Paper by Nathan Ratledge et al: “In many regions of the world, sparse data on key economic outcomes inhibits the development, targeting, and evaluation of public policy. We demonstrate how advancements in satellite imagery and machine learning can help ameliorate these data and inference challenges. In the context of an expansion of the electrical grid across Uganda, we show how a combination of satellite imagery and computer vision can be used to develop local-level livelihood measurements appropriate for inferring the causal impact of electricity access on livelihoods. We then show how ML-based inference techniques deliver more reliable estimates of the causal impact of electrification than traditional alternatives when applied to these data. We estimate that grid access improves village-level asset wealth in rural Uganda by 0.17 standard deviations, more than doubling the growth rate over our study period relative to untreated areas. Our results provide country-scale evidence on the impact of a key infrastructure investment, and provide a low-cost, generalizable approach to future policy evaluation in data sparse environments….(More)”.
Big Data in Biodiversity Science: A Framework for Engagement
Paper by Tendai Musvuugwa, Muxe Gladmond Dlomu and Adekunle Adebowale: “Despite best efforts, the loss of biodiversity has continued at a pace that constitutes a major threat to the efficient functioning of ecosystems. Curbing the loss of biodiversity and assessing its local and global trends requires a vast amount of datasets from a variety of sources. Although the means for generating, aggregating and analyzing big datasets to inform policies are now within the reach of the scientific community, the data-driven nature of a complex multidisciplinary field such as biodiversity science necessitates an overarching framework for engagement. In this review, we propose such a schematic based on the life cycle of data to interrogate the science. The framework considers data generation and collection, storage and curation, access and analysis and, finally, communication as distinct yet interdependent themes for engaging biodiversity science for the purpose of making evidenced-based decisions. We summarize historical developments in each theme, including the challenges and prospects, and offer some recommendations based on best practices….(More)”.
Designing data collaboratives to better understand human mobility and migration in West Africa
“The Big Data for Migration Alliance (BD4M) is released the report, “Designing Data Collaboratives to Better Understand Human Mobility and Migration in West Africa,” providing findings from a first-of-its-kind rapid co-design and prototyping workshop, or “Studio.” The first BD4M Studio convened over 40 stakeholders in government, international organizations, research, civil society, and the public sector to develop concrete strategies for developing and implementing cross- sectoral data partnerships, or “data collaboratives,” to improve ethical and secure access to data for migration-related policymaking and research in West Africa.
BD4M is an effort spearheaded by the International Organization for Migration’s Global Migration Data Analysis Centre (IOM GMDAC), European Commission’s Joint Research Centre (JRC), and The GovLab to accelerate the responsible and ethical use of novel data sources and methodologies—such as social media, mobile phone data, satellite imagery, artificial intelligence—to support migration-related programming and policy on the global, national, and local levels.
The BD4M Studio was informed by The Migration Domain of The 100 Questions Initiative — a global agenda-setting exercise to define the most impactful questions related to migration that could be answered through data collaboration. Inspired by the outputs of The 100 Questions, Studio participants designed data collaboratives that could produce answers to three key questions:
- How can data be used to estimate current cross-border migration and mobility by sex and age in West Africa?
- How can data be used to assess the current state of diaspora communities and their migration behavior in the region?
- How can we use data to better understand the drivers of migration in West Africa?…(More)”
Mapping Africa’s Buildings with Satellite Imagery
Google AI Blog: “An accurate record of building footprints is important for a range of applications, from population estimation and urban planning to humanitarian response and environmental science. After a disaster, such as a flood or an earthquake, authorities need to estimate how many households have been affected. Ideally there would be up-to-date census information for this, but in practice such records may be out of date or unavailable. Instead, data on the locations and density of buildings can be a valuable alternative source of information.
A good way to collect such data is through satellite imagery, which can map the distribution of buildings across the world, particularly in areas that are isolated or difficult to access. However, detecting buildings with computer vision methods in some environments can be a challenging task. Because satellite imaging involves photographing the earth from several hundred kilometres above the ground, even at high resolution (30–50 cm per pixel), a small building or tent shelter occupies only a few pixels. The task is even more difficult for informal settlements, or rural areas where buildings constructed with natural materials can visually blend into the surroundings. There are also many types of natural and artificial features that can be easily confused with buildings in overhead imagery.
