{"id":32105,"date":"2026-07-28T13:17:30","date_gmt":"2026-07-28T13:17:30","guid":{"rendered":"https:\/\/dev.iita.org\/?page_id=32105"},"modified":"2026-07-28T14:28:49","modified_gmt":"2026-07-28T14:28:49","slug":"resilisense-satellite-observable-indicators-of-smallholder-resilience","status":"publish","type":"page","link":"https:\/\/iita.org\/fr\/climate-action\/resilisense-satellite-observable-indicators-of-smallholder-resilience\/","title":{"rendered":"RESILISENSE : IDENTIFICATEURS SATELLITAIRES OBSERVABLES DE LA R\u00c9SILIENCE DES PETITS EXPLOITANTS AGRICOLES"},"content":{"rendered":"
\n\t\t\t\t
\n\t\t
\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

RESILISENSE : IDENTIFICATEURS SATELLITAIRES OBSERVABLES DE LA R\u00c9SILIENCE DES PETITS EXPLOITANTS AGRICOLES<\/h1>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Resilience has risen to the forefront of IITA’s work and across the CGIAR Centres, yet it remains one of the hardest outcomes to measure. Monitoring, evaluation, learning and impact assessment (MELIA) systems rarely collect resilience data, and where they do, it is fragmented and gathered at project-specific levels, which limits cross-project learning and weakens both upward and downward accountability. ResiliSense, developed and hosted within IITA’s Resilience and Climate Adaptation (RCA) Programme in Nairobi, addresses this gap: it integrates the monitoring data that programmes already collect with advances in remote sensing and machine learning to generate resilience insights at the project, programme, and country levels. In doing so, it provides a bridge from targeted household interventions to landscape-level insight.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

THE MEASUREMENT GAP<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tResilience is increasingly recognised as a cross-cutting goal, but it is seldom written into project logical frameworks. A survey that was not designed to assess resilience offers no straightforward route to measure it after the fact, so resilience remains the concern of the few projects that named it as a target rather than the portfolio-wide outcome it should be. The pressures of a changing climate and a tighter development-funding landscape make this gap more acute: donors and farmers alike need evidence that interventions are building the capacity to withstand the next shock. Surveys remain the gold standard, but they are expensive and infrequent, often limited to a baseline and an endline. Satellites paired with machine learning are scalable but, on their own, least accurate exactly where it matters most, among the poorest and most vulnerable households. The most reliable path forward is to combine the two.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

A SURVEY-ANCHORED, SATELLITE-ASSISTED APPROACH<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tRather than adding yet another survey methodology, ResiliSense is input-agnostic and output-flexible. It works with whatever MELIA data a programme already generates, and maps each survey question onto a library of established resilience frameworks, with FAO’s SHARP+ (Self-evaluation and Holistic Assessment of climate Resilience of farmers and Pastoralists) as the primary anchor and the TANGO, MSRI, and RIMA-II frameworks also represented. Results can be reported against a programme’s preferred resilience metric, the Sustainable Development Goals, or the UNFCCC global goal on adaptation, so that a single underlying analysis can serve different reporting needs. Where a survey leaves a resilience dimension unmeasured, ResiliSense identifies whether a credible remote-sensing proxy exists to help fill it, and carries an explicit measure of confidence through to the final score. It is designed to be honest about its limits: dimensions such as governance, social capital, and financial access remain difficult to observe from space and stay survey-anchored, while environmental and land-related dimensions lend themselves well to satellite proxies.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

HOW RESILISENSE WORKS<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

ResiliSense follows five steps. It begins by importing and parsing existing MELIA survey data into a structured question database. A crosswalk engine then maps each question to the SHARP+ indicator library across its economic, social, environmental, governance, and spatial domains, assigning every match a confidence score and routing uncertain matches to expert review. A gap analysis follows, identifying which resilience dimensions the survey leaves uncovered and, where validated proxies exist, fusing in multi-source earth observation: Sentinel-1 radar and Sentinel-2 optical imagery, including the NDVI, NDMI and NDRE vegetation indices, alongside CHIRPS rainfall, ERA5-Land climate reanalysis, and SRTM terrain data, each calibrated against national reference datasets. The tool then aggregates the available indicators into a household-level resilience score, with per-indicator confidence, data sources, and flagged gaps all made transparent. Finally, ResiliSense supports learning and scaling: it advises how future surveys can be designed to close gaps, and it trains machine-learning models to extend resilience estimates across unsurveyed areas, producing maps that can track resilience over time. Extraction, ingestion, inference and visualisation are automated through the programme’s Farm Intelligence Platform, so that a resilience-agnostic dataset can be turned into a resilience-score report with coverage and confidence transparency.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n

