I need a good writer

Annotated Bibliography

Engstrom, R., Hersh, J., & Newhouse, D. (2016). Poverty in HD: What Does High Resolution Satellite Imagery Reveal about Economic Welfare. Working paper.

This paper was a joint effort between researchers and seminar participants at the Boston University Development. The researchers got a financial support from the Strategic Research Program and World Bank Innovation. They selected areas for the sample, and they used some statistics of GN poverty and got some estimated from census of population to understand and prediction of the prevalence of poverty. They compared between the data which created spatial features from high resolution satellite imagery.

Moreover, the researchers made a classification for the objects such as of density and height of buildings, numbers of cars, type of roads and agriculture. The poverty has many correlates, some in urban areas and other in rural areas. Also, they used many indexes and indicators for modeling. They validated the poverty by using high resolution features and they explained the variation the extent of poverty. Finally, they concluded to many results, which indicated to a strong correlation between satellite indicators and predicted welfare. Also, the variables measuring were the strongest predictors of variation in poverty, Finally, they asserted the valuable of satellite imagery to help governments and stakeholders to elimination the poverty.

In sum, it is a useful paper, which has an explanation and analysis of how satellite images were used in poverty research, and what features can be extracted for analysis.

Engstrom, R. (2018). Linking pixels and poverty: Using satellite imagery to map poverty, Panel contribution to the population-environment research network cyber seminar,10516.

The author presented the importance of this topic and how many researchers in different disciplines have worked on poverty. The main goal for these researches is ending poverty in all its forms everywhere, that by defined its location. Recently, the researchers are starting to map the poverty. They performed mapping in traditional way by either using survey of household data or by combining them with census data. They faced many troubles in time, cost, and labors to collect data in many areas. Furthermore, the safety in the unstable areas. They avoided these problems by using satellite imagery. They started with images in night time lights to recognize the variations in poverty between countries. The researcher found "that areas with greater wealth have higher NTL light emissions and poorer areas have fewer light emissions." Since the results were limited to urban areas only. He focused on using high-resolution spatial images of less than 5 meters although they were expensive for researchers. Also, he used other approaches to map poverty areas including simple visual interpretation. He concluded to that the satellite data a very rich field for research and exploration and its helping in mapping of poverty. The successful of night lights to extract the information over large areas.

This research is useful to learn other type of data that can be used to identify poverty. Also, the researcher has proven the ability of night light imagery to measure the poverty areas.

Elvidge, C. D., Sutton, P. C., Ghosh, T., Tuttle, B. T., Baugh, K. E., Bhaduri, B., & Bright, E. (2009). A global poverty map derived from satellite data. Computers & Geosciences, 35(8), 1652-1660.

This research was carried out in cooperation with several specialists, which are geographers, geophysicists, and scholars in environment and energy. Their work relies on satellite data and World Bank data, which are contributed to draw the global poverty map. That has led to define the local poverty line and the international poverty line. Although all countries do not conduct surveys on poverty data on social and economic measures, population density, living conditions, and economic activities. This is not for developed countries, but for developing countries, which is useful for efforts to reduce poverty. Satellite data has proven effective in global mapping. These maps are annual and semi-annual.

This study defined the term “poverty” and it gave many examples from multiple aspects of poverty. Also, it illustrated how to use satellite imageries in poverty research and mapping, by analyzing and exploring any correlation between features.

Engstrom, R., Hersh, J., & Newhouse, D. (2017). Poverty from space: Using high-resolution satellite imagery for estimating economic well-being, World Bank Group.

This work was done by the authors based on the efforts of the World Bank on development issues, in particular poverty and equity. They said that despite the efforts of the statistical offices of all countries, local estimates of poverty and economic well-being are rare or almost non-existent. They noted the use of satellite images contributes to filling large gaps in data shortages. With the development of technology and advanced companies will expand coverage ranges and accurate imaging. They referred to their studies and the features they extracted to predict poverty through them such as: type of roofs, number of buildings, size, height, and density. Also, the size and type of agricultural land, and number of vehicles and cars, the form of roads and paving materials. They are linking these elements through special software for the assessment of well-being. Also, by using nightlights they can know the concentration of economic activity.

In sum, this work was an explanation and analysis of how satellite images were used in research, and what features can be extracted for analysis.