In “Continental-Scale Building Detection from High-Resolution Satellite Imagery”, we address these challenges, using new methods for detecting buildings that work in rural and urban settings across different terrains, such as savannah, desert, and forest, as well as informal settlements and refugee facilities. We use this building detection model to create the Open Buildings dataset, a new open-access data resource containing the locations and footprints of 516 million buildings with coverage across most of the African continent. The dataset will support several practical, scientific and humanitarian applications, ranging from disaster response or population mapping to planning services such as new medical facilities or studying human impact on the natural environment….(More)”.
Machine Learning and Mobile Phone Data Can Improve the Targeting of Humanitarian Assistance
Paper by Emily Aiken et al: “The COVID-19 pandemic has devastated many low- and middle-income countries (LMICs), causing widespread food insecurity and a sharp decline in living standards. In response to this crisis, governments and humanitarian organizations worldwide have mobilized targeted social assistance programs. Targeting is a central challenge in the administration of these programs: given available data, how does one rapidly identify the individuals and families with the greatest need? This challenge is particularly acute in the large number of LMICs that lack recent and comprehensive data on household income and wealth.
Here we show that non-traditional “big” data from satellites and mobile phone networks can improve the targeting of anti-poverty programs. Our approach uses traditional survey-based measures of consumption and wealth to train machine learning algorithms that recognize patterns of poverty in non-traditional data; the trained algorithms are then used to prioritize aid to the poorest regions and mobile subscribers. We evaluate this approach by studying Novissi, Togo’s flagship emergency cash transfer program, which used these algorithms to determine eligibility for a rural assistance program that disbursed millions of dollars in COVID-19 relief aid. Our analysis compares outcomes – including exclusion errors, total social welfare, and measures of fairness – under different targeting regimes. Relative to the geographic targeting options considered by the Government of Togo at the time, the machine learning approach reduces errors of exclusion by 4-21%. Relative to methods that require a comprehensive social registry (a hypothetical exercise; no such registry exists in Togo), the machine learning approach increases exclusion errors by 9-35%. These results highlight the potential for new data sources to contribute to humanitarian response efforts, particularly in crisis settings when traditional data are missing or out of date….(More)”.
Enhancing teacher deployment in Sierra Leone: Using spatial analysis to address disparity
Blog by Paul Atherton and Alasdair Mackintosh:”Sierra Leone has made significant progress towards educational targets in recent years, but is still struggling to ensure equitable access to quality teachers for all its learners. The government is exploring innovative solutions to tackle this problem. In support of this, Fab Inc. has brought their expertise in data science and education systems, merging the two to use spatial analysis to unpack and explore this challenge….
Figure 1: Pupil-teacher ratio for primary education by district (left); and within Kailahun district, Sierra Leone, by chiefdom (right), 2020.
Source: Mackintosh, A., A. Ramirez, P. Atherton, V. Collis, M. Mason-Sesay, & C. Bart-Williams. 2019. Education Workforce Spatial Analysis in Sierra Leone. Research and Policy Paper. Education Workforce Initiative. The Education Commission.
…Spatial analysis, also referred to as geospatial analysis, is a set of techniques to explain patterns and behaviours in terms of geography and locations. It uses geographical features, such as distances, travel times and school neighbourhoods, to identify relationships and patterns.
Our team, using its expertise in both data science and education systems, examined issues linked to remoteness to produce a clearer picture of Sierra Leone’s teacher shortage. To see how the current education workforce was distributed across the country, and how well it served local populations, we drew on geo-processed population data from the Grid-3 initiative and the Government of Sierra Leone’s Education Data Hub. The project benefited from close collaboration with the Ministry and Teaching Service Commission (TSC).