\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

WHERE IT HAS BEEN APPLIED<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tResiliSense has been applied in Malawi, Niger and Nigeria, with further work underway in Ghana and Kenya. The first pilot was in Malawi, where predictions were tested on 351 geo-referenced farms across six districts using a resilience-agnostic survey. There, satellite and climate signals served as validated proxies for environmental resilience indicators, most notably land degradation and, more tentatively, cropping system type, with results shown to be stable across repeated testing. These early findings confirm the wider pattern: the environmental dimensions of resilience are the most readily proxied, while socio-economic dimensions continue to depend on survey data. Work in Niger and Nigeria is testing how well models transfer across agro-ecological regions, while fieldwork in Kenya and Malawi is grounding and validating the scores.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

BUILDING INCLUSION INTO THE SCORE<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tResilience is not experienced equally. Working with the Alliance of Bioversity International and CIAT, the programme is developing a gender and social-inclusion module that extends resilience scoring to better capture the resilience of women in agrifood systems. This helps ensure that, as ResiliSense scales, it surfaces rather than smooths over the vulnerabilities of those most exposed to climate shocks.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

THE ROAD AHEAD<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe goal is an open-source ResiliSense platform that converts resilience-agnostic MEL data into resilience-score reports for use across the project cycle, from identification and design, through implementation, to ex-post assessment. Near-term priorities are to complete the semi-automated crosswalk engine, to deepen the remote-sensing research in Malawi that raises the confidence of scores drawn from resilience-agnostic datasets, and to pilot the prototype with further MEL datasets in new countries. As satellite and machine-learning capabilities advance, the ambition is for resilience assessment to approach what the newest earth-observation models are beginning to achieve for wealth: scalable, high-resolution maps that track change over time and are actionable from farmers to policymakers. Resilience is the more demanding target, more multi-dimensional and more sensitive to shocks, and it will continue to require survey anchoring and to carry greater uncertainty. ResiliSense is designed to improve as those methods do.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n
\n
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

WHY IT MATTERS<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tResiliSense addresses a practical bottleneck at the centre of climate-adaptation programming: how to measure resilience credibly, comparably, and at scale, without locking projects into a single new survey. By showing which resilience dimensions can be measured remotely, it reduces survey costs. By working from data already collected, it makes resilience assessable across a whole portfolio rather than a handful of projects. By scaling household insights across regions, it helps direct adaptation investment to the farms and landscapes that need it most. And by surfacing uncertainty transparently, it guards against satellite proxies masking the vulnerabilities of the most marginalised. Resilience is a harder target than wealth, and ResiliSense does not claim to capture it perfectly. What it offers is an instrument to move resilience measurement from the concern of a few projects to a capability across CGIAR’s climate-adaptation work.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\n<\/div>\n\t\t<\/div>","protected":false},"excerpt":{"rendered":"

RESILISENSE: SATELLITE-OBSERVABLE INDICATORS OF SMALLHOLDER RESILIENCE Resilience has risen to the forefront of IITA’s work and across the CGIAR Centres, […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":1934,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"elementor_header_footer","meta":{"site-sidebar-layout":"no-sidebar","site-content-layout":"","ast-site-content-layout":"full-width-container","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"disabled","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-32105","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/pages\/32105","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/comments?post=32105"}],"version-history":[{"count":20,"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/pages\/32105\/revisions"}],"predecessor-version":[{"id":32146,"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/pages\/32105\/revisions\/32146"}],"up":[{"embeddable":true,"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/pages\/1934"}],"wp:attachment":[{"href":"https:\/\/iita.org\/fr\/wp-json\/wp\/v2\/media?parent=32105"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}