Leveraging Open Data

𝐎𝐩𝐞𝐧 𝐃𝐚𝐭𝐚 𝐂𝐥𝐢𝐦𝐚𝐭𝐞 𝐑𝐢𝐬𝐤 𝐀𝐬𝐬𝐞𝐬𝐬𝐦𝐞𝐧𝐭 𝐓𝐨𝐨𝐥𝐬 – Deep Dive Last week, I shared a post on open data tools for climate risk assessment and their role in climate adaptation. Since it sparked some interest, here’s a follow-up: a closer look at some of the best tools out there. 🦍 UN Biodiversity Lab 🦍 Hosts an amazing 269 datasets on biodiversity, from habitat intactness and ecosystem resilience to socio-economic indicators. – Great extra: national biodiversity statistics for 193 countries. – One highlight (which is integrated into many tools): The „GLC_FCS30“ land-cover map with an incredible 30x30m resolution. ⛈️ WESR Climate ⛈️ I like the tool by the UN Environment Programme because it offers a great framework for analyzing climate change variables: “Drivers” and “Pressures” (what drives climate change), “States” (how it alters Earth's systems), “Impacts” (resulting societal risks) and even “Responses” (what do we do to mitigate them). 🏭 Global Infrastructure Risk Model and Resilience Index (GIRI) 🏭 A collection by the Coalition for Disaster Resilient Infrastructure of an incredible 113 up-to-date and granular datasets on climate risks to buildings and infrastructures. – Great extra: Country-level statistics on average annual losses by climate hazards and infrastructure category. 🏚️ GIS-ImmoRisk 🏚️ Not flashy, but the only tool I know that lets you export building-specific climate risk PDF reports. It even factors in asset details (size, roof shape, windows, …) to assess likely damages by climate hazards. (Covers only Germany.) ❗ Where can you find these and other open climate and nature risk tools? – Click "resources" on the UN Environment Programme's World Environment Situation Room’s website. – Have a look at the MapX tool examples by UNEP/GRID-Geneva. – See the partially free KanataQ tool list. (Thank you, Nawar!) – Check out the tools and resources list of the NOAA. (Thank you, Douglas!) ❗ I’d appreciate hearing your opinion on the tools in this post, which tools you'd recommend, and where to find more. Link to last week's post: https://lnkd.in/dv_GKW83

𝗔𝗜 𝗳𝗼𝗿 𝗚𝗢𝗢𝗗: 𝗡𝗔𝗦𝗔 𝗮𝗻𝗱 𝗜𝗕𝗠 𝗹𝗮𝘂𝗻𝗰𝗵 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗔𝗜 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹 𝗳𝗼𝗿 𝗺𝗼𝗿𝗲 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝘄𝗲𝗮𝘁𝗵𝗲𝗿 𝗮𝗻𝗱 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗳𝗼𝗿𝗲𝗰𝗮𝘀𝘁𝗶𝗻𝗴! 🌍 (𝗧𝗵𝗶𝘀 𝗶𝘀 𝘄𝗵𝗮𝘁 𝘀𝗵𝗼𝘂𝗹𝗱 𝗴𝗲𝘁 𝗺𝗼𝗿𝗲 𝘀𝗽𝗼𝘁𝗹𝗶𝗴𝗵𝘁 𝗽𝗹𝗲𝗮𝘀𝗲 𝗮𝗻𝗱 𝗡𝗢𝗧 𝘁𝗵𝗲 𝗻𝗲𝘅𝘁 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 𝗪𝗿𝗮𝗽𝗽𝗲𝗿!) In collaboration with NASA, IBM just launched Prithvi WxC an open-source, general-purpose AI model for weather and climate-related applications. And the truly remarkable part is that this model can run on a desktop computer. 𝗛𝗲𝗿𝗲'𝘀 𝘄𝗵𝗮𝘁 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗸𝗻𝗼𝘄: ⬇️ → The Prithvi WxC model (2.3-billion parameter) can create six-hour-ahead forecasts as a “zero-shot” skill – meaning it requires no tuning and runs on readily available data. → This AI model is designed to be customized for a variety of weather applications, from predicting local rainfall to tracking hurricanes or improving global climate simulations. → The model was trained using 40 years of NASA’s MERRA-2 data and can now be quickly tuned for specific use cases. And unlike traditional climate models that require massive supercomputers, this one operates on a desktop. Uniqueness lies in the ability to generalize from a small, high-quality sample of weather data to entire global forecasts. → This AI-powered model outperforms traditional numerical weather prediction methods in both accuracy and speed, producing global forecasts up to 10 days in advance within minutes instead of hours. → This model has immense potential for various applications, from downscaling high-resolution climate data to improving hurricane forecasts and capturing gravity waves. It could also help estimate the extent of past floods, forecast hurricanes, and infer the intensity of past wildfires from burn scars. It will be exciting to see what downstream apps, use cases, and potential applications emerge. What’s clear is that this AI foundation model joins a growing family of open-source tools designed to make NASA’s vast collection of satellite, geospatial, and Earth observational data faster and easier to analyze. With decades of observations, NASA holds a wealth of data, but its accessibility has been limited — until recently. This model is a big step toward democratizing data and making it more accessible to all. 𝗔𝗻𝗱 𝘁𝗵𝘀 𝗶𝘀 𝘆𝗲𝘁 𝗮𝗻𝗼𝘁𝗵𝗲𝗿 𝗽𝗿𝗼𝗼𝗳 𝘁𝗵𝗮𝘁 𝘁𝗵𝗲 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝗔𝗜 𝗶𝘀 𝗼𝗽𝗲𝗻, 𝗱𝗲𝗰𝗲𝗻𝘁𝗿𝗮𝗹𝗶𝘇𝗲𝗱, 𝗮𝗻𝗱 𝗿𝘂𝗻𝗻𝗶𝗻𝗴 𝗮𝘁 𝘁𝗵𝗲 𝗲𝗱𝗴𝗲. 🌍 🔗 Resources: Download the models from the Hugging Face repository: https://lnkd.in/gp2zmkSq Blog post: https://ibm.co/3TDul9a Research paper: https://ibm.co/3TAILXG #AI #ClimateScience #WeatherForecasting #OpenSource #NASA #IBMResearch

