+254 721 331 808    training@upskilldevelopment.com

Home / Monitoring and Evaluation

Satellite-Derived Poverty Mapping for Programme Targeting Training Course

Strengthen programme targeting with satellite-derived poverty mapping. Learn to combine satellite imagery, household surveys, population data, GIS, and machine learning to identify priority areas, validate estimates, manage uncertainty, and support transparent, equitable development resource allocation.
Duration: 5 Days Classroom & Online In-House Available Certificate on Completion

Training Registration & Schedule

Compare training options, fees and available dates, then register for your preferred session.

Online Training Registration

Training ModePlatformDurationFee per ParticipantRegistration
LIVE ONLINEInstructor-led training Zoom / Google MeetAttend from anywhere 5 days USD 900 Register Online →

Classroom / On-site Training Schedule

15 upcoming sessions

Swipe horizontally to see all columns →

Training DatesLocationTraining ModeFee per ParticipantRegistration
07 Dec 2026 – 11 Dec 20265 training days Nairobi CLASSROOM USD 1,500 Register Now →
07 Dec 2026 – 11 Dec 20265 training days Nairobi CLASSROOM USD 1,500 Register Now →
07 Dec 2026 – 11 Dec 20265 training days Mombasa CLASSROOM USD 1,750 Register Now →
04 Jan 2027 – 08 Jan 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
01 Feb 2027 – 05 Feb 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
01 Mar 2027 – 05 Mar 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
05 Apr 2027 – 09 Apr 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
03 May 2027 – 07 May 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
07 Jun 2027 – 11 Jun 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
05 Jul 2027 – 09 Jul 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
02 Aug 2027 – 06 Aug 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
06 Sep 2027 – 10 Sep 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
04 Oct 2027 – 08 Oct 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
01 Nov 2027 – 05 Nov 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
06 Dec 2027 – 10 Dec 20275 training days Nairobi CLASSROOM USD 1,500 Register Now →
Need registration assistance? Contact training@upskilldevelopment.com for training dates, invoices and invitation letters.

Nairobi, Kenya Classroom/On-site Training Schedule

Course Date Location Fee Enroll
07/12/2026 to 11/12/2026 Nairobi 1,500 USD Register
07/12/2026 to 11/12/2026 Nairobi 1,500 USD Register
04/01/2027 to 08/01/2027 Nairobi 1,500 USD Register
01/02/2027 to 05/02/2027 Nairobi 1,500 USD Register
01/03/2027 to 05/03/2027 Nairobi 1,500 USD Register
05/04/2027 to 09/04/2027 Nairobi 1,500 USD Register
03/05/2027 to 07/05/2027 Nairobi 1,500 USD Register
07/06/2027 to 11/06/2027 Nairobi 1,500 USD Register
05/07/2027 to 09/07/2027 Nairobi 1,500 USD Register
02/08/2027 to 06/08/2027 Nairobi 1,500 USD Register
06/09/2027 to 10/09/2027 Nairobi 1,500 USD Register
04/10/2027 to 08/10/2027 Nairobi 1,500 USD Register
01/11/2027 to 05/11/2027 Nairobi 1,500 USD Register
06/12/2027 to 10/12/2027 Nairobi 1,500 USD Register

Mombasa, Kenya Classroom/On-site Training Schedule

Course Date Location Fee Enroll
07/12/2026 to 11/12/2026 Mombasa 1,750 USD Register

Kigali, Rwanda Classroom/On-site Training Schedule

Course Date Location Fee Enroll

Dubai, UAE Classroom/On-site Training Schedule

Course Date Location Fee Enroll

Dar es Salaam, Tanzania Classroom/On-site Training Schedule

Course Date Location Fee Enroll

Kampala, Uganda Classroom/On-site Training Schedule

Course Date Location Fee Enroll

Course Introduction

Satellite-derived poverty mapping is an increasingly valuable approach for understanding the geographic distribution of poverty and improving the targeting of development programmes. By combining satellite imagery, geographic information systems, population distribution data, household surveys, and statistical modelling, practitioners can develop spatial estimates of socioeconomic deprivation in areas where conventional statistics may be too aggregated, outdated, or unavailable. This training course equips participants with practical knowledge and analytical skills to produce, interpret, validate, and apply poverty maps for social protection, humanitarian assistance, health, education, livelihoods, rural development, and other poverty reduction interventions. The course emphasizes evidence-based targeting and the importance of understanding both the capabilities and limitations of satellite-derived estimates.

