OPEN STANDARD · OCRF V1.0

Climate financial risk has no Linux. We built it.

Climate Risk Commons puts the same enterprise-grade physical climate-risk platform the world's largest banks use into your hands, free for non-commercial work. Not only standardized data, but the platform to upload open datasets, run experiments, build new models, and design new damage functions.

Request access Explore the standard
Red osier dogwood stems rising through dry golden grasses at the edge of a woodland
Photograph © Edward Burtynsky. Used with permission.
50+climate hazards modelled
241Bgeospatially aligned locations
193countries
AllIPCC emissions scenarios
15time horizons to 2100
Institutions already on board
The Fields Institute University of Toronto · Architecture University of Toronto · Mathematical Finance Tel Aviv University Durham University · Finance and Management Science The Cyprus Academy of Sciences, Letters and Arts Pacific Institute for Climate Solutions · University of Victoria Technical University of Munich · CAMBIR University of Western Ontario · All Science Faculties London School of Economics · doctoral research University of Zurich Queen's University · Smith School of Business · Institute for Sustainable Finance Central Bank of Brazil Universidade Federal do Rio Grande do Norte (UFRN) Stockholm Environment Institute · SEI Latin America Twintree.Org University of British Columbia · Sauder School of Business
Why it matters

Institutions must report numbers they cannot defend.

Bare grey trees standing in a dense field of crimson dogwood stems
Photograph © Edward Burtynsky. Used with permission.

Measuring physical climate risk has shifted from a voluntary exercise to a supervised obligation. IFRS S1 and S2, the CSRD, the EU Taxonomy, TCFD and TNFD have made climate and nature risk a required part of corporate and financial reporting, and prudential supervisors from the EBA to BaFin and FINMA now expect institutions to identify, measure, manage, and monitor physical climate-risk drivers.

The harder test is ownership, not reporting. Auditors and supervisors increasingly expect you to understand and own the data and models behind a tool, rather than accept a vendor's black box. A closed, proprietary model cannot meet that bar by design. Independent reviews of the field, including UNEP FI's Climate Risk Landscape work, keep identifying the same compounding problems: provider methodologies that differ substantially and remain largely opaque, so results cannot be benchmarked.

You cannot defend a methodology you are not permitted to see. The same asset, scored by two providers, can yield materially different risk scores. Relying on any one closed vendor produces a false sense of precision, exactly when supervisors are asking you to understand model uncertainty rather than look past it.
Four failures of the closed model
Failure 01

Numbers you can't defend

Methodology sits inside a vendor black box, closed to the very regulators, auditors, and boards now asking how the figures were produced.

Failure 02

Results that don't compare

Every vendor encodes assets, hazards, and scenarios differently, so similar portfolios diverge and supervisors cannot aggregate across the system.

Failure 03

A costly door, both ways

Evaluation takes months and six figures, and proprietary formats make exit expensive, pricing smaller players out before they even begin.

Failure 04

Science that keeps restarting

Without a shared foundation, researchers rebuild the same infrastructure rather than advancing stochastic and multi-hazard methods.

The structural cure

An open standard is the structural cure.

The closed model is The open standard is
Black-box methodology you are not permitted to inspect Inspectable methodology, so you own your models
Assets, hazards, and scenarios encoded differently by every vendor One shared schema, so results compare across teams and firms
Single-vendor point estimates that manufacture false precision A stochastic, full-distribution engine that makes uncertainty legible
Cost and expertise walls that shut out smaller institutions and emerging markets Open, no-cost access for them and the researchers studying them
Why now: CMIP7. The climate model intercomparison data that virtually every physical-risk system is built on has just been upgraded. CMIP7 replaces CMIP6, whose data stopped at 2014. Climate Risk Commons is among the first production systems to ship on CMIP7, so you start on the current standard rather than last decade's.
What it is

An open standard, anchored by two pieces.

Climate Risk Commons is an open technical standard for physical climate-risk analysis. The Open Climate Risk Framework (OCRF) defines the shared contracts, asset schema, reference pipeline, APIs, SDKs, and tooling that let hazards, assets, and impact functions interoperate. The reference pipeline, Ecofusion, runs the entire specification end-to-end on a laptop or a cluster using open reference data. Every component is licensed under Apache 2.0, with terms you can hand to your legal office. Through CDTexpress, you reach the full Climate Digital Twin behind it.

How it works

Three open contracts, one comparable result

INPUT CONTRACT 01 Climate hazard data INPUT CONTRACT 02 Physical assets INPUT CONTRACT 03 Impact functions OCRF REFERENCE PIPELINE Ecofusion runs on a laptop or a cluster OUTPUT Comparable, auditable risk metrics

Anyone can run the standard end to end on open reference data. Swap in production-grade inputs when a decision depends on it.

