Reproducible methods for climate risk modeling

𝗕𝗥𝗘𝗔𝗞𝗜𝗡𝗚 𝗡𝗘𝗪𝗦- after 1,5 years, our 𝗖𝗹𝗶𝗺𝗮𝘁𝗲 𝗥𝗶𝘀𝗸 𝗦𝘁𝗿𝗲𝘀𝘀 𝗧𝗲𝘀𝘁𝗶𝗻𝗴 𝗠𝗲𝘁𝗵𝗼𝗱𝗼𝗹𝗼𝗴𝘆 benchmarking paper with UNEPFI is finally out! 💡What started as an idea almost 2 years ago is now finally coming to life. 🔭After numerous workshops and survey sessions with 20+ UNEPFI banks . 📝Long hours researching, discussing, summarizing, writing. Our report now synthesizes all this collected and public information in one place to help finance professionals 𝗻𝗮𝘃𝗶𝗴𝗮𝘁𝗲 𝗲𝗺𝗲𝗿𝗴𝗶𝗻𝗴 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗿𝗶𝘀𝗸 𝘀𝘁𝗿𝗲𝘀𝘀 𝘁𝗲𝘀𝘁𝗶𝗻𝗴 𝗽𝗿𝗮𝗰𝘁𝗶𝗰𝗲𝘀 and strengthen their risk management capabilities. We have developed this report as collaboration between SAS and the United Nations Environment Programme Finance Initiative (UNEP FI) and their 20+ banks. Based on survey and workshops conducted with 20+ UNEPFI bank this report explores: 📌What are the common scenarios, approaches and assumptions applied by banks for assessing Transition and Physical risks 📌Which risk measures banks use to simulate the 𝗳𝗶𝗻𝗮𝗻𝗰𝗶𝗮𝗹 𝗶𝗺𝗽𝗮𝗰𝘁 𝗼𝗳 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗿𝗶𝘀𝗸𝘀 📌How do banks adress and manage 𝗠𝗼𝗱𝗲𝗹 𝗥𝗶𝘀𝗸 embedded in their climate risk models 📌To what extent is climate stress 𝗶𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗲𝗱 with bank's other forward looking processes📌How vital is the 𝘀𝘂𝗽𝗽𝗼𝗿𝘁𝗶𝗻𝗴 𝗿𝗼𝗹𝗲 𝗼𝗳 𝗮 𝗿𝗼𝗯𝘂𝘀𝘁 𝗜𝗧 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 for an efficient and integrated climate risk stress testing 📌𝗖𝗮𝘀𝗲 𝘀𝘁𝘂𝗱𝗶𝗲𝘀 & 𝗰𝗼𝗻𝗰𝗿𝗲𝘁𝗲 𝗲𝘅𝗮𝗺𝗽𝗹𝗲𝘀 of how banks adress climate risk management 📌Expert perspectives on 𝘁𝗵𝗲 𝗿𝗼𝗮𝗱 𝗮𝗵𝗲𝗮𝗱 for the climate risk stress testing discipline Additionally, the report highlights areas for further enhancement in climate stress testing methodologies. By presenting 𝗴𝗼𝗼𝗱 𝗽𝗿𝗮𝗰𝘁𝗶𝗰𝗲𝘀 𝗳𝗼𝗿 𝗯𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸𝗶𝗻𝗴 and identifying areas for prioritization I am confident this report will help institutions in 𝗺𝗼𝘃𝗶𝗻𝗴 𝘁𝗵𝗲𝗶𝗿 𝗖𝗹𝗶𝗺𝗮𝘁𝗲 𝗥𝗶𝘀𝗸 𝗦𝘁𝗿𝗲𝘀𝘀 𝗧𝗲𝘀𝘁𝗶𝗻𝗴 𝗽𝗿𝗼𝗰𝗲𝘀𝘀 𝘁𝗼 𝘁𝗵𝗲 𝗻𝗲𝘅𝘁 𝗹𝗲𝘃𝗲𝗹. 🎢What a journey this was. I am so grateful for the opportunity to be part of this exercise and co-lead this great initiative. 👏My big thanks and congratulations go to the report team: Maheen Arshad, Melanie O'Toole, Arjun Mahalingam,David Trinh for this excellent work. The report download link can be found below. I am happy to provide more details and eager to hear your thoughts.