The programme introduces the main satellite and geospatial datasets used in poverty analysis, including daytime optical imagery, night-time lights, built-up area products, building footprints, vegetation indices, road networks, settlement maps, and population distribution grids. Participants will explore how these data can reveal characteristics associated with living conditions, such as settlement density, access to services, infrastructure availability, agricultural landscapes, and connectivity to economic opportunities. The course also examines the role of geolocated household surveys, census information, consumption expenditure records, asset indices, and multidimensional poverty indicators in providing reference data for model development. Participants will learn why satellite observations are most useful when interpreted alongside reliable socioeconomic information rather than treated as direct measurements of household income or poverty status.

A central component of the training focuses on the technical workflow for developing satellite-derived poverty maps. Participants will learn how to acquire and prepare geospatial datasets, harmonize coordinate systems, define suitable geographic units, extract spatial features, integrate population information, and construct analytical datasets. The course introduces statistical and machine learning approaches, including regression, random forests, gradient boosting, spatial modelling, and image-based feature extraction. Participants will examine how training data are used to establish relationships between observed welfare indicators and geographic characteristics, and how those relationships can be applied to estimate poverty-related indicators in locations with limited survey coverage. Practical exercises will emphasize reproducibility, careful feature selection, appropriate model design, and transparent documentation of analytical decisions.

The course gives particular attention to converting poverty maps into practical programme targeting strategies. Participants will examine how geographic poverty estimates can inform the selection of priority districts, communities, service delivery areas, and locations for additional field assessment. Applications will include social protection expansion, cash transfer programmes, food security interventions, health outreach, school support, water and sanitation investments, agricultural livelihoods, and emergency assistance. Participants will learn to combine estimated poverty prevalence with population counts, vulnerability indicators, service accessibility, operational constraints, and programme eligibility criteria to estimate the number of potentially underserved people and identify geographic gaps in coverage. The training also explores how poverty maps can support transparent prioritization, resource allocation, scenario analysis, and monitoring of geographic equity.

Reliable poverty mapping requires rigorous validation and a clear understanding of uncertainty. Satellite-derived features may reflect settlement density, infrastructure, vegetation, or economic activity without fully capturing household income, consumption, social exclusion, disability-related costs, or differences in living standards within the same neighbourhood. Urban informal settlements, remote rural communities, nomadic populations, and areas affected by conflict or displacement may be particularly difficult to characterize using remotely sensed information alone. Participants will learn to assess model performance, compare predictions against independent survey evidence, examine spatial and demographic disparities in prediction errors, and communicate confidence intervals or other uncertainty measures. The course stresses that a poverty map is an analytical aid rather than a definitive register of poor households, and that individual eligibility decisions require appropriate verification and established programme procedures.

Responsible use of satellite-derived poverty estimates is integrated throughout the training. Participants will examine privacy protection, data governance, informed consent where applicable, risks associated with combining sensitive datasets, algorithmic bias, and the consequences of misclassification for vulnerable communities. The course introduces safeguards for preventing geographic estimates from becoming an inappropriate substitute for household-level assessment, community consultation, or official eligibility verification. Participants will learn to document data sources, model assumptions, limitations, update requirements, and decision rules so that poverty mapping remains transparent and accountable. By the end of the course, they will be better equipped to develop practical geospatial poverty analysis workflows and use their findings to strengthen programme reach, improve resource allocation, and support equitable development outcomes.

