MWI-001

Geospatial Poverty Mapping for Village-Level Area Targeting in Social Assistance Programmes (Malawi)

Download PDF
Malawi Sub-Saharan Africa Low income Design & Development Phase Likely

World Bank Poverty and Equity Global Practice research team (Melany Gualavisi, David Newhouse for WBER study; Roy van der Weide, Brian Blankespoor, Chris Elbers, Peter Lanjouw for JDE study); United Nations ESCAP Statistics Division (geospatial SAE guide); National Statistical Office of Malawi (IHS survey data custodian).

At a Glance

What it does Prediction (including forecasting) — Vulnerability, needs and risk assessment, including predictive analytics
Who runs it World Bank Poverty and Equity Global Practice research team (Melany Gualavisi, David Newhouse for WBER study; Roy van der Weide, Brian Blankespoor, Chris Elbers, Peter Lanjouw for JDE study); United Nations ESCAP Statistics Division (geospatial SAE guide); National Statistical Office of Malawi (IHS survey data custodian).
Programme Geospatial poverty mapping for village-level area targeting (research using household survey, satellite imagery, and partial registry data)
Confidence Likely
Deployment Status Design & Development Phase
Key Risks Data-related risks
Key Outcomes Partial registry model achieves rank correlation of 0.
Source Quality 2 sources — Academic journal article

This case concerns a body of applied research led by World Bank Poverty and Equity Global Practice researchers and academic partners, which develops and evaluates machine-learning-based geospatial poverty mapping methods to support village-level geographical targeting of social assistance programmes in Malawi. The research programme spans multiple studies published between 2022 and 2025, addressing a core operational challenge in low-income countries: how to identify the poorest villages for geographic targeting when comprehensive household-level data are unavailable or outdated.

The primary methodological contribution, documented in the World Bank Economic Review (Gualavisi and Newhouse, 2025, Vol. 39, No. 2, pp. 377-409), introduces a cost-effective strategy that combines household consumption survey data, publicly available geospatial indicators, and a simulated partial registry to produce village-level poverty estimates. The partial registry simulates data from 450 villages across 10 impoverished districts in Malawi, containing proxy poverty indicators collected at the household level. These proxy indicators are used to impute estimates of household per capita consumption, which in turn train a prediction model using publicly available geospatial data. The machine-learning approach employs XGBoost (extreme gradient boosting), a tree-based ensemble algorithm, to integrate the survey and geospatial features for prediction. The geospatial predictors include publicly available satellite-derived indicators such as night-time light intensity, normalised difference vegetation index (NDVI) from satellite imagery, land cover classifications, road network density, population density estimates, and building footprint data. The household survey data come from the Malawi Integrated Household Survey (IHS), which is a nationally representative consumption and expenditure survey conducted by the National Statistical Office of Malawi with World Bank support.

The key quantitative finding is that the partial registry model achieves a rank correlation of 0.75 with actual village-level welfare measures, substantially outperforming three alternative approaches: proxy means test (PMT) scores, the Meta Relative Wealth Index, and predictions from household survey data combined with geospatial indicators alone, which produced rank correlations ranging from negative 0.02 to 0.2. The results hold under various robustness checks, including the addition of Gaussian noise to the proxy poverty indicators, demonstrating that even imperfect household-level data from a partial registry significantly improves the accuracy of geospatial poverty predictions for village-level geographic targeting.

A complementary study by van der Weide, Blankespoor, Elbers, and Lanjouw, published in the Journal of Development Economics (2024, Vol. 167), directly evaluates the accuracy of poverty maps based on remote sensing data alone in Malawi. The study first obtains small area estimates (SAE) of poverty by combining household expenditure survey data with population census data as a benchmark, then produces a second poverty map using only survey data combined with predictors derived from remote sensing. The two approaches reveal similar broad geographic poverty patterns, but the remote-sensing-based maps are less reliable for estimates of specific small areas. The study concludes that remote-sensing-based poverty maps may perform adequately for comparing poverty between assemblies of areas but should be used with caution when the focus is on estimates for individual small areas.

A further methodological contribution is provided by the United Nations ESCAP Statistics Division (2024), which developed a geospatial small area estimation how-to guide using Northern Malawi as a worked example. This guide demonstrates how geospatial indicators can be integrated with survey data using small area estimation techniques to produce poverty estimates at fine geographic scales, with evidence suggesting that combining geospatial data with surveys increases the precision of poverty estimates by an amount equivalent to expanding the survey sample by a factor of 3 to 7, depending on the context and indicator.

The technical approach across these studies uses traditional machine learning rather than deep learning or foundation models. The primary algorithms include XGBoost (gradient-boosted decision trees), along with other ensemble and regression methods. The models are trained on combinations of household survey variables and geospatial features, with the prediction target being village or primary sampling unit (PSU) level consumption or poverty estimates. No automated eligibility decisions are made; the outputs are informational poverty maps and rankings used by human analysts and policymakers to inform geographic targeting decisions for social assistance programmes.

The research is situated within the context of Malawi's social assistance system, where geographic targeting is used to prioritise districts and communities for programme coverage. Malawi is a low-income country in Sub-Saharan Africa where approximately half the population lives below the national poverty line. The social protection system includes several poverty-targeted cash transfer programmes, most notably the Social Cash Transfer Programme (SCTP) and the Malawi Social Action Fund (MASAF), both of which use geographic and community-based targeting mechanisms to identify beneficiaries. The poverty maps produced by these research methods could directly inform the first stage of this targeting process, helping to identify which villages and areas should receive priority coverage.

