Publication: Leveraging Imagery Data in Evaluations: Applications of Remote-Sensing and Streetscape Imagery Analysis
Loading...
Date
2024-03-05
ISSN
Published
2024-03-05
Author(s)
Editor(s)
Abstract
Imagery data offer the potential to answer critical questions regarding the relevance and effectiveness of development initiatives, providing a factual basis for decision-making and the refinement of policies and programs. Imagery data, encompassing a diverse array of sources from remote-sensing imagery to digital photos, offer a vast and underused resource for understanding the dynamics of change in urban development and other geospatial phenomena. Despite their ubiquity, imagery data remain relatively neglected in the evaluation of international development interventions, primarily on account of perceived barriers in relation to computation and expertise. However, recent advances in machine learning and increased computational resources have made imagery data more accessible. This paper explores the potential of imagery data in evaluations and presents various data types and methodologies, demonstrating their advantages and limitations. An Independent Evaluation Group case study on a World Bank urban development project in Bathore, Albania, illustrates the practical application of different imagery data and methodologies. By leveraging imagery data, evaluators can gain insights into the geographical impact of development interventions. Moreover, integrating imagery data with other information sources, such as surveys and socioeconomic statistics, offers strong potential for deepening the understanding of complex phenomena.
Link to Data Set
Citation
“Ziulu, Virginia. 2024. Leveraging Imagery Data in Evaluations: Applications of Remote-Sensing and Streetscape Imagery Analysis. IEG Methods and Evaluation Capacity Development Working Paper Series. © World Bank. http://hdl.handle.net/10986/41152 License: CC BY-NC 3.0 IGO.”
Associated URLs
Associated content
Other publications in this report series
Journal
Journal Volume
Journal Issue
Collections
Related items
Showing items related by metadata.
Publication Estimating Small Area Population Density Using Survey Data and Satellite Imagery(World Bank, Washington, DC, 2019-03)Country-level census data are typically collected once every 10 years. However, conflict, migration, urbanization, and natural disasters can cause rapid shifts in local population patterns. This study uses Sri Lankan data to demonstrate the feasibility of a bottom-up method that combines household survey data with contemporaneous satellite imagery to track frequent changes in local population density. A Poisson regression model based on indicators derived from satellite data, selected using the least absolute shrinkage and selection operator, accurately predicts village-level population density. The model is estimated in villages sampled in the 2012/13 Household Income and Expenditure Survey to obtain out-of-sample density predictions in the nonsurveyed villages. The predictions approximate the 2012 census density well and are more accurate than other bottom-up studies based on lower-resolution satellite data. The predictions are also more accurate than most publicly available population products, which rely on areal interpolation of census data to redistribute population at the local level. The accuracies are similar when estimated using a random forest model, and when density estimates are expressed in terms of population counts. The collective evidence suggests that combining surveys with satellite data is a cost-effective method to track local population changes at more frequent intervals.Publication Protected Areas and Deforestation : New Results from High Resolution Panel Data(World Bank Group, Washington, DC, 2014-11)This paper investigates the effectiveness of protected areas in slowing tropical forest clearing in 64 countries in Asia/Pacific, Africa, and Latin America for the period 2001-2012. The investigation compares deforestation rates inside and within 10 kilometers outside the boundary of protected areas. Annual time series of these deforestation rates were constructed from recently published high-resolution data on forest clearing. For 4,028 parks, panel estimation based on a variety of park characteristics was conducted to test if deforestation is lower in protected areas because of their protected status, or if other factors explain the difference. For a sample of 726 parks established since 2002, a test also was conducted to investigate the effect of park establishment on protection. The findings suggest park size, national park status, and management by indigenous people all have significant association with effective protection across regions. For the Asia/Pacific region, the test offers compelling evidence that park establishment has a near-immediate and powerful effect.Publication Big Data and Thriving Cities(World Bank, Washington, DC, 2017-03)The recent global diffusion of new technologies, combined with the use of big data analytics, can help policymakers promote the effective development of future cities that provide living and work environments in