Duration

5 days

Who Should Attend

  • Poverty reduction specialists responsible for identifying underserved populations and designing targeted development interventions.

  • Social protection officers planning cash transfers, social assistance, and safety-net programmes.

  • Monitoring, evaluation, accountability, and learning professionals assessing programme coverage and geographic equity.

  • GIS specialists and remote sensing analysts working with satellite imagery and socioeconomic geographic data.

  • Economists and poverty analysts conducting welfare measurement, spatial poverty analysis, and development research.

  • Government officials involved in national poverty reduction strategies, regional planning, and public resource allocation.

  • National statistics office personnel working with household surveys, census data, and small area estimation.

  • Humanitarian programme managers targeting assistance to vulnerable communities affected by shocks and displacement.

  • Food security and livelihoods specialists identifying priority locations for resilience and poverty alleviation interventions.

  • Health programme planners examining geographic deprivation and barriers to essential health services.

  • Education specialists targeting school support, learning interventions, and services in underserved communities.

  • Rural development practitioners assessing infrastructure gaps, market access, and geographically concentrated poverty.

  • International development agency and donor personnel responsible for programme design, targeting, and results monitoring.

  • Data scientists and machine learning practitioners developing geospatial welfare prediction models.

  • Public policy researchers examining spatial inequality, multidimensional poverty, and distributional outcomes.

  • NGO and civil society programme officers supporting community-level targeting and equitable service delivery.

  • Urban planners and municipal authorities analysing neighbourhood deprivation and informal settlement conditions.

  • Climate resilience and disaster recovery specialists identifying poverty exposure and vulnerable locations.

  • Consultants conducting poverty assessments, geospatial analysis, and programme feasibility studies.

  • Digital transformation professionals developing geospatial information systems and data-driven targeting tools.

Course Objectives

By the end of this course, participants will be able to:

  • Explain the principles of satellite-derived poverty mapping and distinguish remotely sensed indicators, model-based welfare estimates, small area estimates, and directly measured household poverty indicators.

  • Identify and acquire appropriate satellite imagery, population grids, building footprints, settlement layers, road networks, household surveys, census information, and socioeconomic reference datasets for poverty analysis.

  • Prepare and integrate geospatial and household-level datasets using consistent geographic boundaries, coordinate reference systems, spatial resolutions, quality checks, and reproducible data preparation procedures.

  • Extract relevant geospatial features, including built-up characteristics, night-time illumination, vegetation indicators, settlement density, and accessibility measures, to support poverty-related modelling.

  • Apply appropriate statistical and machine learning methods to estimate poverty prevalence, welfare indicators, or other clearly defined poverty-related outcomes from available survey and geographic information.

  • Evaluate model performance using suitable validation strategies, prediction error measures, independent reference data, and spatially informed testing that reduces the risk of misleading accuracy estimates.

  • Translate poverty mapping outputs into geographic programme targeting strategies by combining estimated poverty prevalence with population counts, vulnerability information, service gaps, and operational eligibility criteria.

  • Design prioritization approaches that consider uncertainty, materiality, geographic equity, population coverage, implementation costs, and the consequences of incorrectly classifying communities.

  • Apply responsible data governance practices covering privacy, bias assessment, transparent documentation, appropriate access controls, community safeguards, and the limitations of geographic estimates for individual decisions.

  • Develop a practical poverty mapping and programme targeting workflow that produces interpretable maps, priority-area analyses, validation summaries, and recommendations for programme planning and monitoring.

Comprehensive Course Outline

Module 1: Foundations of Satellite-Derived Poverty Mapping

  • Understanding poverty mapping, spatial deprivation, geographic inequality, welfare measurement, and the role of earth observation in development planning.

  • Distinguishing income poverty, consumption poverty, asset-based welfare, multidimensional poverty, and geographic proxies used in programme targeting.

  • Reviewing conventional poverty assessment approaches, household surveys, census-based estimates, small area estimation, and satellite-assisted alternatives.