Our analysis focused on teacher development, training and the deployment of new teachers across regions, drawing on exam data. Surveys of teacher training colleges (TTCs) were conducted to assess how many future teachers will need to be trained to make up for shortages. Gender and subject speciality were analysed to better address local imbalances. The team developed a matching algorithm for teacher deployment, to illustrate how schools’ needs, including aspects of qualifications and subject specialisms, can be matched to teachers’ preferences, including aspects of language and family connections, to improve allocation of both current and future teachers….(More)”
Text Your Government: Participatory Cell Phone Technology in Ghana
Article by Emily DiMatteo: “Direct citizen engagement can be transformed with innovative technological tools. As communities search for new ways to connect citizens to democratic processes, using existing technological devices such as cell phones can reach a number of citizens—including those typically excluded from policy processes. This occurred in Ghana when a technology startup and social enterprise called VOTO Mobile (now Viamo) created polling and information sharing software that uses mobile phone SMS texts and voice calls. Since its founding in 2010, the Ghana-based company has worked to use mobile technology to advance democratic engagement and good governance through new communication channels between citizens and their government.
Previous methods to overcome public participation challenges in Ghana include using public radio. However, when VOTO Mobile evaluated technological capabilities in several districts, cell phones offered a new way to engage. The option to contact citizens via text or voice call also helped remove certain barriers to participation in political processes, including distance, language and literacy. In 2012-2013, VOTO Mobile facilitated a project called the, “Mobile for Social Inclusive Government,” to increase citizen engagement and participation. The project used the company’s software to disseminate local information and conduct citizen surveys in four Ghanaian districts: Tamale, Savelugu, Wa and Yendi. VOTO Mobile partnered with civil society organizations including Savana Signatures, GINKS and Amplify Governance, as well as District Assemblies in local district governments.
Participant selection for the project utilized pre-existing District Assembly membership data across the four districts to contact citizens to participate. This outreach also was supplemented by the project’s partner organizations and ultimately involved more than 2,000 participants. In using VOTO Mobile’s technological platform of interactive text and voice call surveys, the project gathered feedback from citizens as they shared concerns with their local government. There was a large focus on input from marginalized populations across the districts including women, young people and people with disabilities. In addition to the cell phone surveys, the platform enabled online consultations between citizens and local district officials in place of face-to-face visits.
As a result, local district governments were able to crowdsource information directly from citizens, leading to increased citizen input in subsequent policy formulation and planning processes….(More)”.
Ethiopia’s blockchain deal is a watershed moment – for the technology, and for Africa
Iwa Salami at The Conversation: “At the launch of bitcoin in 2009 the size of the potential of the underlying technology, the blockchain, was not fully appreciated.
What has not been fully exploited is the unique features of blockchain technology that can improve the lives of people and businesses. These include the fact that it is an open source software. This makes its source code legally and freely available to end-users who can use it to create new products and services. Another significant feature is that it is decentralised, democratising the operation of the services built on it. Control of the services built on the blockchain isn’t in the hands of an individual or a single entity but involves all those connected to the network.
In addition, it enables peer to peer interaction between those connected to the network. This is key as it enables parties to transact directly without using intermediaries or third parties. Finally, it has inbuilt security. Data stored on it is immutable and cannot be changed easily. New data can be added only after it is verified by everyone in the network.
Unfortunately, bitcoin, the project that introduced blockchain technology, has hogged the limelight, diverting attention from the technology’s underlying potential benefits….
But this is slowly changing.
A few companies have begun showcasing blockchain capabilities to various African countries. Unlike most other cryptocurrency blockchains which focus on private sector use in developed regions like Europe and North America, their approach has been to target the governments and public institutions in the developing world.
In April the Ethiopian government confirmed that it had signed a deal to create a national database of student and teacher IDs using a decentralised digital identity solution. The deal involves providing IDs for 5 million students across 3,500 schools which will be used to store educational records.
This is the largest blockchain deal ever to be signed by a government and has been making waves in the crypto-asset industry.
