Using Data to Improve Carbon Impact Programs

Dear all, Going live today … in collaboration with the World Resources Institute Land & Carbon Lab and Global Forest Watch, we used AI to map the global drivers of forest loss at 1km resolution - a 100x improvement over previous (10km) state of the art models -- for every year 2001 - 2022. Forest loss is the single largest threat to terrestrial biodiversity; is responsible for c. 15% of anthropogenic CO2 emissions; and is a major focus for emerging policies and targets at local to global scales (such as EUDR). To prevent and even reverse forest loss, we need to understand the underlying drivers of forest loss, and how these drivers vary geographically, and have been varying through time. Methodologically, this is an example of the rapidly advancing field of AI-powered remote sensing, using scaled up deep learning (specifically, specially adapted vision models) that can cope with the immense volume, complexity, and noise levels in satellite data and associated geospatial data. This work required advanced data processing, model and infrastructure development, expert human labelling, rigorous evaluation, domain expertise, and of course, great people, great team work … and time! Some examples of uses and potential impact: 🌲 Global Forest Watch leverages the drivers data as a key input for their global forest carbon flux model, enabling more accurate estimations of emission factors and, when combined with carbon flux data, identifying GHG emissions by specific drivers. 🌳 The Joint Research Centre (JRC) integrates the drivers of forest loss data into their 2020 global forest cover map, directly supporting the EU's regulation on deforestation-free supply chains. 🌴 The drivers data are already being used by WRI in methods being developed to account for land use change emissions in greenhouse gas inventories. 🍁 More generally, these detailed maps provide crucial insights into deforestation patterns and drivers, empowering local communities, policymakers, land managers, researchers and others to intervene effectively to prevent deforestation. To learn more, see the links below, which I stole without shame from a complementary LinkedIn post from our amazing WRI colleague Michelle Sims (hello and thanks Michelle!). And a shout out to some of the other key people involved:  Radost Stanimirova, PhD, Anton Raichuk, Maxim Neumann, Jessica Richter, Forrest Follett, @James MacCarthy, Kristine Lister, Christopher Randle, Lindsey Sloat, Elena Esipova, Jaelah Jupiter, Charlotte Y. Stanton, PhD, Dan Morris, Christy Melhart Slay, Nancy Harris. 👉 The ERL paper: https://lnkd.in/gxV34-3W 👉 Summary of key findings: https://lnkd.in/gghcyVzx 👉Technical blog: https://lnkd.in/gBv5ErKU Data is available on: 🌎 Google Earth Engine: https://lnkd.in/gt4t9zhp 🌏 World Resources Institute's Data Explorer: https://lnkd.in/gbVMUzpx 🌍 Global Forest Watch: https://gfw.global/2LUOmIx 🌍 Zenodo (including training + val data): https://lnkd.in/gsn-J9gg

Why do so many corporate decarbonization efforts stall between the sustainability report and meaningful action? In my recent byline for Financial Times Agenda, co-authored with Professor Dr. Gunther Friedl and Professor Dr. Jürgen Ernstberger from TUM School of Management, we argue it is fundamentally a data challenge. The problem is not a lack of data – it is that businesses are not connecting data across workstreams and supply chains. Our solution, a "Green Ledger," taps into established accounting frameworks. The core principle is to start treating carbon like a currency – tracking it with the same granularity as a financial transaction. By integrating carbon data into financial systems, companies can manage emissions with the same precision they apply to their balance sheets. This transforms sustainability from a compliance exercise into a driver for decisions that benefit both business and the planet. I invite you to read our full perspective: https://lnkd.in/eFMnZ9PN Technical University of Munich