  • Identifying suitable applications in social protection, humanitarian assistance, health, education, food security, livelihoods, and infrastructure investment.

Module 2: Satellite Imagery and Geospatial Data Sources

  • Examining optical satellite imagery, night-time lights, built-up area products, vegetation indices, building footprints, and other relevant geospatial indicators.

  • Acquiring population distribution grids, road networks, settlement layers, travel-time surfaces, administrative boundaries, and public service location datasets.

  • Reviewing household surveys, census information, consumption expenditure data, asset indices, and multidimensional poverty indicators as model reference sources.

  • Assessing spatial resolution, observation dates, coverage gaps, licensing, metadata, data quality, and compatibility between datasets.

Module 3: Geospatial Data Preparation and Feature Engineering

  • Preparing satellite imagery, administrative boundaries, population grids, and survey reference data for consistent spatial analysis.

  • Extracting features describing built-up intensity, settlement structure, vegetation, accessibility, night-time illumination, and proximity to infrastructure.

  • Linking geolocated survey observations with geographic features while accounting for survey design, spatial displacement, and confidentiality requirements.

  • Managing missing data, inconsistent spatial units, temporal mismatches, outliers, and documentation requirements for reproducible analytical workflows.

Module 4: Poverty Indicators and Model Development

  • Defining the intended prediction target, including poverty headcount, consumption-based welfare, asset-based indices, or multidimensional deprivation indicators.

  • Understanding relationships between household welfare and observable geographic characteristics without assuming that any single feature directly measures poverty.

  • Preparing model development datasets and selecting appropriate training, validation, and testing procedures for the available reference information.

  • Comparing regression, random forests, gradient boosting, and other suitable predictive approaches according to data characteristics and analytical objectives.

Module 5: Machine Learning and Advanced Poverty Prediction

  • Developing supervised learning workflows that link survey-derived welfare measures with satellite features and complementary geospatial covariates.

  • Exploring image-based prediction approaches that extract patterns from satellite imagery using suitable computer vision and deep learning methods.

  • Comparing feature-based, image-based, and hybrid modelling strategies according to prediction needs, computing resources, interpretability, and data availability.

  • Examining spatial dependence, model transferability, feature importance, overfitting, and the limitations of extrapolating predictions to unfamiliar areas.

Module 6: Poverty Map Production and Spatial Analysis

  • Producing poverty prevalence surfaces, welfare prediction maps, and geographic summaries using appropriate GIS and statistical software.

  • Aggregating model outputs to districts, municipalities, wards, settlements, or programme implementation areas while preserving meaningful spatial comparisons.

  • Combining estimated poverty rates with population grids to estimate the number of people potentially affected by poverty in priority locations.

  • Mapping service accessibility, settlement characteristics, geographic inequalities, and potential concentrations of underserved populations.

Module 7: Validation, Uncertainty, and Model Reliability

  • Evaluating predictive performance with suitable error measures, independent reference observations, and geographically appropriate validation strategies.

  • Examining spatial and demographic variation in prediction errors across urban, rural, remote, and underserved communities.

  • Quantifying or communicating uncertainty using prediction intervals, confidence measures where appropriate, sensitivity analysis, and alternative model scenarios.

  • Distinguishing descriptive spatial patterns, predictive accuracy, causal evidence, and the degree of confidence warranted for operational targeting decisions.

Module 8: Programme Targeting and Resource Allocation

  • Translating poverty maps into priority-area classifications and targeting scenarios aligned with programme objectives and eligibility rules.

  • Combining estimated poverty prevalence with population size, vulnerability, service gaps, accessibility, programme costs, and implementation capacity.

  • Comparing geographic targeting approaches and examining trade-offs between broad coverage, concentration of assistance, exclusion risks, and inclusion errors.

  • Developing priority lists and resource allocation scenarios that support transparent decisions while retaining appropriate household verification and community engagement.

Module 9: Responsible Poverty Mapping, Ethics, and Governance

  • Protecting household privacy and sensitive geographic information through data minimization, controlled access, secure storage, and appropriate disclosure practices.