which citizens can thrive. In particular, innovative applications of geospatial and sensing technologies and the penetration of mobile phone technology are providing unprecedented data collection This data can be analyzed for many purposes, including tracking population and mobility, private sector investment, and transparency in federal and local government. To help development practitioners within and beyond the World Bank take advantage of these trends, this brief profiles a sample of big data applications to support improved urban development in low- and middle-income countries. It also cites potential opportunities for big data analytics to help developing nations achieve sustainable urban growth, while reducing the economic differential with high-income countries.Publication Scaling up Social Assistance Where Data is Scarce(Washington, DC: World Bank, 2024-05-15)During the recent Covid-19 shock (2020/21), most countries used cash transfers to protect the livelihoods of those affected by the pandemic or by restrictions on mobility or economic activities, including the poor and vulnerable. While a large majority of countries mobilized existing programs and/or administrative databases to expand support to new beneficiaries, countries without such programs or databases were severely limited in their capacity to respond. Leveraging the Covid-19 shock as an opportunity to leapfrog and innovate, various low-income countries used new sources of data and computational methods to rapidly develop -level welfare-targeted programs. This paper reviews both crisis-time programs and regular social protection operations to distill lessons that could be applicable for both contexts. It examines three programs from the Democratic Republic of Congo, Togo, and Nigeria that used geospatial and mobile phone usage data and/or artificial intelligence (AI), particularly machine learning methods to estimate the welfare of applicants for individual-level welfare targeting and deliver emergency cash transfers in response to the pandemic. Additionally, it reviews two post-pandemic programs, in Lomé, Togo and in rural Lilongwe, Malawi, that incorporated those innovations into the more traditional delivery infrastructure and expanded their monitoring and evaluation framework. The rationale, key achievements, and main challenges of the various approaches are considered, and cases from other countries, as well as innovations beyond targeting, are taken into account. The paper concludes with policy recommendations and promising research topics to inform the discourse on leveraging novel data sources and estimation methods for improved social assistance in and beyond emergency settings.Publication Meta-Evaluation of IEG Evaluations (FY15-19)(Washington, DC: World Bank, 2022-02-14)IEG’s meta-evaluation serves as an input for the upcoming independent external review of its evaluations. The report focuses on aspects of credibility related to the rationale, focus, use of innovative methods, and various research design attributes as formulated in evaluation reports and their respective approach papers. Drawing on a set of 28 evaluations published from fiscal year 2015 to 2019, the meta-evaluation offers six major conclusions and suggestions based on a systematic review of evaluation scope, reliability, validity (including construct, internal, external, and data analysis validity), consistency, and the integration of innovative methods.
Users also downloaded
Showing related downloaded files
Publication Education, Social Norms, and the Marriage Penalty(Washington, DC: World Bank, 2024-10-16)A growing literature attributes gender inequality in labor market outcomes in part to the reduction in female labor supply after childbirth, the child penalty. However, if social norms constrain married women’s activities outside the home, then marriage can independently reduce employment, even in the absence childbearing. Given the correlation in timing between childbirth and marriage, conventional estimates of child penalties will conflate these two effects. The paper studies the marriage penalty in South Asia, a context featuring conservative gender norms and low female labor force participation. The study introduces a split-sample, pseudo-panel approach that allows for the separation of marriage and child penalties even in the absence of individual-level panel data. Marriage reduces women’s labor force participation in South Asia by 12 percentage points, whereas the marginal penalty of childbearing is small. Consistent with the central roles of both opportunity costs and social norms, the marriage penalty is smaller among cohorts with higher education and less conservative gender attitudes.Publication Remarks at the United Nations Biodiversity Conference(World Bank, Washington, DC, 2021-10-12)World Bank Group President David Malpass discussed biodiversity and climate change being closely interlinked, with terrestrial and marine ecosystems serving as critically important carbon sinks. At the same time climate change acts as a direct driver of biodiversity and ecosystem services loss. The World Bank has financed biodiversity conservation