GIS Application in Carbon Projects Geographic Information Systems (GIS) are essential tools in carbon projects, particularly in carbon sequestration, carbon stock assessment, REDD+ programs, and climate mitigation initiatives. GIS integrates spatial data, remote sensing, and environmental modeling to quantify, monitor, and verify carbon storage. 1️ Baseline Carbon Stock Assessment GIS is used to estimate existing carbon stocks in: Forest biomass Soil organic carbon Wetlands and mangroves Agricultural lands How it works: Satellite imagery classification (forest vs non-forest) Land Use/Land Cover (LULC) mapping Biomass estimation using allometric equations Integration of field sample plots with spatial interpolation Output: Carbon stock map (tCO₂e per hectare) 2️ Land Use / Land Cover (LULC) Change Detection GIS enables monitoring of: Deforestation Afforestation Reforestation Degradation Using multi-temporal satellite imagery (e.g., Sentinel, Landsat), GIS supports: NDVI analysis Change detection modeling Forest loss quantification This is critical for REDD+ and voluntary carbon markets. 3️ Carbon Sequestration Modeling GIS models carbon sequestration potential for: Agroforestry systems Mangrove restoration Forest regeneration Soil carbon enhancement Spatial modeling incorporates: Rainfall Soil type Elevation Temperature Vegetation density Output: Sequestration potential map 4️ Project Boundary Delineation GIS defines: Project area boundaries Buffer zones Leakage zones Control/reference sites Accurate spatial delineation is critical for carbon credit validation and certification. 5️ MRV (Monitoring, Reporting & Verification) GIS supports carbon MRV by: Monitoring biomass changes over time Generating time-series maps Producing verifiable spatial evidence Integrating drone imagery and field GPS data Spatial databases improve transparency and compliance. 6️ Leakage and Risk Assessment GIS evaluates: Fire risk Deforestation pressure Urban expansion Agricultural encroachment Risk maps help ensure permanence of carbon storage. 7️ Carbon Accounting and Reporting GIS integrates with carbon accounting models to: Calculate total carbon credits (tCO₂e) Estimate avoided emissions Prepare validation reports Spatial dashboards and maps support stakeholder communication. 8️ Policy and Climate Planning Governments and NGOs use GIS to: Identify high carbon stock areas Prioritize conservation zones Develop climate adaptation strategies Support NDC implementation Common GIS & Remote Sensing Tools Used ArcGIS Pro QGIS Google Earth Engine ERDAS Imagine Python (GeoPandas, Rasterio) PostGIS Drone-based mapping tools Benefits of GIS in Carbon Projects ✔ Accurate carbon quantification ✔ Transparent MRV system ✔ Reduced uncertainty ✔ Spatial decision support ✔ Climate mitigation planning ✔ Increased credibility in carbon markets

𝗥𝗲𝗺𝗼𝘁𝗲 𝗦𝗲𝗻𝘀𝗶𝗻𝗴 𝗳𝗼𝗿 𝗙𝗼𝗿𝗲𝘀𝘁 𝗖𝗮𝗿𝗯𝗼𝗻: 𝗨𝗻𝗹𝗼𝗰𝗸𝗶𝗻𝗴 𝗮 𝗣𝗮𝘁𝗵 𝗙𝗼𝗿𝘄𝗮𝗿𝗱 A report prepared by Carbon Direct in collaboration with Meta takes a deep look at how remote sensing can transform forest carbon projects. It’s an important contribution to the sustainability fraternity, helping us move from aspiration to action when it comes to credible carbon accounting. 💵 📈 Forests remain one of our most powerful tools for climate mitigation, yet measuring, monitoring, reporting, and verifying (MMRV) their carbon potential is still complex and costly. This document highlights how remote sensing through satellites, lidar, and AI, can make MMRV more transparent, accessible, reliable, and scalable. 𝗞𝗲𝘆 𝘁𝗮𝗸𝗲𝗮𝘄𝗮𝘆𝘀 𝗜 𝗳𝗼𝘂𝗻𝗱 𝗽𝗮𝗿𝘁𝗶𝗰𝘂𝗹𝗮𝗿𝗹𝘆 𝘂𝘀𝗲𝗳𝘂𝗹: ➡️ We need clear standards on what constitutes acceptable remote sensing data and workflows. ➡️Geographic and ecological boundaries of datasets must be defined—models aren’t universally applicable. ➡️Managing uncertainty in carbon credit issuance is critical to building trust in the voluntary carbon market. ➡️A global benchmarking dataset and centralized data portal could democratize access to high-quality tools. ➡️Deep learning models (like Meta’s canopy height mapping) can deliver higher resolution, more accurate forest insights. 𝗪𝗵𝗼 𝗯𝗲𝗻𝗲𝗳𝗶𝘁𝘀? -Project developers gain cost-effective tools for reliable monitoring. -Registries and VVBs can strengthen credibility through standardized data use. -Buyers and investors get greater confidence in the integrity of carbon credits. -And for the broader sustainability community—it’s about scaling nature-based solutions with rigor and equity. Reading this, I am reminded of how vital it is to align governance, innovation, and community building. Remote sensing isn’t just technology—it’s a bridge between science, markets, and planetary health. #planetaryhealth #planetaryboundaries #sustainability #ClimateAction #carbonfootprint #NetZero #ClimateEmergency #SDG #ESG #GHG #netzero #forests #carbonmarkets #remotesensing