The implementing agencies include the World Bank Poverty and Equity Global Practice research team, with key researchers including Melany Gualavisi and David Newhouse for the WBER study, and Roy van der Weide, Brian Blankespoor, Chris Elbers, and Peter Lanjouw for the JDE study. The UNESCAP guide was produced by the Statistics Division in collaboration with academic partners. No operational deployment of these models within Malawi's social protection delivery system has been documented; all work remains at the research and development stage.

Human oversight is inherent in the research context: analysts develop, validate, and interpret the poverty maps, and no automated eligibility or benefit decisions are made. The decision criticality is low because the outputs serve as informational inputs to geographic targeting decisions rather than directly determining individual eligibility. The primary risks relate to data quality and representation, as the accuracy of poverty predictions depends on the quality and coverage of both the household survey data and the geospatial indicators, and there are documented concerns about the reliability of remote-sensing-based estimates for specific small areas.

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Assessment of needs/conditions + enrolment primaryMonitoring and evaluation
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social assistance
Programme Name Geospatial poverty mapping for village-level area targeting (research using household survey, satellite imagery, and partial registry data)
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Poverty targeted Cash Transfers (conditional or unconditional)
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Programme Description Research programme developing machine-learning-based geospatial poverty mapping methods to support village-level geographic targeting of social assistance programmes in Malawi. The methods are designed to inform the first stage of geographic targeting used by programmes such as the Social Cash Transfer Programme (SCTP) and the Malawi Social Action Fund (MASAF), which use geographic and community-based targeting to allocate programme coverage across villages and districts.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Classical ML
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Model Selection and Training
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Adapted from open-source
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary Not documented
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary Not assessed
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Not documented
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary Not documented
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary Low
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HITL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Mix of in-house and third-party
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Data-related risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Informal assessment

Risk Dimensions

Operational and system integration risks
  • Human oversight protocol
  • Independent evaluation
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Geospatial and remote sensing dataNon-personalLinks data across multiple systemsCurrently available and usedPublicly available satellite-derived indicators including night-time light intensity (VIIRS), NDVI vegetation indices, land cover classifications, road network density, population density estimates, and building footprint data; varying spatial resolutions; cloud cover affects temporal coverage during rainy season
Social registriesPersonalLinks data across multiple systemsPrecondition that would need to be establishedSimulated partial registry containing proxy poverty indicators from 450 villages across 10 impoverished districts; in operational context would require household-level data collection in target areas; demonstrates that even imperfect household data significantly improves geospatial predictions
Survey and census dataPersonalSingle source (no linkage)Currently available and usedMalawi Integrated Household Survey (IHS) conducted by National Statistical Office with World Bank support; nationally representative consumption and expenditure survey; updated periodically but not continuously; provides ground-truth welfare measures for model training

Gualavisi, M. and Newhouse, D. (2025) 'Integrating Survey and Geospatial Data for Geographical Targeting of the Poor and Vulnerable: Evidence from Malawi', The World Bank Economic Review, 39(2), pp. 377-409. doi:10.1093/wber/lhf008.

View source Academic journal article

van der Weide, R., Blankespoor, B., Elbers, C. and Lanjouw, P. (2024) 'How accurate is a poverty map based on remote sensing data? An application to Malawi', Journal of Development Economics, 171, 103349. doi: 10.1016/j.jdeveco.2024.103349.

View source Academic journal article
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Design & Development Phase
Year Initiated The year the AI system was first initiated or development began. 2022
Scale / Coverage The scale and geographic or population coverage of the deployment. Simulated partial registry covering 450 villages across 10 impoverished districts in Malawi; nationally representative IHS survey data; no operational deployment
Technical Partners External technology vendors, academic partners, or development partners involved. World Bank Poverty and Equity Global Practice; academic partners associated with World Bank research programme. No commercial vendor involvement documented.
Outcomes / Results Partial registry model achieves rank correlation of 0.75 with actual village-level welfare, substantially outperforming PMT scores, Meta Relative Wealth Index, and survey-plus-geospatial predictions alone (rank correlations ranging from -0.02 to 0.2) (Gualavisi and Newhouse, WBER 2025). Remote-sensing-based poverty maps replicate broad geographic poverty patterns but are less reliable for specific small areas (van der Weide et al., JDE 2024). Combining geospatial data with surveys using SAE increases precision equivalent to expanding sample by factor of 3 to 7 (UNESCAP, 2024).
Challenges Remote-sensing-based poverty maps less reliable for small-area estimates than census-based SAE benchmarks. Accuracy of village-level predictions depends on quality and coverage of household survey data and geospatial indicators. No operational deployment documented despite research completion. Geospatial predictors alone insufficient without ground-truth survey data. Partial registry approach requires initial investment in household-level data collection in target areas.

How to Cite

DCI AI Hub (2026). 'Geospatial Poverty Mapping for Village-Level Area Targeting in Social Assistance Programmes (Malawi)', AI Hub AI Tracker, case MWI-001. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/MWI-001 [Accessed: 1 April 2026].

Change History

Created 30 Mar 2026, 08:40
by v2-import (import)