>380,000 data points on climate policy data. This is the culmination of >2 years work with a great team on the OECD - OCDE Climate Actions and Policies Measurement Framework (CAPMF). Still cannot believe that the CAPMF data is finally publicly available.   All >380,000 data points are publicly available. Ready to be explored by you and your colleagues to analyse 👉 climate policy trends 👉 which policies worked and which did not 👉 differences in climate policy approaches across countries and across time 👉 any climate policy-related question that you may have      Link to the database: https://oe.cd/dx/capmf Please like, comment, share, and - above all - USE!   #climatepolicy, #mitigation, #climatedata, #climatechange, #sustainability

A breakthrough in climate data accessibility: meet CRA5 ERA5 is one of the most important global reanalysis datasets for weather and climate research — but in raw float32 form it reaches around 400 TB, which is a major barrier for storage, sharing and AI workflows. CRA5 tackles this by compressing ERA5 to just 0.85 TB using the neural-network framework Aeolus — a 470× reduction. Despite the extreme compression, the dataset preserves key climatological patterns, power spectra and extreme-weather structures, with a reported mean absolute temperature error of only 0.17 K across 37 vertical levels. Why it matters: CRA5 makes high-resolution atmospheric data far more portable and accessible, lowering infrastructure barriers for researchers, smaller teams and AI-based weather forecasting. Code, pretrained models and dataset links are available on GitHub. This could be a real game-changer for climate and weather research. https://lnkd.in/dB4NedpS

With 4 years left of the SDGs, it is worth pausing to reflect on what a decade of monitoring has truly taught us. The United Nations Statistical Commission’s review of SDG measurement is both impressive and candid. Over the past decade, the global indicator framework has expanded substantially, strengthened national statistical systems, improved coordination across agencies, and embedded disaggregation more systematically into development reporting. The SDG framework has become a genuine global public good. At the same time, the report is clear about structural lessons that can inform any post-2030 framework. (1) Alignment: between policy ambition and statistical feasibility must happen earlier. In several cases, targets were politically negotiated before indicators were methodologically mature, creating complexity, uneven implementation, and reporting burdens for countries. (2) Capacity constraints: remain significant, particularly in lower income contexts. Many countries still face resource limitations, data gaps, and uneven ability to report regularly across all indicators. (3) Simplicity: one of the report’s strongest lessons is that the SDG framework became highly complex, with a large number of indicators creating reporting burdens and stretching national capacity. Future frameworks should focus on fewer, clearer, high value indicators that drive decision making rather than compliance reporting. The opportunity for the private sector is not to replace official statistics, nor to create parallel systems. It is to strengthen the architecture that already exists and to bridge any residual data gaps that may exist . Two opportunities stand out. - The emphasis on involving statisticians early in agenda setting. Private sector research organizations can contribute methodological expertise upstream, helping ensure that future development targets are measurable, comparable, and grounded in robust survey and data science practices from the outset. - The use of non traditional data sources, as an important evolution in SDG monitoring. Private sector datasets, including high quality experiential and behavioral data, can complement national sources. But this integration must meet standards of transparency, documentation, interoperability, and quality assurance consistent with official statistics principles. Gallup’s World Poll illustrates what this alignment can look like. Nationally representative, globally comparable survey data have supported SDG related insights on food insecurity, forced labor, diet quality and safety. These data have helped illuminate dimensions of development that are not captured in administrative or consistently captured in national survey systems alone. The broader lesson from a decade of SDG monitoring is clear: sustainable development requires sustainable data systems. Those systems must be methodologically sound, institutionally anchored, and collaborative by design. The report link is in the comments below.