Carbon data is moving 𝘂𝗽𝘀𝘁𝗿𝗲𝗮𝗺 in construction. Design tools now treat it like cost or performance. Great example: Autodesk’s new Fusion platform now has a Manufacturing Sustainability Insights add-on that shows embodied carbon in real time as you model. Gensler’s gBlox.CO₂ tool does the same, letting architects compare carbon impacts of design choices at the very start of a project. That changes 𝘸𝘩𝘦𝘯 carbon data shows up. Instead of arriving late in procurement, it’s influencing decisions upstream, while projects are still being shaped. On the other side, Buy Clean laws are pushing carbon data deeper into procurement, with requirements for Environmental Product Declarations (EPDs) and maximum global warming potential (GWP) thresholds. Together, these shifts are aligning demand and supply around the same standard. → 𝗗𝗲𝘀𝗶𝗴𝗻𝗲𝗿𝘀 𝗲𝘅𝗽𝗲𝗰𝘁 𝗶𝗻𝘀𝘁𝗮𝗻𝘁 𝗰𝗮𝗿𝗯𝗼𝗻 𝗰𝗼𝗺𝗽𝗮𝗿𝗶𝘀𝗼𝗻𝘀 as part of their workflow → 𝗣𝗿𝗼𝗰𝘂𝗿𝗲𝗺𝗲𝗻𝘁 𝗿𝘂𝗹𝗲𝘀 𝗲𝗻𝗳𝗼𝗿𝗰𝗲 𝘃𝗲𝗿𝗶𝗳𝗶𝗲𝗱 𝗱𝗶𝘀𝗰𝗹𝗼𝘀𝘂𝗿𝗲𝘀 at the point of bidding → 𝗣𝗿𝗼𝗱𝘂𝗰𝗲𝗿𝘀 𝗻𝗲𝗲𝗱 𝗘𝗣𝗗𝘀 𝗶𝗻 𝗽𝗹𝗮𝗰𝗲 or risk being left out of both conversations What that really means: 𝗩𝗲𝗿𝗶𝗳𝗶𝗲𝗱 𝗘𝗣𝗗𝘀 𝗮𝗿𝗲 𝗯𝗲𝗰𝗼𝗺𝗶𝗻𝗴 𝘁𝗵𝗲 𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 𝗼𝗳 𝘀𝘂𝗽𝗽𝗹𝘆 𝘢𝘯𝘥 𝗱𝗲𝗺𝗮𝗻𝗱. They’re how producers enter the market, and how designers and contractors make informed choices. That’s progress. Carbon isn’t a background thing; it’s visible, comparable, and shaping decisions from the first sketch to the final bid.

Leveraging GHG data and analytics to accelerate business transformation 🌎 As regulations tighten and the demand for transparency grows, businesses face increasing pressure to adopt robust greenhouse gas (GHG) data and analytics systems. Establishing a structured framework for emissions measurement and analysis is critical for compliance, but its benefits extend far beyond regulatory requirements. A comprehensive GHG data architecture enables businesses to measure, manage, and act on emissions across the full value chain, paving the way for meaningful transformation. To meet both current and future expectations, organizations must focus on measuring emissions across Scopes 1, 2, and 3. Addressing direct emissions (Scope 1), energy-related emissions (Scope 2), and value chain emissions (Scope 3) ensures a complete understanding of an organization’s carbon footprint. Scope 3, in particular, represents the largest and most complex challenge, but it also holds the greatest opportunity for reducing environmental impact and driving systemic change across supply chains. With precise data on emissions across all scopes, businesses can move beyond compliance to actionable insights. By identifying carbon hotspots and setting reduction targets, organizations can optimize processes such as energy efficiency, supply chain sourcing, and logistics management. These actions help integrate sustainability into business operations while delivering cost efficiencies and improving resilience. A robust GHG data and analytics system also facilitates full-value chain transformation. Leveraging technologies like machine learning, scenario modeling, and ecosystem data exchanges enables businesses to plan for long-term carbon reduction strategies and innovate low-carbon products. Addressing emissions holistically across Scopes 1, 2, and 3 ensures alignment with global climate goals while creating competitive advantages in sustainable markets. Measuring and acting on emissions across the entire value chain is no longer optional. Businesses equipped with accurate data and advanced analytics capabilities can meet regulatory demands, reduce emissions at scale, and drive meaningful progress toward a low-carbon economy. Source: Gartner #sustainability #sustainable #business #esg #climatechange #GHG