around the world, including over 116 million hectares of Marine and Coastal Protected Areas, 10 million hectares of Terrestrial Protected Areas, and over 300 protected habitats, biological buffer zones and reserves. The COVID pandemic, biodiversity loss, climate change are all reminders of how connected we are. The recovery from this pandemic is an opportunity to put in place more effective policies, institutions, and resources to address biodiversity loss.Publication Media and Messages for Nutrition and Health(World Bank, Washington, DC, 2020-06)The Lao People’s Democratic Republic (Lao PDR) has experienced rapid and significant economic growth over the past decade. However, poor nutritional outcomes remain a concern. Rates of childhood undernutrition are particularly high in remote, rural, and upland areas. Media have the potential to play an important role in shaping health and nutrition–related behaviors and practices as well as in promoting sociocultural and economic development that might contribute to improved nutritional outcomes. This report presents the results of a media audit (MA) that was conducted to inform the development and production of mass media advocacy and communication strategies and materials with a focus on maternal and child health and nutrition that would reach the most people from the poorest communities in northern Lao PDR. Making more people aware of useful information, essential services and products and influencing them to use these effectively is the ultimate goal of mass media campaigns, and the MA measures the potential effectiveness of media efforts to reach this goal. The effectiveness of communication channels to deliver health and nutrition messages to target beneficiaries to ensure maximum reach and uptake can be viewed in terms of preferences, satisfaction, and trust. Overall, the four most accessed media channels for receiving information among communities in the study areas were village announcements, mobile phones, television, and out-of-home (OOH) media. Of the accessed media channels, the top three most preferred channels were village announcements (40 percent), television (26 percent), and mobile phones (19 percent). In terms of trust, village announcements were the most trusted source of information (64 percent), followed by mobile phones (14 percent) and television (11 percent). Hence of all the media channels, village announcements are the most preferred, have the most satisfied users, and are the most trusted source of information in study communities from four provinces in Lao PDR with some of the highest burden of childhood undernutrition.Publication Economic Recovery(World Bank, Washington, DC, 2021-04-06)World Bank Group President David Malpass spoke about the world facing major challenges, including COVID, climate change, rising poverty and inequality and growing fragility and violence in many countries. He highlighted vaccines, working closely with Gavi, WHO, and UNICEF, the World Bank has conducted over one hundred capacity assessments, many even more before vaccines were available. The World Bank Group worked to achieve a debt service suspension initiative and increased transparency in debt contracts at developing countries. The World Bank Group is finalizing a new climate change action plan, which includes a big step up in financing, building on their record climate financing over the past two years. He noted big challenges to bring all together to achieve GRID: green, resilient, and inclusive development. Janet Yellen, U.S. Secretary of the Treasury, mentioned focusing on vulnerable people during the pandemic. Kristalina Georgieva, Managing Director of the International Monetary Fund, focused on giving everyone a fair shot during a sustainable recovery. All three commented on the importance of tackling climate change.Publication Making Procurement Work Better – An Evaluation of the World Bank’s Procurement System(Washington, DC: World Bank, 2024-12-06)This evaluation assesses the results, successes, and challenges of the World Bank 2016 procurement reform. Procurements acquire the works, goods, and services necessary to achieve the World Bank’s project development outcomes. The World Bank’s procurement processes must ensure that clients get the best value for every development dollar. In 2016, the World Bank reformed its procurement system for Investment Project Financing and launched a new procurement framework aimed at enhancing the Bank’s development effectiveness through better procurement. The reform sought to reduce procurement bottlenecks impeding project performance and modernize procurement systems. It emphasized cutting edge international good practice principles and was intended to be accompanied by procurement capacity strengthening to help client countries. This evaluation offers three recommendations to scale up reform implementation and enhance portfolio and project performance: (i) Improve change management support for the reform’s implementation. (ii) Strategically strengthen country-level procurement capacity. (iii) Consistently manage the full spectrum of procurement risks to maximize project success.