🌍📊Drought Risk Mapping using Random Forest Modelling Understanding drought risk requires combining climate science with modern geospatial analytics. In this study, a Random Forest machine learning model was applied to TerraClimate data (2014–2024) to analyze drought dynamics across Kenya . The analysis integrates several key components: • Drought Occurrence Rate (DOR) 🌧️ derived from monthly PDSI values (PDSI < −2) to quantify how frequently drought conditions occur. • Random Forest predictive modelling 🤖 using climate predictors (precipitation, evapotranspiration, soil moisture, minimum and maximum temperature). • Spatial drought probability mapping 🗺️ to estimate the likelihood of drought occurrence. • Risk classification (5 classes) 📍 to identify areas with very low to very high drought risk. • Model validation using ROC–AUC, overall accuracy, and Kappa statistics 📈 to evaluate predictive performance. The results are visualized through an integrated geospatial dashboard including: • Spatial maps of drought probability and drought occurrence rate 🛰️ • Annual and monthly drought occurrence trends (2014–2024) 📅 • Risk classification maps for decision support 🧭 • Area coverage analysis of drought risk classes 📊 Such approaches demonstrate how machine learning and Earth observation data can support drought monitoring, climate risk assessment, and early warning systems 🌱, especially in regions where climate variability significantly impacts agriculture and water resources. #DroughtRisk #ClimateAnalytics #RandomForest #GoogleEarthEngine #GeospatialAnalysis #ClimateScience #MachineLearning #Hydrology #EarthObservation #EnvironmentalModeling

Flood science has historically been trapped between two extremes: hydrodynamic models that are highly accurate but computationally expensive, or global models that are too coarse (>1 km) to capture critical local vulnerabilities. Bridging this divide requires a fundamental shift from physics-based deduction to data-driven induction, a challenge that has defined my research over the last four years. This week, I am very happy to share that I have formalized this solution by submitting my Ph.D. thesis at Hong Kong Baptist University: "Towards GeoAI-based Data-driven Flood Management Solutions: A Synergistic Machine Learning and Earth Observation Framework" As illustrated, the thesis establishes a scalable GeoAI framework built on three synergistic pillars: 1. High-Dimensional Earth Observation (The Data) Leveraging multi-temporal global data streams (Landsat, Sentinel) to transition the field from data scarcity to data abundance. 2. Planetary-Scale Geo-Computation (The Platform) Utilizing cloud clusters (Google Earth Engine) and HPC (Shaheen-III) to democratize processing power, enabling the analysis of petabyte-scale geospatial data without traditional hardware constraints. 3. Machine Learning Analytics (The Engine) We systematically benchmarked 14 ML architectures to resolve the "accuracy-efficiency" trade-off, establishing a robust modeling engine. This framework was first operationalized across Pakistan's diverse landscapes to reveal that 95 million people reside in high-risk zones, before being scaled globally to produce the first harmonized 30 m flood susceptibility baseline. The Output: Global Flood Susceptibility Map (GFSM v1) By applying a climate modeling scheme (across 192 climate zones), we produced the first globally harmonized, 30 m resolution flood susceptibility baseline derived entirely from open-access data. This research addresses the "data equity deficit" in the Global South, where 89% of flood-exposed populations reside, often without high-resolution risk data. Next Steps: I will be releasing the open-source code, the GFSM v1 dataset, and the GEE web applications in the coming weeks. If you are interested in the work, feel free to drop a message to dicsuss further possibilities! For more info, feel free to check my updated portfolio: www.waleedgeo.com #geoai #earthengine #floodrisk #remotesensing #hkbu #datascience #gfsm #flood