🛑BREAKING: Brazil Calls for a Global Public Digital Infrastructure to Speed Up Climate Action🛑 💠At the request of COP30 President, Ambassador André Corrêa do Lago, the Instituto de Tecnologia e Sociedade (ITS Rio) and Ronaldo Lemos formulated Brazil's call for a Global Public Digital Infrastructure for Climate (Climate DPI), a proposal that positions data, finance, and intelligence as the missing layer of the Paris Agreement’s implementation. 💠The green transition lacks a shared digital backbone. Climate action today is fragmented across nations, funds, and data silos. Climate DPI aims to correct this by functioning as an “operating system for climate action”, where digital identity, interoperable payments, and open environmental data converge into a single ecosystem. 💠Its architecture, ClimateStack, links five layers: 🟢 Identity - unique digital records for individuals, organizations, and climate assets. 🟢 Finance - smart contracts enabling transparent flows, compensation, and carbon credits. 🟢 Open data - integration of satellite and sensor networks (GEOSS, Copernicus, INPE/PRODES). 🟢 Applications - public digital services for deforestation alerts, risk forecasting, and climate markets. 🟢 Access - multi-interface delivery (web, SMS, radio) to ensure inclusion. 💠By connecting existing but isolated technologies, the project envisions real-time emissions tracking, faster disaster response (up to 40%), and universal climate alerts by 2035. 💠Strategically, Brazil frames Climate DPI as COP30’s digital legacy, a move that links digital public goods and climate governance. A project that can redefine how the world measures, finances, and enforces its climate commitments. 🔗 Read the full proposal on the official COP30 website. https://lnkd.in/dTUXJFw6

🚀 25 years in the making—#OpenCEDA is live! When I released the very first version of the Comprehensive Environmental Data Archive (CEDA) back in 2000 as a PhD student at Leiden, I imagined a world where rigorous, transparent Scope 3 data would be available to anyone tackling climate change. Today that vision becomes reality. CEDA is now free and open to the public at openceda.org—unlocking >95 % of global GDP/GHG coverage, 400 industry sectors across 148 countries and regions, and tens of thousands of up-to-date emissions factors, refreshed annually. This milestone is the work of an incredible community. Deep gratitude to Mo Li, Ph.D., Cheng Lin, Yohanna Maldonado, Michael Steffen, Jake Feintzeig, Jonathan Gidden, Gizem Ilayda Dinç Liston Witherill, Christian Anderson—and every researcher, practitioner, and customer who has shaped CEDA since its 2000 debut. Whether you’re a start-up calculating your footprint, a Fortune 500 driving supply-chain decarbonization, or a researcher pushing LCA boundaries—this data is yours. Dive in, build, question, and tag me with what you create. Let’s accelerate climate action together! #Scope3 #LCA #GHGAccounting #OpenData #Sustainability #ClimateTech

🔍 I've been thinking deeply about what makes data-powered governance truly effective. After some observation and some experience, I've identified three critical ingredients – what I humbly call the "Three D's". 📊 Data Exchange Platforms: The foundation that enables innovation through open data sharing and collaborative models. Estonia's X-Road has revolutionized public services by creating a secure data exchange layer connecting government databases. Citizens can access nearly all government services online, with 99% of public services available digitally. Singapore's Smart Nation Sensor Platform integrates data from sensors and IoT devices across the city to optimize everything from traffic flow to energy consumption. 📜 Data Policies: The essential guardrails that establish trust. The European Union's GDPR has set a global standard for data protection, enhancing citizen trust while creating a framework for responsible innovation. Closer home, the DPDP will start to set benchmarks for data-centric guardrails for a massive, diverse, and data-rich country like India. 🧩 Decision-Support Systems: The mechanisms that transform data into action. South Korea's COVID-19 response leveraged their Epidemic Investigation Support System to enable rapid contact tracing while maintaining transparency with citizens. Also, New Zealand's Integrated Data Infrastructure connects data across government agencies to inform policy decisions with robust economic analysis, resulting in more targeted and effective social programs. 💡 When these 3D's are combined deftly by the public-sector, citizen-centric governance becomes the cornerstone for any government. For the scale India operates at, it's a very good opportunity to show the way for the Global South. 🤔 I think we're at that inflection point with the recent announcement of AI Kosha and the DPDP, and they can help safely incubate innovative solutions that will optimize the delivery of government schemes, thereby ensuring timely, targeted assistance for citizens. Thoughts? #DigitalTransformation #PublicSector #Innovation #DataStrategy

