How climate data becomes actionable knowledge

I recently had the opportunity to discuss with Marcia Toledo Sotillo, director of #adaptation and #resilience at the UN High-Level Climate Champions, about our experience in democratizing climate risk assessment. The Race to Resilience campaign, led by the High-Level Climate Champions, has set an ambitious goal: enhance the resilience of 4 billion people by 2030 by mobilizing action from the so-called "non-state actors" - local communities, NGOs, companies... Assessing and understanding climate risks is the first step of this transformation. Thanks to five decades of intensive research in climate science and earth system modeling, information about future climate and its impacts is available at unprecedented precision and depth. However, accessing and interpreting this data can be almost impossible for non-state actors, as it requires very specific technical and scientific expertise. Since 2019, Callendar has been bridging this gap by developing tools that transform scientific data into ready-to-use, localized information. Our solutions cater to a wide range of stakeholders, from billion-dollar industrial projects to individuals. In 2024, we delivered climate risk assessments - such as submersion, heatwave or wildfire - to over 230,000 people in France. While a far cry of the 4 billion target, it represents a scalable model that can be replicated globally. I strongly believe that delivering high-quality, actionable climate impact assessments to half of humanity within 5 years is technically feasible. However, there is no one-size-fits-all solution for adaptation. Climate impacts vary greatly from one place to another and solutions must be tailored to local contexts. To be truly effective, our approach requires both global endorsement and local collaboration, ensuring that communities have access to tools and support tailored to their specific needs.

When I first started meeting bureaucrats, policymakers, and politicians while working on air pollution and climate change, I assumed scientific research would naturally lead to better policies. But over time, I kept getting the same response—expressed in different ways. Here, I’m sharing some early experiences that shaped my understanding of this disconnect. 🔹 One of my first experiences was when a very senior officer invited us to discuss solutions. As scientists, we proposed a research-driven approach that would take two to three years. His response? "We have funding that must be spent within a year. We expected practical solutions from you. We can’t wait three years—I might even be transferred before then." 🔹 Another realization came when we proposed analyzing pollution sources. A senior officer responded, "We already know the sources—traffic, industry, construction, waste burning, road dust, cooking fuel, etc. Will your study show anything drastically different?" When we explained that our study would refine insights and reduce uncertainties, his response was: "We don’t care about these nuances right now. That detail matters later, once mitigation efforts are underway. Right now, we need feasible solutions that fit economic, demographic, and practical constraints." Another officer later remarked: "Scientists aren’t here to provide solutions. Their focus is securing funding, publishing papers, and showcasing work to funders." He even cited global reports that had never been downloaded. At that moment, I felt disappointed. But I also realized they weren’t entirely wrong—perhaps even more right than I was. Policymakers work within short funding cycles, shifting priorities, and limited tenures—typically three years for an officer, five for a politician. Their constraints are real, and their approach reflects these realities. 💡 This disconnect between science and policy is a major barrier in sustainability. Scientists seek accuracy, while policymakers need actionable, timely solutions. So, how do we bridge this gap? ✔ Policy-Research Intermediaries – Teams that translate scientific findings into actionable policies. ✔ Adaptive Research Timelines – Delivering short-term, high-impact solutions alongside long-term studies. ✔ Collaborative Working Groups – Scientists, policymakers, and stakeholders aligning research with real-world needs. ✔ Flexible Funding Models – Ensuring funding supports both immediate action and long-term research. 🚀 If we don’t bridge this gap, science remains detached from policy, and policy stays reactive instead of proactive. #AirPollution #ClimateAction #SciencePolicy #Sustainability #Collaboration #ResearchToAction

Every year, natural disasters hit harder and closer to home. But when city leaders ask, "How will rising heat or wildfire smoke impact my home in 5 years?"—our answers are often vague. Traditional climate models give sweeping predictions, but they fall short at the local level. It's like trying to navigate rush hour using a globe instead of a street map. That’s where generative AI comes in. This year, our team at Google Research built a new genAI method to project climate impacts—taking predictions from the size of a small state to the size of a small city. Our approach provides: - Unprecedented detail – in regional environmental risk assessments at a small fraction of the cost of existing techniques - Higher accuracy – reduced fine-scale errors by over 40% for critical weather variables and reduces error in extreme heat and precipitation projections by over 20% and 10% respectively - Better estimates of complex risks – Demonstrates remarkable skill in capturing complex environmental risks due to regional phenomena, such as wildfire risk from Santa Ana winds, which statistical methods often miss Dynamical-generative downscaling process works in two steps: 1) Physics-based first pass: First, a regional climate model downscales global Earth system data to an intermediate resolution (e.g., 50 km) – much cheaper computationally than going straight to very high resolution. 2) AI adds the fine details: Our AI-based Regional Residual Diffusion-based Downscaling model (“R2D2”) adds realistic, fine-scale details to bring it up to the target high resolution (typically less than 10 km), based on its training on high-resolution weather data. Why does this matter? Governments and utilities need these hyperlocal forecasts to prepare emergency response, invest in infrastructure, and protect vulnerable neighborhoods. And this is just one way AI is turbocharging climate resilience. Our teams at Google are already using AI to forecast floods, detect wildfires in real time, and help the UN respond faster after disasters. The next chapter of climate action means giving every city the tools to see—and shape—their own future. Congratulations Ignacio Lopez Gomez, Tyler Russell MBA, PMP, and teams on this important work! Discover the full details of this breakthrough: https://lnkd.in/g5u_WctW  PNAS Paper: https://lnkd.in/gr7Acz25

