🌍 DAC2026 Summary & Wiki/AI: Climate & Health

Resources - Ressources
1

Climate & Health at DAC2026: Country Configurations, Partnerships, and Scaling

:warning: Note: This summary was generated and reviewed by the dhis2 docs Ask AI tool and may contain errors. As this is a Wiki post, we encourage you to edit and improve this content with your own expertise, or reply with your questions for discussion!

For technical implementation guidance on CHAP modeling,
the Climate App, and the Open Climate Service, see the
DHIS2 Climate & Health Academy playlist. [You can also check out: DHIS2 Climate & Health Academy 2026 Wiki/AI: Technical Reference and Implementation Guide]
This post covers the programme and partnership dimensions —
what countries are doing, what is working, and what the
community still needs to solve.

Technical Scope and Core Toolkit

The DHIS2 Climate & Health initiative has expanded from 10 pilot countries to 18 implementing nations. The technical framework consists of three primary software components designed to integrate meteorological data into national Health Information Systems (HIS):

  • The Climate App: Mapped within the GIS infrastructure to aggregate and import environmental variables (such as precipitation and temperature) directly into DHIS2 organization units.
  • CHAP (Climate Health Analytics Platform): A containerized modeling application running predictive disease-forecasting algorithms (such as Bayesian modeling and machine learning) locally on country-managed servers.
  • Open Climate Service (OCS): A platform built on the OpenEO standard, released in preview at DAC2026, allowing ministries of health to host and process satellite and climate data on-premise.

Country Implementations and Use Cases

Dengue Forecasting in Laos

Laos has operationalized dengue forecasting within its routine health information system [Early Warning for Climate Sensitive Diseases]. The platform executes on a weekly schedule:

  1. Daily: Automated ingestion of climate data.
  2. Mondays: Submission and aggregation of routine health surveillance data.
  3. Tuesdays: Generation of disease forecasts.
  4. Tuesday Evenings: Transmission of alert notifications to provincial health offices [Early Warning for Climate Sensitive Diseases].

The forecasts populate the existing Emergency Operations Centre (EOC) dashboard. At the time of DAC2026, the data-to-forecast pipeline required manual trigger steps, with automation work ongoing in partnership with the University of Oslo [Early Warning for Climate Sensitive Diseases].

Malaria Risk Stratification and Campaign Planning in Togo

Togo’s Ministry of Health configured a predictive dashboard utilizing five years of historical DHIS2 malaria data alongside rainfall records [Climate Health Panel: Enabling & Sharing Local Innovation].

  • Methodology: The system calculates district-level outbreak thresholds.
  • Operational Outcome: The resulting risk maps identified specific districts requiring an extension of the Seasonal Malaria Chemoprevention (SMC) campaign. The Ministry presented this data to the Global Fund to secure funding for a fourth SMC distribution cycle in high-risk districts [Climate Health Panel: Enabling & Sharing Local Innovation].

High-Resolution Covariate Modeling in Rwanda

To address the limitations of coarse global climate grids, the implementation in Rwanda incorporates high-resolution satellite imagery [Climate Data Integration Deep-dive].

  • Local Covariates: The model maps marshlands and rice fields at 30-meter resolution to isolate local vector breeding sites in valley bottoms.
  • Confounding Controls: The modeling pipeline controls for non-climatic interventions, such as the protective coverage of Indoor Residual Spraying (IRS), to prevent the misinterpretation of climate signals [Climate Data Integration Deep-dive].

Nutrition and Food Security Modeling in Uganda

HISP Uganda is piloting predictive models for Severe Acute Malnutrition (SAM) [Climate Data Integration Deep-dive]. The system correlates routine clinical nutrition data with food security proxies, including:

  • The Standardized Precipitation Index (SPI) to track agricultural drought.
  • Gross Primary Productivity (GPP) measurements to estimate local crop yields and vegetation health [Climate Data Integration Deep-dive].

Automated Pipelines in South Sudan

In South Sudan, HISP Tanzania deployed CAPS (Climate Analytics Pipeline Scheduler) [Climate Data Integration Deep-dive].

  • Functionality: CAPS automates the download of climate data, the import into DHIS2, and the execution of the CHAP modeling script.
  • Output: Generated alerts and risk projections are pushed to a simplified five-tab dashboard designed for non-technical program managers [Climate Data Integration Deep-dive].

Air Quality Mapping in Sri Lanka

The implementation in Sri Lanka integrates particulate matter (PM2.5) data at a one-kilometer resolution, combining satellite observations with local ground monitoring stations to analyze correlations with respiratory admissions [Climate Data Integration Deep-dive].