Achieving 60% primary & proxy primary data coverage for Scope 3 purchased goods and services Spend-based emissions factors are as a good starting point. As many have noted, transitioning to primary data supports strategic decision-making and supplier decarbonization approaches. As expectations from customers continue to increase, it was a priority in 2025 to transition toward supplier-specific primary data for Scope 3 Categories 1 and 2. Here is an approach that enabled 60% emission coverage with primary & primary proxy data 1️⃣ Start with readily available high-quality datasets - leverage datasets such as CDP to incorporate primary supplier data. 2️⃣ Expand beyond datasets - strategically review individual sources of supplier-specific emission factors to improve coverage in key categories 3️⃣ Replace spend-based factors with primary data proxies - develop category averages from supplier data where reasonable coverage exists. 4️⃣ Apply consistently across time - extend methodology to prior years for comparability. Why were product carbon footprints (PCFs) not used as primary data source? In healthcare, PCF availability remains limited, and the diversity of products for a b2b Tier 1 makes invoice-level matching impractical at scale. Achieving over 50% primary data meaningfully improves the confidence and usefulness of Scope 3 data, enabling: 🔹 Better identification of decarbonization opportunities 🔹 Greater comparison of supplier carbon performance 🔹 Stronger alignment between reporting and procurement strategy After completion of limited assurance, I can share more on the impact — indications are a material downward shift in reported emissions across all years. #Scope3

Turning Data into Action Improving sustainability in healthcare starts with meaningful data. At AdventHealth, we’ve been working to strengthen our approach to tracking and reducing emissions with real-time insights. Watershed recently published a case study on our journey, highlighting how automating data collection has helped us: ✅ Set clear targets, including a 50% emissions reduction by 2030 ✅ Streamline reporting, cutting the time to produce annual reports in half ✅ Improve supplier engagement, driving better Scope 3 visibility We’re grateful for the collaboration across our teams and the strong support behind this work. Read the full case study here: https://lnkd.in/efyn8tTp

🚀 Getting Started with Better Emissions Data for Scope 3.1 (Purchased Goods and Services) Welcome to the first post in a series dedicated to supercharging your supply chain emissions intelligence. 🌱 Over the coming days and weeks, I'll be sharing practical tips to help you enhance your emissions data and pinpoint actionable initiatives with your suppliers. Let’s dive into Part 1/n: transitioning from spend-based to activity-based emissions data. 💡 Why Spend-Based Isn't Enough Many companies still rely on spend-based emission factors to estimate supply chain emissions, but this approach can be misleading. 💸 Spend is influenced by prices, discounts, currency effects, and more—leading to a skewed picture. Plus, these factors often represent industry averages, which can result in inaccuracies. 🔧 The Activity-Based Approach A more precise method is to break down purchased goods to their material level and use activity-based emission factors. Instead of using a generic kgCO2/$ spent factor for a water pump, consider the materials involved—steel, aluminum, PET, rubber—and apply emission factors based on the weight of each material. ⚖️ This approach significantly improves accuracy. 📊 Gathering Activity-Level Data Accessing activity-level data can be easier than you think. For commodities and single-material components, material and unit-weight data might be available on purchase orders, invoices, or product specs. 📝 For more complex items, consider requesting a bill-of-materials (BOM) from your supplier or use AI tools like Terralytiq’s teardown bot to estimate a BOM (attached picture is the estimation from our algorithm for prompt "detailed BOM for 0.5 kw water pump 35lbs." ✅ Conclusion By the end of this process, you'll have your procurement portfolio broken down by materials and quantities, enabling you to use activity-based emission factors for a much more accurate carbon footprint. 🌍 👉 Stay tuned for the next post, where I'll explore how to make activity-based EFs supplier and supply chain-specific with minimal primary data. #SupplyChain #Sustainability #CarbonFootprint #Scope3 #EmissionsData #ESG