I believe that the deal marks a watershed moment for the use of blockchain and the crypto-asset industry, and for African economies because it offers the promise of blockchain being used for real socio-economic change. The deal means that blockchain technology will be used to provide digital identity to millions of Ethiopians. Digital identity – missing in most African countries – is the first step to real financial inclusion, which in turn has been shown to carry a host of benefits….(More)”.
The Case for Open Land-Data Systems
Tim Hanstad at Project Syndicate: “Last month, a former Zimbabwean cabinet minister was arrested for illegally selling parcels of state land. A few days earlier, a Malaysian court convicted the ex-chairman of a state-owned land development agency of corruption. And in January, the Estonian government collapsed amid allegations of corrupt property dealings. These recent events all turned the spotlight on the growing but neglected threat of land-related corruption.
Such corruption can flourish in countries that are unprepared to manage the heightened demand for land that accompanies economic and population growth. Land governance in these countries – institutions, policies, rules, and records for managing land rights and use – is underdeveloped, which undermines the security of citizens’ land rights and enables covert land grabs by the well connected.
In Ghana, for example, the government keeps land records for only about 2% of currently operating farms; the ownership of the remainder is largely undocumented. In India, these records were, until recently, often kept in disorganized stacks in government offices.
Under such circumstances, corruption becomes relatively easy and lucrative. After all, when recordkeeping is nonexistent or chaotic, who can confidently identify the rightful owner of a parcel of land? As the United Nations Food and Agriculture Organization and Transparency International put it in a report a decade ago, “where land governance is deficient, high levels of corruption often flourish.” This corruption “is pervasive and without effective means of control.”
Globally, one in five people report having paid a bribe to access land services. In Africa, two out of three people believe the rich are likely to pay bribes or use their connections to grab land. Uncertainty about land rights can also affect housing security – around a billion people worldwide say they expect to be forced from their homes over the next five years.
Inevitably, the marginalized and vulnerable are the worst affected, whether they are widows driven from their homes by speculators or entire communities subjected to forced eviction by developers. Weak land rights and corruption also fuel conflict within communities, such as in Kenya, where political parties promise already-occupied land to supporters in an attempt to win votes.
But there is reason for hope. The ongoing revolution in information and communications technology provides unprecedented opportunities to digitize and open land records. Doing so would clarify the land rights of hundreds of millions of people globally and limit the scope for corrupt practices….(More)”.
Bridging the data-policy gap in Africa
Report by PARIS21 and the Mo Ibrahim Foundation (MIF): “National statistics are an essential component of policymaking: they provide the evidence required to design policies that address the needs of citizens, to monitor results and hold governments to account. Data and policy are closely linked. As Mo Ibrahim puts it: “without data, governments drive blind”. However, there is evidence that the capacity of African governments for data-driven policymaking remains limited by a wide data-policy gap.
What is the data-policy gap?
On the data side, statistical capacity across the continent has improved in recent decades. However, it remains low compared to other world regions and is hindered by several challenges. African national statistical offices (NSOs) often lack adequate financial and human resources as well as the capacity to provide accessible and available data. On the policy side, data literacy as well as a culture of placing data first in policy design and monitoring are still not widespread. Thus, investing in the basic building blocks of national statistics, such as civil registration, is often not a key priority.
At the same time, international development frameworks, such as the United Nations 2030 Agenda for Sustainable Development and the African Union Agenda 2063, require that every signatory country produce and use high-quality, timely and disaggregated data in order to shape development policies that leave no one behind and to fulfil reporting commitments.
Also, the new data ecosystem linked to digital technologies is providing an explosion of data sourced from non-state providers. Within this changing data landscape, African NSOs, like those in many other parts of the world, are confronted with a new data stewardship role. This will add further pressure on the capacity of NSOs, and presents additional challenges in terms of navigating issues of governance and use…
Recommendations as part of a six-point roadmap for bridging the data-policy map include:
- Creating a statistical capacity strategy to raise funds
- Connecting to knowledge banks to hire and retain talent
- Building good narratives for better data use
- Recognising the power of foundational data
- Strengthening statistical laws to harness the data revolution
- Encouraging data use in policy design and implementation…(More)”