  • Assessing algorithmic bias, unequal data coverage, underrepresentation of vulnerable groups, and risks associated with inappropriate geographic generalization.

  • Establishing documentation standards for data sources, model versions, prediction limitations, validation results, and decisions informed by poverty maps.

  • Designing safeguards that prevent model-based geographic estimates from being used as definitive evidence of an individual household's poverty status or programme eligibility.

Module 10: Practical Implementation and Targeting Strategy Development

  • Developing an end-to-end poverty mapping prototype using sample survey data, satellite-derived features, population information, and administrative boundaries.

  • Producing and interpreting spatial poverty estimates, priority-area maps, validation summaries, and uncertainty-aware programme targeting outputs.

  • Designing a practical implementation plan covering data access, analytical capacity, software, governance, stakeholder consultation, and future model updates.

  • Presenting a final targeting strategy that documents methods, limitations, prioritization criteria, validation findings, and recommendations for responsible programme use.

Training Approach

This course will be delivered by our skilled trainers who have vast knowledge and experience as expert professionals in the fields. The course is taught in English and through a mix of theory, practical activities, group discussion and case studies. Course manuals and additional training materials will be provided to the participants upon completion of the training.

Tailor-Made Course

This course can also be tailor-made to meet organization requirement. For further inquiries, please contact us on: Email: training@upskilldevelopment.com Tel: +254 721 331 808

Training Venue 

The training will be held at our Upskill Training Centre. We also offer training for a group (at a discount of 10% to 50%) at requested location all over the world. The Onsite course fee covers the course tuition, training materials, two break refreshments, buffet lunch, airport transfers, Upskill gift package, and guided tour.

Visa application, travel expenses, dinners, accommodation, insurance, and other personal expenses are catered by the participant

Certification

Participants will be issued with Upskill certificate upon completion of this course.

Airport Pickup and Accommodation

Airport pickup and accommodation is arranged upon request. For booking contact our Training Coordinator through Email: training@upskilldevelopment.com, +254 721 331 808

Terms of Payment:

Unless otherwise agreed between the two parties’ payment of the course fee should be done 3 working days before commencement of the training so as to enable us to prepare better.

Choose Your Training Format

Attend a scheduled session or request a customized programme for your organization.

Classroom Training

Attend instructor-led training at one of our scheduled training locations.

Live Online Training

Join interactive instructor-led sessions remotely from your office or home.

In-House Training

Customize the course content, dates and delivery for your team or organization.

Certification

Participants who successfully complete the programme receive a Certificate of Completion from Upskill Development Institute.

Request Course Information

Need a Tailor-Made Programme?

We can customize the course content, duration, schedule and delivery format to match your organization's objectives.

Dates & Fees Enquire Now

Organizations we've served

Some of Our Recent Clients

We support professional development and institutional capacity building for organizations across a wide range of sectors. Explore a selection of organizations featured in our client portfolio.

SNV logoSNV
National Communications Authority logoNational Communications Authority
Masinde Muliro University of Science and Technology logoMasinde Muliro University of Science and Technology
Kenya Medical Research Institute logoKenya Medical Research Institute
Save Lamu logoSave Lamu
UNICEF logoUNICEF
Fairtrade Africa logoFairtrade Africa
World Agroforestry (ICRAF) logoWorld Agroforestry (ICRAF)
CPI logoCPI
Food and Agriculture Organization (FAO) logoFood and Agriculture Organization (FAO)
University of Southampton logoUniversity of Southampton
Ngali Holdings logoNgali Holdings
STOPAIDS logoSTOPAIDS
International Fertilizer Development Center (IFDC) logoInternational Fertilizer Development Center (IFDC)
Wide Communications logoWide Communications

Learn. Apply. Grow.

Build skills that make a difference at work

Upskill Development Institute offers practical professional training, customized group programmes and flexible learning options to help individuals and organizations strengthen performance.

Chat with us on WhatsApp