🌍 A new era of open data has arrived 🌍 On 1 October 2025, European Centre for Medium-Range Weather Forecasts - ECMWF made its entire Real-time Catalogue open to all, under a CC-BY-4.0 licence. This is one of the largest meteorological datasets in the world, now freely accessible for science, innovation and entrepreneurship. This moment feels very much like when Landsat data was opened years ago — a decision that unlocked billions in economic value, empowering entrepreneurs, local governments, and innovators to build solutions that no one had imagined at the time. Now, with open meteorological data: 🔹 Local businesses can create new weather-driven services — from agriculture optimisation and insurance models to logistics and retail planning. 🔹 Entrepreneurs and startups gain access to world-class data to train AI/ML models, develop predictive tools, and build new digital products without prohibitive licensing barriers. 🔹 Local governments can improve urban planning, resilience strategies, and climate adaptation measures by tapping into global-scale forecasts at local resolution. 🔹 Communities worldwide benefit from better preparedness, aligning with the UN’s Early Warnings for All initiative — protecting lives and livelihoods. Innovation often begins when barriers to data fall away. With ECMWF opening the gates, we can expect new industries, smarter decisions, and stronger climate resilience to emerge — just as we saw with the Landsat revolution. 💡 The question is: who will be the first to harness this opportunity and turn open forecasts into open futures? https://lnkd.in/e5SEt-dP #OpenData #ClimateResilience #Innovation #Entrepreneurship #WeatherData #ECMWF #AI #Geospatial

🗽 As New York City elects its next mayor — and ushers in a new city administration — it’s worth revisiting if and how data can serve as a cornerstone for urban flourishing (when done responsibly). 👉 A few years ago, I had the opportunity to testify before the #NYC Council Committee on Technology and the Commission on Public Information and Communication (COPIC) on how the city could better leverage and share data to improve people’s lives. While progress has been made since then, many of the recommendations remain as relevant as ever — perhaps even more so as NYC confronts new challenges in an era of AI, climate change, and widening inequalities. 🏙️ My testimony, “Leveraging and Sharing Data for Urban Flourishing,” outlined four key questions still vital for the incoming NYC leadership: 1️⃣ Why should NYC care about data and data collaboration? Because open and accessible data not only enable transparency — they improve decision-making, service delivery, and public trust. 2️⃣ If you build a data-sharing framework, will they come? Only if it’s demand-driven, matching real public problems with data supply. 3️⃣ How can we engage the private sector? Through data collaboratives that unlock the public value of private data. 4️⃣ Is technology the answer? It’s necessary but not sufficient — the real challenge is cultural and institutional: creating the incentives, governance and trust, and leadership to act. 💡 In addition to those four themes, I would add a few additional recommendations for the next administration: ✅ Establish a “City Data Commons” — a shared, secure environment that enables responsible data reuse across agencies and sectors, guided by public purpose and ethical safeguards. ✅ Appoint Data Stewards across agencies — empowered to broker responsible data collaboration, ensuring compliance, quality, and value creation. ✅ Adopt AI-Ready Data Standards — ensuring the city’s data infrastructure is prepared for generative and predictive uses while remaining transparent and equitable. ✅ Institutionalize Social License mechanisms — to ensure public legitimacy and trust in how data (especially personal or sensitive) is reused for innovation and policymaking (this could include establishing a Data Assembly, a citizens assembly on the re-use of data). ✅ Conduct a “100 Questions for New York City” initiative — to identify the most pressing and high-impact questions that, if answered with data, could improve urban life and guide strategic priorities across the new administration. ✅ Invest in civic data literacy and capacity — so that not just city officials but also communities can use data to inform action and co-create solutions. ✅ Measure and communicate impact — tracking how data-driven initiatives improve outcomes, reduce disparities, and make city government more responsive. 🔗 Read testimony: https://lnkd.in/e5w6sh85 #data #NYC #mayor #elections #data4good