Accurate modeling of CO₂ storage in the subsurface is a critical challenge for scaling Carbon Capture and Storage (CCS). 🌎 But here’s the catch: the inverse problem (recovering geological properties from sparse field observations) is severely ill-posed. 🤒 Traditional approaches either struggle with the scarcity of measured data or are too computationally expensive. 💸 In our new work, we introduce Fun-DDPS (Function-space Decoupled Diffusion Posterior Sampling), a generative framework that decouples the problem into two parts: a function-space diffusion model that learns a prior over geological parameters, and a differentiable Local Neural Operator surrogate for physics modeling and conditioning. ✨ Why does the decoupling matter? The diffusion prior handles the heavy lifting of recovering missing geological information, while the neural operator surrogate makes data assimilation fast and physically grounded — no expensive full-physics simulations in the loop. Key results on synthetic CCS datasets: ⏩ 11x improvement in forward modeling with only 25% observations ✅ Robust inverse modeling for data assimilation under sparse, noisy conditions 🔥 First rigorous validation of diffusion-based inverse solvers against asymptotically exact Rejection Sampling (RS) posteriors This points toward a scalable, practical path for uncertainty-aware subsurface characterization — something the CCS community needs as projects move from pilots to full-scale deployment. 📷 Huge kudos to my amazing collaborators — this work wouldn’t have been possible without them: @IsaacJu13 @AnimaAnandkumar Sally M Benson @ggg_www_ #CarbonCapture# #CO2Sequestration# #MachineLearning# #DiffusionModels# #NeuralOperators# #AI4Science# #CCS# #Sustainability#

The EPA published its power plant carbon repeal on 17th September. Its model selects 154 gigawatts of new combined-cycle gas capacity by 2035 with or without the carbon rules. The emissions and price forecasts are different. Repeal produces 406 million tonnes more power-sector CO2 in 2035, a 37% increase, while average retail electricity prices are projected to be 5.8% lower. Equal new gas capacity does not mean equal electricity production. In the repeal model, more coal plants keep operating and fewer renewables get built. There is a crucial assumption. The case retaining the rules assumes carbon capture works and can be installed on time. EPA disputes that feasibility. The model comparison cannot prove both paths are achievable. Both cases include rising data-center demand. Neither isolates the emissions caused by AI. The model also removes more requirements than the final partial repeal, a difference EPA says would not change its conclusions.

ExxonMobil won approval for its Rose carbon-capture project in Texas, allowing the company to move ahead with the emission-reducing development that could be among the biggest of its kind

Canada and Alberta have reached a carbon pricing deal that would pave the way for construction of a new oil pipeline starting as early as 2027, while scaling back a carbon capture project that Ottawa tied to the plan. Prime Minister Mark Carney and Alberta Premier Danielle Smith announced the agreement on Friday