This is Climate 2.0: stochastic, multi-hazard, coherent across hazards and countries, and built for the extreme tail rather than the average case.

Eight components of membership
OCRF spec and asset schema.How assets and exposure are encoded, so analyses share a common vocabulary.
Ecofusion reference pipeline.An end-to-end DataFusion engine that runs on a laptop or a cluster.
Impact-function library.Validated functions for common asset-hazard pairs.
SDK and API clients.Permissive Python and R clients as the on-ramp to the standard.
Sample notebooks.Portfolio analysis, sensitivity testing, and regulatory submissions.
Conformance test suite.What an implementation must pass to claim conformance, so outputs remain comparable.
Documentation.Workflows, uncertainty explainers, and regulatory mapping.
Multi-hazard stress testing.An asset's exposure to several correlated hazards at once.
What you can build
Use case

See your real exposure

Load your asset or loan-book addresses; the twin geolocates them and returns flood, heat, and wildfire exposure for the assets you actually hold, not a headline figure.

Use case

Stand up a CMIP7 stress test

Run a stochastic, multi-pathway test across thousands of scenarios, in a structure a supervisor can read and an auditor can follow.

Use case

Bring your own data

Load your own datasets, models, and damage functions and still produce a result that compares cleanly with everyone else's.

Use case

Screen a city or development portfolio

Development banks, ministries, and city networks screen assets for priority physical risks and share the method with anyone who needs to use it.

"If this data only serves the institutions that can already afford it, we have not solved the climate-risk problem. We have just priced some people out of knowing it." DR. RON DEMBO · CEO AND FOUNDER, RISKTHINKING.AI
The model

The architecture is open. The signal remains commercial.

You can build a serious, end-to-end risk system on the open release. The commercial layer is additive, not a gate: a 7M+ asset database with twelve years of curation, 2,000+ pathway scenarios downscaled to 10km and recalibrated annually, a patented multi-hazard correlation engine, and production infrastructure including enterprise integrations, on-premises deployment, SOC-2, and VELO.

Built to pass your security review. There is no opaque third-party binary to fear, because your information-security team can read exactly what runs before it touches your environment. Transparency is the default, precisely what CISOs and regulators have spent years asking closed vendors to provide.
A cluster of lichen-gilded tree trunks rising from tangled deadfall and red dogwood undergrowth
Photograph © Edward Burtynsky. Used with permission.
What you do not get
Membership is notMembership is
RiskThinking.AI's proprietary high-fidelity data, which is reserved for paying customers; the commercial revenue it earns is what sustains the open platformThe full machinery for calculating physical climate risk, with an environment for open datasets you can download directly to power it
A demonstration or teaching editionThe same engine that powers the world's largest financial institutions, applied to open reference data or to whatever you bring yourself
A dataset play; no single dataset, however good, delivers replicationComparability: two teams on the same schema, conformance suite, and engine can replicate one another's work and compare findings directly; only a standard does that
The Commons is a not-for-profit, founded and funded by RiskThinking.AI, using the same standards as the commercial platform. That shared foundation keeps open research and commercial practice interoperable rather than letting them drift apart.
A movement, not a release

Governance built to outlast us.

Thriving open-source ecosystems are communities, not codebases. Climate Risk Commons is a not-for-profit, founded and funded by RiskThinking.AI: the first maintainer of the standard, not its owner. As adoption grows, a neutral foundation follows, so what you build on remains in place in five years. You retain full freedom to bring your own data, models, and damage functions, while holding your work to a standard the whole community shares.

Commercial vendors cluster around large, listed, global portfolios. The underserved long tail, agriculture and supply chains, real estate and unlisted assets, single river basins, specific hazards and geographies, is exactly where researchers work. Building that science on the open standard adds the coverage the market has left out and folds it into a shared, comparable foundation rather than another silo. Researchers are the people who pressure-test a standard, validate it, and extend it into the underserved corners, giving it a legitimacy no single vendor's marketing can buy.

Expect rough edges. Specs, APIs, and data schemas may change during the preview, sometimes with little notice. Availability is a plan, not a promise; the exact order and timing of drops may shift.
1

Groundwork

Resolve the patent-rights path, select the licence, prepare the repository, finalize spec v1, and onboard pilot users.

2

Ecosystem ignition

Public release of Ecofusion, OCRF, and the schema; the open tier goes live; design partners, including universities and innovation labs, join.

3

Standard expansion

Community contributions, academic partners, deeper regulatory engagement, and the transition to a neutral foundation.

4

Scale and sustain

Premium data, support, and advanced capabilities sustain the open core, keeping the standard continually improving for everyone building on it.

Partner FAQ

Questions we hear from partners.