Partnerships, Financing, and Global Standards

The Challenge of Institutionalisation in Mozambique

Mozambique has deployed CHAP nationally, established a data-sharing MOU with the national meteorological institute, and automated malaria alerts to district offices [Climate Health Panel: Taking Innovation to Scale]. However, the Ministry of Health highlighted ongoing dependencies:

“CHAP is up and running — alerts are being received. But institutionalisation is not implementation. We have extreme dependence on partners for the maintenance of the platform. We need to integrate CHAP into the national cycle of planning — so that the government talks about CHAP, not just the partners.” — Dr. Baltazar Kadrinho, Mozambique Ministry of Health [Climate Health Panel: Taking Innovation to Scale]

Global Fund Catalytic Financing

The Global Fund’s Climate and Health Catalytic Fund supports approximately 19 countries, with 7 of those implemented in partnership with the University of Oslo and the HISP network [Climate Health Panel: Taking Innovation to Scale]. As countries transition into the GC8 grant cycle, funding must compete within existing national budgets alongside commodities like diagnostics and therapeutics [Climate Health Panel: Taking Innovation to Scale].

WHO Collaborative Alignment

The World Health Organization (WHO) and the University of Oslo are working to align climate-informed surveillance with international health security standards [Climate Health Panel: Taking Innovation to Scale]. The partnership is focused on integrating environmental variables directly into standard epidemiological surveillance protocols rather than establishing parallel databases [Climate Health Panel: Taking Innovation to Scale].

UN-Endorsed Statistical Standards (UK ONS)

The UK Office for National Statistics (ONS) presented the SOHI framework for measuring climate impacts on health [Climate Health Panel: Taking Innovation to Scale]. In March 2026, the UN Statistical Commission endorsed six priority SOHI indicators. Two of these indicators use national DHIS2 datasets as their primary data source (measuring malaria and diarrhea in Ghana and Rwanda) [Climate Health Panel: Taking Innovation to Scale].

Community-Level Adaptation (Save the Children)

Save the Children International is implementing Green Climate Fund (GCF) projects in Laos and Malawi [Climate Health Panel: Taking Innovation to Scale]. These projects focus on operationalizing Health National Adaptation Plans (HNAPs) at the community level. The program trains local health workers to interpret dashboard trends and translate model alerts into village-level preventative actions [Climate Health Panel: Taking Innovation to Scale].

South-South Technical Exchange

Technical configurations and governance structures are increasingly shared directly between regional nodes [Climate Health Panel: Enabling & Sharing Local Innovation]:

Core Project Updates at DAC2026

  • CHAP Models: Expansion to 34 community-contributed modeling repositories on GitHub, including R and Python-based models.
  • CAPS Scheduler: Deployment of automated data retrieval and model execution pipelines.
  • WorldPop Integration: Native mapping layer availability of 100-meter gridded demographic data to calculate population-at-risk denominators.
  • Open Climate Service: Release of an on-premise data repository preview to host climate datasets locally.

Documented Implementation Challenges

  • The Operationalization Gap: Outbreak predictions must align with inflexible logistical timelines. If a high-accuracy malaria forecast is generated, but national bed net or chemical spray distribution cycles are fixed on multi-year procurement schedules, the health system cannot act on the alert [Climate Health Panel: Taking Innovation to Scale].
  • The Risk of Forecast Failure: Issuing early-warning alerts that do not materialize can degrade community trust in local public health authorities [Climate Health Panel: Taking Innovation to Scale]. Model precision and clear communication of uncertainty are operational requirements [Climate Health Panel: Taking Innovation to Scale].
  • Environmental Data Access: Gridded global meteorological data is often too coarse for local epidemiological tracking. Securing high-resolution data requires formal data-sharing agreements with national meteorological agencies, which face administrative and institutional barriers.
  • Financial Trade-Offs: Integrating climate-health applications competes directly with primary clinical services for GC8 allocations. Implementers must demonstrate that predictive modeling reduces overall system expenditures (e.g., preventing emergency response costs) to justify the investment [Climate Health Panel: Taking Innovation to Scale].

What to Watch

The ten DAC2026 Climate & Health sessions:

:graduation_cap: For technical implementation guidance on CHAP, the Climate App, and the Open Climate Service: DHIS2 Climate & Health Academy playlist

Community Call to Action

The Climate & Health project is community-driven — and the best source of knowledge about what is working is the people doing the work in countries.

  • Share your use case — whether you are in one of the 18 current countries or exploring independently, what you are learning is valuable to the community.
  • Ask questions about getting started with the Climate App or CHAP — the thread below reaches people who have been through the process in multiple countries.
  • Connect with your regional HISP group about climate health support — HISP WCA, HISP Tanzania, HISP Uganda, HISP Rwanda, and HISP Saugiditus are all active in the project.
  • Visit dhis2.org/climate for documentation, software downloads, and contact information.
1 Like
🗓️DAC2026 Thematic Summaries & Wikis/AI
DHIS2 Climate & Health Academy 2026 Wiki/AI: Technical Reference and Implementation Guide