estimate population numbers in small areas based on enumeration data from sample areas and nationwide information about administrative boundaries, building locations, settlement types, and other factors related to population density. We demonstrated this model by estimating population sizes in every 10- m grid cell in Nigeria with national coverage. These gridded population estimates and areal population totals derived from them are accompanied by estimates of uncertainty based on Bayesian posterior probabilities. The model had an overall error rate of 67 people per hectare (mean of absolute residuals) or 43% (using scaled residuals) for predictions in out-of-sample survey areas (approximately 3 ha each), with increased precision expected for aggregated population totals in larger areas. This statistical approach represents a significant step toward estimating populations at high resolution with national coverage in the absence of a complete and recent census, while also providing reliable estimates of uncertainty to support informed decision making.
BASE
In: Computers, environment and urban systems, Band 75, S. 132-145
In: Computers, environment and urban systems, Band 110, S. 102104
Pandemics such as COVID-19 and their induced lockdowns/travel restrictions have a significant impact on people's lives, especially for lower-income groups who lack savings and rely heavily on mobility to fulfill their daily needs. Taking the COVID-19 pandemic as an example, this study analysed the risk of returning to poverty for low-income households in Hubei Province in China as a result of the COVID-19 lockdown. Employing a dataset including information on 78,931 government-identified poor households, three scenarios were analysed in an attempt to identify who is at high risk of returning to poverty, where they are located, and how the various risk factors influence their potential return to poverty. The results showed that the percentage of households at high risk of returning to poverty (falling below the poverty line) increased from 5.6% to 22% due to a 3-month lockdown. This vulnerable group tended to have a single source of income, shorter working hours, and more family members. Towns at high risk (more than 2% of households returning to poverty) doubled (from 27.3% to 46.9%) and were mainly located near railway stations; an average decrease of 10–50 km in the distance to the nearest railway station increased the risk from 1.8% to 9%. These findings, which were supported by the representativeness of the sample and a variety of robustness tests, provide new information for policymakers tasked with protecting vulnerable groups at high risk of returning to poverty and alleviating the significant socio-economic consequences of future pandemics.
BASE
Travel and physical distancing interventions have been implemented across the World to mitigate the COVID-19 pandemic, but studies are needed to quantify the effectiveness of these measures across regions and time. Timely population mobility data were obtained to measure travel and contact reductions in 135 countries or territories. During the 10 weeks of March 22 - May 30, 2020, domestic travel in study regions has dramatically reduced to a median of 59% (interquartile range [IQR] 43% - 73%) of normal levels seen before the outbreak, with international travel down to 26% (IQR 12% - 35%). If these travel and physical distancing interventions had not been deployed across the World, the cumulative number of cases might have shown a 97-fold (IQR 79 - 116) increase, as of May 31, 2020. However, effectiveness differed by the duration and intensity of interventions and relaxation scenarios, with variations in case severity seen across populations, regions, and seasons.Competing Interest StatementThe authors have declared no competing interest.Funding StatementThis study was supported by the grants from the Bill & Melinda Gates Foundation (OPP1134076); the European Union Horizon 2020 (MOOD 874850). N.R. is supported by funding from the Bill & Melinda Gates Foundation (OPP1170969). O.P. is supported by the National Science Foundation (1816075). A.J.T. is supported by funding from the Bill & Melinda Gates Foundation (OPP1106427, OPP1032350, OPP1134076, OPP1094793), the Clinton Health Access Initiative, the UK Department for International Development (DFID) and the Wellcome Trust (106866/Z/15/Z, 204613/Z/16/Z). Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:Ethical clearance for collecting and using secondary population mobility data was granted by the institutional review board of the University of Southampton (No. 48002). All data were supplied and analyzed in an anonymous format, without access to personal identifying information.All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).Yes I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesCode for the model simulations is available at the following GitHub repository: https://github.com/wpgp/BEARmod. The data on COVID-19 cases and interventions reported by country are available from the data sources listed in Supplementary Materials. The parameters and population data for running simulations and estimating the severity are listed in Supplementary Data S1 to S2. The population movement data obtained from Baidu are available at: https://qianxi.baidu.com/. The Google COVID-19 Aggregated Mobility Research Dataset used for this study is available with permission of Google, LLC.
BASE
In: SSHO-D-20-00098
SSRN
Working paper
In: Social sciences & humanities open, Band 3, Heft 1, S. 100102
ISSN: 2590-2911
In: Computers, environment and urban systems, Band 80, S. 101444
The national census is an essential data source to support decision-making in many areas of public interest. However, this data may become outdated during the intercensal period, which can stretch up to several decades. In this study, we develop a Bayesian hierarchical model leveraging recent household surveys and building footprints to produce up-to-date population estimates. We estimate population totals and age and sex breakdowns with associated uncertainty measures within grid cells of approximately 100 m in five provinces of the Democratic Republic of the Congo, a country where the last census was completed in 1984. The model exhibits a very good fit, with an R2 value of 0.79 for out-of-sample predictions of population totals at the microcensus-cluster level and 1.00 for age and sex proportions at the province level. This work confirms the benefits of combining household surveys and building footprints for high-resolution population estimation in countries with outdated censuses.
BASE
Thirty years after the discovery of HIV-1, the early transmission, dissemination, and establishment of the virus in human populations remain unclear. Using statistical approaches applied to HIV-1 sequence data from central Africa, we show that from the 1920s Kinshasa (in what is now the Democratic Republic of Congo) was the focus of early transmission and the source of pre-1960 pandemic viruses elsewhere. Location and dating estimates were validated using the earliest HIV-1 archival sample, also from Kinshasa. The epidemic histories of HIV-1 group M and nonpandemic group O were similar until ~1960, after which group M underwent an epidemiological transition and outpaced regional population growth. Our results reconstruct the early dynamics of HIV-1 and emphasize the role of social changes and transport networks in the establishment of this virus in human populations.
BASE
In: Population and development review, Band 49, Heft 2, S. 231-254
ISSN: 1728-4457
AbstractIn times of crisis, real‐time data mapping population displacements are invaluable for targeted humanitarian response. The Russian invasion of Ukraine on February 24, 2022, forcibly displaced millions of people from their homes including nearly 6 million refugees flowing across the border in just a few weeks, but information was scarce regarding displaced and vulnerable populations who remained inside Ukraine. We leveraged social media data from Facebook's advertising platform in combination with preconflict population data to build a real‐time monitoring system to estimate subnational population sizes every day disaggregated by age and sex. Using this approach, we estimated that 5.3 million people had been internally displaced away from their baseline administrative region in the first three weeks after the start of the conflict. Results revealed four distinct displacement patterns: large‐scale evacuations, refugee staging areas, internal areas of refuge, and irregular dynamics. While the use of social media provided one of the only quantitative estimates of internal displacement in the conflict setting in virtual real time, we conclude by acknowledging risks and challenges of these new data streams for the future.