01What is the Climate Risk Commons?▸

An open initiative to give the climate physical-risk field a shared technical foundation. Today, climate-risk analysis is fragmented across data vendors, asset taxonomies, hazard models, impact functions, and reporting workflows: outputs are hard to compare, assumptions are hard to audit, and providers are hard to integrate. The Commons addresses this by publishing an open standard, a reference pipeline, open data, and tooling that anyone can inspect, run, and build on.

It is a not-for-profit, founded and funded by RiskThinking.AI, with governance moving to a neutral, non-profit foundation so the standard outlives any single company's commercial decisions.

02What's the difference between the Commons and OCRF?▸

The Climate Risk Commons is the initiative and the ecosystem: the community of partners, the open assets, and the governance that stewards them. The Open Climate Risk Framework (OCRF) is the core technical specification at its heart. It defines common contracts for the three inputs to physical-risk analysis, climate hazard data, physical assets, and impact functions, so data and models from different providers can interoperate and produce comparable, auditable outputs.

A simple way to say it: the Commons is the community and the home; OCRF is the standard the community builds around.

03What's included in the Commons?▸

The open assets, free to inspect, run, and build on:

  • The OCRF specification: input contracts for climate hazards, physical assets, and impact functions, plus the output model.
  • Ecofusion: an open reference pipeline that implements OCRF end to end.
  • Open reference data: run the full pipeline and validate results without a commercial relationship.
  • A starter library of open impact (damage) functions.
  • Output APIs and SDKs, plus supporting tooling and documentation.
  • Open governance: spec versioning, a published contribution process, and a public roadmap, stewarded through the foundation.

Anyone can run OCRF end to end on the open reference data. Production-grade results at scale typically draw on commercial data and functions, from RiskThinking.AI or from other conforming providers.

04Why use OCRF?▸

If you produce, consume, or review climate physical-risk analysis, OCRF gives you four things the current fragmented landscape does not.

  • Comparability. When hazards, assets, and impact functions conform to the same contracts, results from different vendors, models, and internal teams can be placed side by side and meaningfully compared.
  • Auditability. Every assumption is inspectable: which hazard data, which asset representation, which impact functions. For teams answering to boards, regulators, and auditors, tracing an output through an open pipeline beats black-box scores.
  • No lock-in. Open contracts let you swap providers, mix data sources, or bring your own functions without rebuilding your workflow. Your methodology attaches to the standard, not to any single vendor.
  • Lower cost to start. The spec, Ecofusion, reference data, and starter functions are free to run. Stand up a working end-to-end analysis, validate against your own portfolio, then decide which commercial inputs to bring in.

The pitch in one line: OCRF turns climate physical-risk analysis from incompatible vendor black boxes into an open architecture you can inspect, compare, and own.

05What should the ecosystem build?▸

The standard is designed so value grows with participation. We're actively looking for partners to build:

  • Conforming data products: hazard, asset, and exposure data published against the OCRF input contracts, including from providers who compete with RiskThinking.AI.
  • Impact functions: sector-, peril-, and region-specific damage functions contributed to the open library or offered commercially against the spec.
  • Integrations and connectors: bridges into risk platforms, portfolio systems, GIS tools, reporting and disclosure workflows, and cloud data platforms.
  • Implementations and tooling: alternative pipelines, validation and conformance tools, benchmarking suites, and developer utilities.
  • Research and methods: work that tests, extends, and improves the methods encoded in the spec, published so others can reproduce it.
  • Applications: decision tools for underwriting, lending, asset management, supply chain, infrastructure planning, and regulatory reporting that consume OCRF outputs.
06What does building in the ecosystem look like?▸
  1. Orient. Read the OCRF spec and the three input contracts. Clone Ecofusion and run it end to end on the reference data: a day or two, and you have a working mental model of the whole architecture.
  2. Pick your surface. Decide where you sit in the stack: data providers publish against an input contract, modelers contribute or sell impact functions, tool builders consume outputs through the APIs, implementers build specialized pipelines.
  3. Build against the contracts. Use the open contracts as your interface. The reference pipeline and open data are your test harness: if your component works with Ecofusion on reference data, it works with the ecosystem.
  4. Validate conformance. Run the validation tooling to confirm your component conforms. Conformance makes your product plug-compatible with everything else in the ecosystem, and it's the claim you put in front of customers.
  5. Contribute back where it makes sense. Fixes, tooling, docs, and open impact functions flow through the published contribution process, building reputation and giving you a voice in where the spec goes next.
  6. Ship and distribute. Offer your conforming product commercially or openly. The standard is your distribution: every OCRF adopter is a prospective user of every conforming component.

Throughout, the community channel and stewardship team are available for technical questions, and spec gaps you hit feed directly into the roadmap.

