ResiliSense: Satellite-Driven Climate Resilience Measurement Platform

Scaling Readiness describes how complete a technology's development is and its ability to be scaled. It produces a score that measures a technology's readiness along two axes: the level of maturity of the idea itself, and the level to which the technology has been used so far.

Each axis goes from 0 to 9 where 9 is the “ready-to-scale” status. For each technology profile in the e-catalogs we have documented the scaling readiness status from evidence given by the technology providers. The e-catalogs only showcase technologies for which the scaling readiness score is at least 8 for maturity of the idea and 7 for the level of use.

The graph below represents visually the scaling readiness status for this technology, you can see the label of each level by hovering your mouse cursor on the number.

Scaling readiness score of this technology

Maturity of the idea 6 out of 9

Semi-controlled environment: testing

Level of use 5 out of 9

Common use by projects connected to technology providers

The United Nations Sustainable Development Goals that are applicable to this technology.

Goal 1: no poverty

Helps identify vulnerable farming areas and households so support and investments can be better targeted.

Goal 2: zero hunger

Strengthens food security by improving the targeting of climate-smart agriculture interventions and reducing crop losses from climate shocks.

Goal 13: climate action

Supports climate adaptation by tracking farm-level resilience over time and guiding investments toward climate-smart practices.

Goal 17: partnerships for the goals

Promotes collaboration by providing shared, open data that can be used by governments, donors, researchers, and the private sector.

Goal 10: reduced inequalities

Attuned to mapping accurately the vulnerabilities and resilience scores of marginalized populations that are expected to benefit most from targeted interventions.

Step-by-Step Implementation Guide

Step 1: Inception — Engage with IITA RCA Programme

Contact IITA's Resilience and Climate Adaptation (RCA) Programme to initiate the project. Define the geography (country, region, or project area), identify which climate resilience indicators you need (e.g., land degradation, cropping system stability), and clarify the decision-making questions the resilience evidence must answer. This scoping ensures the platform is tailored to your specific context and objectives.

Step 2: Data and Ground-Truth Collection

Identify available ground-truth datasets that will be used to train and validate the machine learning models. This includes existing household surveys, project monitoring and evaluation (M&E) records, or field data from previous studies. Where calibration is needed, plan a lightweight field-validation campaign in the target landscape to collect ground-truth labels for the supervised machine learning classifiers. The quality of ground-truth data, including any available GPS data points, directly affects model accuracy.

Step 3: Calibration and Validation

ResiliSense models are calibrated for your target agroecological zone using the ground-truth data. Supervised classifiers (Logistic Regression, SVM, Random Forest, Gradient Boosting) are trained with stratified cross-validation, hyperparameter tuning, and 20-seed robustness checks to ensure reliability. The models are validated against ground-truth data before outputs are released, ensuring decision-grade accuracy for your specific context.

Step 4: Baseline Resilience Analysis

Run a baseline resilience analysis over your project area and counterfactual zones (comparison areas without intervention). The platform fuses multi-source Earth observation data— such as Sentinel-1 SAR for cloud-penetrating imagery, Sentinel-2 indices (NDVI, NDMI, NDRE, BSI, SAM) for vegetation and soil condition, CHIRPS for precipitation, ERA5-Land for temperature and wind, and SRTM for slope—through machine learning to produce farm-level predictions with confidence intervals.

Step 5: Embed Resilience Scores in M&E Framework

Build resilience scores directly into your project's results framework so subsequent rounds of analysis directly answer your M&E questions. Define how resilience indicators will be tracked over time, which administrative units or value chains will be monitored, and how confidence intervals and uncertainty estimates will be incorporated into decision-making. Offers guidance on what changes to make to your M&E plan to ensure accurate assessments. This ensures the platform supports ongoing monitoring rather than just one-off assessments.

Step 6: Iteration — Seasonal or Annual Updates

Run seasonal or annual updates to track resilience trends over time. Use confidence intervals and uncertainty estimates when communicating results to stakeholders, acknowledging the limitations of satellite-derived predictions. The platform enables repeatable monitoring, allowing you to see whether resilience is improving or declining across project cycles.

Step 7: Reporting and Decision Support

Use ResiliSense outputs to feed adaptation finance proposals, climate-smart agriculture program baselines and endlines, regenerative agriculture targeting, and CGIAR initiative reporting. Outputs can support NDCs and NAPs reporting, donor board presentations, and internal strategic planning. The platform's open methods (documented algorithms, published validation results, openly released code) supports transparency and reproducibility for all stakeholders.

Downloads

• image.png (PNG, 51.36 KB)