Ferreira, T. (2017) The extension of existing data and methods to measure poverty and mobility in data-poor, Agrarian Sub-Saharan Africa, Dissertation presented for the degree of Doctor of Philosophy (Economics) in the Faculty of Economic and Management Sciences at the University of Stellenbosch.

The author presented this dissertation for the degree of Doctor in Economics Philosophy at the University of Stellenbosch. This research relies on poverty and what the methods are to measure it. The researcher tried to fill the gap of lack of data. He gave an overview about study area, economic, and social situation in it. Then, he began analyzing the satellite data to come up with results. He used daylight data to measure socio-economic outcomes. Also, he tried to identify rural agricultural areas, where the presence of plants enables the researcher to measure the use of the earth. It also contributes to detect droughts, which increase poverty. Finally, Ferreira found that the images in the nightlights could not measure economic activity in Sub-Saharan Africa.

This research and other research contribute effectively to alleviating poverty and focusing the efforts of organizations in poor places only. Also, it is a useful research to learn other methods for measuring the poverty.

Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., & Ermon, S. (2016). Combining satellite imagery and machine learning to predict poverty. Science, 353(6301), 790-794.

These authors contributed equally to this work. They are in various fields from Stanford University in California. Moreover, they cooperated with National Bureau of Economic Research in Boston, MA. Their research on poverty, and it targeted developing countries.

They relied on high-resolution satellite imagery for five African countries, which are Nigeria, Tanzania, Uganda, Malawi and Rwanda. They pointed to the evolution of technology, and they explained their approach. The nightlights are not quite effective, as they have little ability to distinguish between poor and poorer areas, but it is effective in distinguishing between densely populated areas from other low-population areas. Also, that nightlights are good for estimating economic well-being. They explained through the analysis of satellite images that daylight contributes to the detection of the advantages related to the materials used in the construction of roofs and roads.

The research was a joint effort, based on the analysis of satellite imageries and the spatial features which became apparent through it. It is useful and offers a good explanation for satellite imagery analysis.

Morikawa, R. (2014). Remote sensing tools for evaluating poverty alleviation projects: A case study in Tanzania. Procedia Engineering. 78.

The purpose of this article was to alleviate poverty and its effects on rural areas, and preserving the agricultural environment, which is related to the economic situation of farmers. The researcher used plant reflection to know the ecology of crops and determine the types of vegetation. It can also detect if there any future problems such as drought and soil erosion, and work to find solutions early. That contributes to measuring the conditions of the local environment in the long term. All this is done by the so-called “NDVI” the normalized difference vegetation index. Thus, serving communities and poverty alleviation projects, and developing their work to improve living conditions. For example, communities suffering from famine will predict this in advance and therefore take their precautions early by reforestation, avoiding logging, protecting water collection sites and adopting sustainable cultivation techniques.

In sum, this research uses spatial analysis and remote sensing to detect any future problems, which are helping to save time, efforts, and human life.

Steele, J. E., Sundsøy, P. R., Pezzulo, C., Alegana, V. A., Bird, T. J., Blumenstock, J., ... & Hadiuzzaman, K. N. (2017). Mapping poverty using mobile phone and satellite data. Journal of The Royal Society Interface, 14(127), 20160690.

This study represented the first attempt to created predictive maps of poverty that by using a collection of CDR and RS data. It further provided an example of processed the CDR data and created detailed maps without revealing the user or the information. The remote sensing data captured the environmental metrics and physical properties like vegetation indices, night-time lights, climatic conditions. In addition, captured other data that related to human living conditions and behavior like distance to roads or major urban areas. All these data were obtained from many sources especially for this study and were processed to ensure that resolutions, extents, and projections matched. They used geographically referenced datasets representing asset, consumption and income-based measures of wellbeing. The concluded their study to important results. They found that the models employing a combination of CDR and RS data generally provided an advantage more than the models only based on either data source. Also, they found the spatial covariance in the data was very important. They found also the consumption has been shown to be lower than the predictive power for assets. Further, there are some changes in the income and consumption by day or week, related to changes in the family size, get or loss the job, and piecework or harvest outcomes.

It is a useful study that demonstrated the data sources that can be used to the spatial distribution of poverty. In addition, their findings provide further support for correlations between socio-economic measures and night-time light intensity, access to roads and cities, entropy of contacts and mobility features.