07How do academics, researchers, and developers benefit?▸

For researchers and academics:

  • Reproducibility by default: methods published against OCRF re-run by anyone, on open data, in an open pipeline.
  • A path from paper to practice: contributed methods get adopted by practitioners, giving academic work real-world uptake.
  • Shared infrastructure: spec, pipeline, and data remove months of setup, so effort goes into the science.
  • Influence on the standard: early-access researchers shape how v1 encodes hazards, exposure, and vulnerability.

For developers and implementers:

  • A stable foundation: open contracts and versioned specs mean a vendor API change won't strand your work.
  • Distribution through the standard: every OCRF adopter is a prospective user of conforming tools and apps.
  • Zero-friction start: pipeline, sample data, SDKs, and docs are free, so evaluation costs an afternoon, not a procurement cycle.
  • Community and visibility: recognition in a growing ecosystem, a direct line to the team, and a voice in the roadmap.
08What does RiskThinking.AI keep as proprietary IP?▸

RiskThinking.AI contributes the standard, the reference pipeline, and open reference data to the Commons, and retains three high-value inputs plus enterprise offerings, licensed commercially:

  • Bias-corrected and downscaled climate hazard data, including derivative hazards.
  • Physical-asset discovery data.
  • Proprietary impact functions beyond the open starter set.
  • An enterprise edition of the pipeline, running a step ahead of the open release, with priority fixes and newer capabilities.
  • Onboarding, technical support with SLAs, and premium VELO capabilities.

What differs is the data flowing through it, not the machinery doing the work. The commercial gateway is a data purchase: buying the proprietary hazard and asset data unlocks the enterprise pipeline, proprietary functions, and support relationship. These offerings sit outside the foundation and compete on merit alongside anyone else who builds against the spec.

09Why is RiskThinking.AI open-sourcing this?▸

Because a standard is worth more than an island. A shared, inspectable architecture grows the whole market for climate physical-risk analysis, and RiskThinking.AI chooses to compete on data quality and analytics rather than on lock-in. Open adoption also lets prospects prove value with zero friction before any commercial conversation, which suits a trust-driven market with slow procurement.

10Who governs the Commons? Can I trust its neutrality?▸

The open assets, the spec, Ecofusion, open reference data, the open impact-function library, and governance itself, are stewarded through a neutral, non-profit foundation. Governance is lightweight but real: clear spec versioning, a published contribution process, reference implementations, and a public roadmap. RiskThinking.AI is the founding steward and holds no privileged position in the spec; competing providers are explicitly welcome to conform and contribute.

11Who should join, and what do partners get?▸

We're engaging five kinds of partners:

  • Founding institutions: a seat shaping governance and the v1 standard.
  • Data providers: distribution through a common contract.
  • Developers and implementers: a stable foundation to build products on.
  • Researchers: reproducible methods and real-world adoption.
  • Adopters: financial institutions, corporates, and public agencies wanting comparable, auditable risk outputs.

Early partners get direct influence on the v1 specification, early access to the reference pipeline and sample data, visibility as founding participants, and a direct channel to the stewardship team.

12How do I get involved?▸

Join the early access preview. Send your GitHub handle and contact email and confirm the early access terms. We'll onboard you to the repositories, the community channel, and the spec. From there, run the reference pipeline on the sample data and tell us what you find: early feedback directly shapes the public v1 release.

Contact: academic@riskthinking.ai · Bring: GitHub handle, contact email, agreement to early access terms.

13What data can members use?▸

The open reference datasets provided within the Commons environment, any open dataset you upload, and any data, models, or damage functions of your own. Results remain conformant with the standard regardless of whose data powers them.

14Are results produced on open data scientifically credible?▸

Yes. The engine, schema, and conformance suite are identical to the commercial stack. Precision depends on the resolution of the data used, and you should report that, exactly as good science already requires.

15What if I later need high-fidelity data?▸

That is a commercial conversation, and we are happy to have it. Write to academic@riskthinking.ai and we will route it to the right team.

16Can membership be used for commercial work?▸

No. Membership is free for non-commercial research only. Commercial use of the platform or of RiskThinking.AI's data requires a commercial licence.

How to join

Membership is free for non-commercial research.

Individual researchers

Apply directly, show proof of your institution or university, and provide a sentence or two on why you intend to use it.

academic@riskthinking.ai

Faculties and universities

Enrol all your bona fide students, researchers, and faculty at once. A short letter of intent from the institution is enough to formalize it.

Enrol your institution
The invitation. Closed competitors are racing to build a wall. We are building a community. It is ready for you to read, run, and build on today. Join the community that evolves this project. Contribute, and gain from the contributions of others. Open-source community: opensource@riskthinking.ai