While my focus these days is 100% on Earthmover, there are still a couple of papers in the pipeline from my old lab at Lamont-Doherty Earth Observatory. This one just published in GRL, led by the amazing duo Julius Busecke and Dhruv Balwada addresses an important issue in climate modeling: the impact of model resolution on air-sea fluxes: https://lnkd.in/guydiNyZ The exchange of heat between the ocean and atmosphere plays a crucial role in shaping Earth's weather and climate. However, many climate models miss the effects of small-scale flow features like sharp spatial temperature differences in the ocean or local changes in wind. In this study, we used high-resolution coupled climate simulations to show that these small-scale variations have a big impact on how much heat moves from the ocean to the atmosphere. On average, they lead to more ocean cooling—about 4 watts per square meter across the globe—and in some regions, the effect is much stronger, reaching up to 100 watts per square meter. The two main drivers of these changes are small-scale fluctuations in wind and ocean temperatures. Our results suggest that improving how climate models represent these small-scale features could make them more accurate at predicting ocean heat uptake. In addition to the science result, I'm especially proud of the open-science aspect of this paper. Doing this analysis was very data-intensive, requiring us to reprocess dozens of terabytes of model output with expensive bulk-formula and diffusion-smoothing algorithms. The code to reproduce is not just available--it actually works! 😂 And all of the data is publicly available via high-throughput cloud object storage. Check out the github repo for all the details of how we did it: https://lnkd.in/gA99y_gG

Our work "An Efficient SSP-based Methodology for Assessing Climate Risks of a Large Credit Portfolio" is out. This is joint work with Emmanuel Gobet and Ying Jiao. https://lnkd.in/eBnswcbx Comments welcome! Abstract: We examine climate-related exposure within a large credit portfolio, addressing transition and physical risks. We design a modeling methodology that begins with the Shared Socioeconomic Pathways (SSP) scenarios and ends with describing the losses of a portfolio of obligors. The SSP scenarios impact the physical risk of each obligor via a DICE-inspired damage function and their transition risk through production, requiring optimal adjustment. To achieve optimal production, the obligor optimizes various energy sources to align its greenhouse gas (GHG) emission trajectories with SSP objectives, while accounting for uncertainties in consumption trajectories. Ultimately, we obtain a Gaussian factor model whose dimension is of the order of the number of obligors. Two efficient dimension reduction methods (Polynomial Chaos Expansion and Principal Component Analysis) provide a fast and accurate method for analyzing credit portfolio losses.

The Basel Committee on Banking Supervision has released a groundbreaking methodology for incorporating physical climate risks into banks' credit risk models a significant step toward aligning financial risk management with climate realities. As climate-related disasters escalate in frequency and severity, banks are increasingly exposed to physical risks like floods, droughts, and storms. These risks can directly impair the ability of borrowers to repay loans, especially in vulnerable sectors like agriculture, real estate, and manufacturing. Key highlights from the framework: - Physical risk scenarios (e.g., chronic heat, acute flood events) are now directly modeled into probability of default (PD) and loss given default (LGD) estimations. - Integrates hazard, exposure, and vulnerability data at borrower or asset level. - Encourages forward-looking, granular, and geospatial risk assessments. - Recommends combining climate science data with traditional credit risk indicators. - Highlights the importance of data availability, uncertainty management, and ongoing calibration. This approach enhances banks’ capacity to proactively adjust capital buffers and credit policies in light of climate change, while also enabling regulators to better assess systemic climate risks. What this means for banks: Institutions that embed these climate-informed practices will not only be more resilient but also better aligned with emerging regulatory expectations and ESG market standards. As we transition into a low-carbon economy, climate risk is not a future threat — it's a current credit issue. This framework helps bridge that gap. #ClimateRisk #BaselCommittee #CreditRisk #SustainableFinance #PhysicalRisk #Banking #ESG #RiskManagement #ClimateFinance #FinancialStability