OPAL for Public Data and Good

What?

OPAL is a data-powered decision and coordination support system for development and humanitarian interventions.

How?

The platform provides analysis, decisions, coordination, incident monitoring, task tracking, and real-time feedback for better impact management on specific Areas.

The modular Impact-Areas provide an additional layer within OPAL, enabling targeted analysis, coordination, and decision-making for specific sectors such as health, agriculture, infrastructure, and social inequalities.

Why?

The use of OPAL is essential in expanding Big Data’s social potential while ensuring inclusivity, particularly in humanitarian contexts. By enabling privacy-preserving access to sensitive datasets through a “send the code to the data” model, OPAL facilitates equitable data use without compromising individual privacy.

This approach allows governments, NGOs, and researchers to get insights that inform policies and interventions, reaching vulnerable and often overlooked populations. Unlike limited, ad hoc data access methods, OPAL offers a scalable, secure, and transparent framework that fosters trust and enables the design of humanitarian initiatives that leave no one behind.

Mission

OPAL exists to close the gap between information and action in humanitarian crises.
We work toward shaping technological, legal and ethical frameworks that keep sensitive, locally generated data in the hands of the communities it concerns, while putting it to work for the common good.
Concretely, OPAL equips responders with a trusted platform that:

Integrates real-time, privacy-protected data from satellites, sensors, and community-participatory insights;
Generates risks models and actionable recommendations through AI models;
Automates routine alerts and task assignments, so teams can act faster; and
Coordinates government, NGO and community efforts before, during and after a disaster.

By pairing responsible data governance with rapid, data-driven decision-making, OPAL empowers organizations to protect more lives, livelihoods and infrastructure.

OPAL for Flood | Senegal Pilot

Every rainy season, large areas of Senegal’s river valley disappear under water, crippling harvests, uprooting families and eroding hard-won development gains. Globally, floods already cause US $105 billion in damage each year and force more than 20 million people from their homes. With climate change projected to drive a 20–40 % jump in flood frequency by 2050 (IPCC), the stakes for countries like Senegal—where agriculture remains the main livelihood for 46 % of households (Le Monde, 2025)—are only getting higher. Yet today’s flood-response systems are fragmented and reactive, hampered by siloed data and minimal real-time coordination.

OPAL for Flood turns that weakness into strength. Our platform ingests satellite imagery, different datasets, and community inputs, then uses machine-learning models to provide insights of where, when and whom flood might hit. The platform translate those insights into clear, shared action plans: alerting residents in real time, guiding local officials on how to respond (e.g., where to pre-position pumps or how to allocate cash transfers), and helping national agencies coordinate relief in real time.
By moving from after-the-fact reaction to AI and data-driven prevention and joint action, OPAL for Flood aims to safeguard lives, protect livelihoods and build lasting climate resilience.

Other countries in West Africa are being considered to pilot OPAL
for Floods.

Supporting Organizations

Real World Applications

OPAL and its technology have already proven effective in a number of ongoing projects. A brief summary of these applications is as follows:

Exploiting the Possibilities Offered by Big Data to Monitor the Achievement of the Sustainable Development Goals in Morocco

This project, supported by UNDP Morocco and the Moroccan Ministry of Economy and Finance, aimed to improve official statistical methodologies by using Big Data, in order to improve the timeliness and reliability of progress towards the Sustainable Development Goals. Additionally, this project contributed to strengthening the Moroccan digital ecosystem by improving the design, implementation, and monitoring of fair public policies, and informing better investment decisions towards achieving g the SDGs. Our organization conducted a benchmark study and developed three pilot publications to monitor priority indicators for sustainable development in Morocco: mental health (target 3.4) using Google Trends data; water stress (indicator 6.4.2) using earth observation; and ICT skills (indicator 4.4.1) using data collected through an online survey in Facebook.

Climate-Induced Migration in Africa and Beyond: Big Data and Predicative Analytics (CLIMB)

Senegal, Sub-Saharan Africa (SSA)
September 2023 - December 2025
Partner(s): Belmont Forum (Funder), IDEMA, Initiative Prospective Agricole et Rurale (IPAR), Malmö University (MAU), Paris-Lodron-University Salzburg (PLUS), The Institute for Quantitative Social Science (IQSS) at Harvard University, Vrije Universiteit

Climate change (interlinked with humanitarian crises and other economic and health factors) could have led to internal resettlements, international migration, and other (new) forms of human mobility. However, the empirical link between various climatic conditions and migration outcomes was highly contested, and, to date, no unified theoretical approach had adequately captured the complexity and contextual dependency of climate-induced migration. To address this gap, CLIMB sought to develop a holistic approach which would allow a better understanding of the mechanisms and pathways underlying the climate-migration nexus, and to predict temporal-spatial mobility patterns in Africa and beyond. Specifically, we investigated how climate change might intersect with conflicts, poverty, and epidemics, among other adversities, and how these forces might operate in tandem in driving human migration, with a special focus on Africa.

MPI+: Leveraging Non-Traditional Data to Monitor and Map Multidimensional Poverty in the Favelas of Brazil

This project leveraged novel ‘non-traditional’ data for mapping and monitoring multidimensional poverty in informal urban settings, while taking into account and reflecting context-specific nuances. It was carried out in partnership with and build on the work of the Brazilian NGO Gerando Falcões (GF), and focuses on 2 Brazilian favelas—Morro da Providência in Rio de Janeiro and Favela dos Sonhos in São Paulo. Concretely, we sought to evaluate and estimate different proxies from a subset of dimensions of the Multidimensional Poverty Index (MPI+) developed by GF using survey data. These proxy estimates enable to map and monitor multidimensional poverty patterns and trends at fine grained levels of spatial and temporal granularity, and possibly at lower costs. The project yielded indicators and methodologies that could be expanded to other dimensions of the index, as well as other Brazilian favelas, and possibly other countries.

Resources

Official statistics and big data in Latin America: Data enclosures and counter-movements

With the rise of the data-driven economy, the state-owned sector of official statistics has been pressured to ‘modernise’ and engage with Big Data. However, most of these data sources are controlled by tech corporations. This journal article address the conflicts this brings about from a Latin American perspective through three case studies—including OPAL—, involving national statistical offices, international organizations, and the private sector.