The regulation will come whether you’re ready or not. CSRD. California climate rules. SBTi targets. Supply chain disclosures. But compliance is the floor — not the ceiling. The real upside comes when you use the same data you’re collecting for compliance to run your business better. That means: • Tying energy usage to cost savings initiatives • Using emissions data to drive procurement decisions • Creating transparency for customers that unlocks larger deals • Building internal investment cases based on risk-adjusted ROI, not reporting pressure Sustainability data, if done right, becomes an operational dataset. And operational datasets are how you find margin. The smartest CFOs? They’re not just checking the box. They’re turning it into their edge.

Data points sourced from national weather services and international disaster registers, are the raw material from which to sculpt an understanding of climate risks. Climate analytics companies would not exist if OpenData didn’t exist. These raw data sources are the ingredients forming the recipe - the product of usable knowledge. But the necessary condition for cooking the recipe is having the capacity to work scientifically with this raw data. We're confident enough of that, we don't mind sharing our sources. Attached is what we currently use to collect raw climate data. 🌐 Time series of meteorological observations, collected sub-hourly across the world - an immense volume of data. 🌐 Global climate models, which tend to be updated perhaps every 8 years, after much work and analysis. 🌐 Satellite mapping, which has undergone generational advances. Each new probe seeks to convey a new state-of-the-art in image resolution, wavelength detection, and measurement/pass frequency. It’s a good idea to pursue end-use climate risk insights on a semi-regular basis, to accommodate for the evolution of underlying data collection and modeling that ultimately feed into the analytics. Companies seeking compliance with risk disclosure requirements may wish to get a fresh risk assessment each time they plan to rely on it for internal strategy, or embed it in an annual sustainability or financial report. It’s the right combination of scientific data workflow and high-quality resources that enables advanced climate risk management. The beauty of innovation lies in transforming something complex and unwieldy into a clear, meaningful, and useful YES-NO RISK answer. ======= Weather Trade Net provides physical climate and extreme weather risk analytics using high-quality resources and scientific post-processing. - corporate sustainability disclosures - predictive modeling for risk management

In a The World Bank blog, German Caruso and Inés de Marcos introduce the Climate Effects Navigator Toolkit (CLIENT), a new interactive platform that combines climate and human capital data to analyze the long-term effects of disasters on health, education, and livelihoods. Key features: 📊 Tracks six hazard types (e.g. droughts, floods, heatwaves, hurricanes) over nearly five decades. Users can tweak thresholds, timeframes, and measure by land or population to analyze exposure, frequency, and severity at subnational levels. 🧍Uses census microdata to show who’s most affected. Users can explore how disasters impact school attendance, employment, electricity access, and more, before and after events, to highlight vulnerable groups like children or underserved households. ⚙ Overlays World Bank project data with climate-affected areas, helping identify where current initiatives are helping, and where gaps remain, enabling better targeting of climate-smart investments. 🔍 Integrates almost five decades of climate data across 38,000+ subnational regions and harmonizes climate records, census data, population stats, and administrative boundaries into a flexible toolkit with over 300 customizable parameters. 🗒️ Read the blog: https://lnkd.in/gGsURKjD 🖥️ Try the toolkit: https://lnkd.in/gUJB3Kkc 💻 Check out the Climate Change Knowledge Portal: https://lnkd.in/gw2eThqb

🚀 Exciting news to share! The 2024 Department of the Interior Remote Sensing Activities report is out, and it highlights ClimateEngine.org's work with Bureau of Land Management in the article “Improving Accessibility of Data to Support Adaptive Management and Decision-Making.” This write-up spotlights our partnership between Bureau of Land Management, Climate Engine / Desert Research Institute, and collaborators at NOAA National Integrated Drought Information System (NIDIS), US Department of Agriculture (USDA) Agricultural Research Service (ARS), and University of California, Merced, showcasing how we’re translating satellite and climate data into site-specific, one-page, PNG/PDF reports that BLM resource managers, monitoring staff, range specialists, wildlife biologists, and planners can apply directly in decision documents. A huge thank-you to the BLM staff who have guided user testing, shared feedback from the field, and keep pushing us to build tools that actually move the needle on drought response, land health assessment, and adaptive management. This project has really helped us focus on translating Earth observations archives into actionable documents and is shaping how we think about Climate Engine going forward! 🔗 Read the article here: https://lnkd.in/gC6QzBtC 🔗 Read the full report here: https://lnkd.in/gcY3H_dZ Here’s to more data-driven decisions, healthier landscapes, and continued collaboration in 2025! #RemoteSensing #ClimateEngine #PublicLands #AdaptiveManagement #Drought #BLM #DOI #EarthObservations #Geospatial Kristen O'Shea Tim Assal, Ph.D. Justin Huntington Emily Kachergis Sarah McCord Brady Allred