The paper introduces KG‑Chronos‑2, a surrogate forecasting model that augments a frozen Chronos‑2 time‑series predictor with knowledge‑graph‑conditioned retrieval and correction mechanisms for HEC‑RAS water‑surface elevation (WSE) prediction. In a benchmark involving 64 24‑hour windows across 4,675 cross sections, KG‑Chronos‑2 outperforms persistence, residual LSTM, GeoFNO, and hydraulic DCRNN‑style models, achieving a 0.246970 event‑balanced RMSE and reducing error by 14.13% relative to frozen Chronos‑2. The model also attains the lowest active‑window and final‑lead RMSE among the evaluated systems, demonstrating the benefit of coupling a frozen temporal predictor with project‑specific knowledge for warm‑start HEC‑RAS forecasting.
By Edward Holmberg, Elias Ioup, Mahdi Abdelguerfi
ChannelFlow-Tools is an open‑source, configuration‑driven pipeline that generates machine‑learning‑ready datasets for three‑dimensional obstructed channel flows. It combines procedural obstacle geometry generation across six shape families, signed‑distance‑field voxelisation, lattice‑Boltzmann simulation, and packaging into ML‑ready tensors, all driven by reproducible configuration files. The pipeline is validated through mesh‑integrity audits, SDF representation checks, solver benchmarks, and data‑integrity audits, and it has been used to train surrogate models (3D U‑Net, FNO, U‑FNO) that learn geometry‑to‑flow mappings and exhibit physically interpretable behaviour on out‑of‑distribution splits.
By Shubham Kavane, Lukas Schr\"oder, Kajol Kulkarni, Fernando Gonzalez, Harald Koestler
The paper introduces the Mass‑Conserving Perceptron (MCP), a physics‑aware AI framework that enforces conservation laws while learning hydrological process relationships from data. By progressively adding physically meaningful components—such as bounded soil storage, state‑dependent conductivity, variable porosity, infiltration capacity, surface ponding, vertical drainage, and nonlinear water‑table dynamics—to a single MCP storage unit, the authors demonstrate that predictive skill for daily streamflow improves across 15 U.S. catchments. The study finds that the impact of each process representation varies with hydroclimate, with vertical drainage boosting performance in arid and snow‑dominated basins but hindering it in rainfall‑dominated ones, while surface ponding has minimal effect; the best MCP configurations rival LSTM benchmarks while retaining explicit physical interpretability.
By Mohammad A. Farmani, Hoshin V. Gupta, Ali Behrangi, Muhammad Jawad, Sadaf Moghisi, Guo-Yue Niu
arXiv:2609.37565v1 Announce Type: new
Abstract: Deep learning surrogates can produce high-resolution coastal flood maps orders of magnitude faster than physics-based hydrodynamic simulators, yet tran...
By Bilal Hassan, Areg Karapetyan, Samer Madanat
The paper introduces the Spatiotemporal Conditional Operator (STCO), a framework for learning neural operators that can incorporate prescribed target‑time condition fields—such as body motion, inflow disturbances, or body‑force actuation—into time‑dependent PDE simulations. STCO combines a Flow‑Aware Graph Leaf (FAGL) partitioning scheme with Dual‑Site Feature‑wise Linear Modulation (DSFiLM) to inject these conditions before and after the core operator computation. Evaluated on twelve backbone architectures across an immersed‑boundary CFD benchmark, STCO achieves significant reductions in relative‑L2 field error (31.1%) and pressure‑derived load error (24.7%) while improving long‑lead predictions for most backbones.
By Xingxin Yang, Zhan Zhang, Juan Li
arXiv:2602. 22188v2 Announce Type: replace Abstract: Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid with the rock on the interfaces.
By Nathalie C. Pinheiro, Donghu Guo, Hannah P. Menke, Aniket C. Joshi, Claire E. Heaney, Ahmed H. ElSheikh, Christopher C. Pain
arXiv:2603.25779v2 Announce Type: replace-cross
Abstract: Groundwater represents a key element of the water cycle, yet it exhibits complex and context-dependent relationships that make its modeling c...
By Matteo Salis, Gabriele Sartor, Rosa Meo, Stefano Ferraris, Abdourrahmane M. Atto
The paper investigates why latent neural surrogate solvers, which compress physical system dynamics into a lower‑dimensional space, often fail during long‑horizon autoregressive rollouts. It demonstrates that training the latent representation only for reconstruction leads to instability, and proposes a set of training interventions—Koopman operator learning, Hamming noise injection, and multi‑step rollout fine‑tuning—that align the latent space with long‑horizon forecasting. These interventions reduce long‑rollout error by about 40 % and achieve accuracy comparable to full‑resolution models while using far fewer floating‑point operations and GPU memory, enabling stable extrapolation in mesoscale crystal‑plasticity simulations of high‑cycle fatigue.
By Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville
arXiv:2607. 23667v1 Announce Type: cross Abstract: A flow surrogate validated on a simple regime is often taken as evidence that the approach will carry to a richer one.
By Georg Winkler, Martin Stoll
arXiv:2606. 06077v1 Announce Type: cross Abstract: Autonomous underwater vehicle (AUV) launch and recovery (LAR) into the hull of an advancing host platform requires traversal of a complex, three-dimensional propeller wake whose hydrodynamic structure cannot be characterised by a uniform current model.
By Zachary Cooper-Baldock, Paulo E. Santos, Russell S. A. Brinkworth, Karl Sammut
arXiv:2607. 04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularly in mountainous regions where temperature can vary by several degrees over short distances.
By Francisco Passos
The paper introduces Sensitivity‑Constrained Neural Operators (SC‑NOs), which augment standard neural operator training with sampled Jacobian supervision from differentiable solvers or discrete adjoints. By matching selected sensitivities during training, SC‑NOs improve forward prediction accuracy and significantly enhance gradient‑based inverse reconstruction for distributed fields. Experiments on advection–diffusion, RANS–Spalart–Allmaras, high‑dimensional gridded inputs, and a shallow‑water tsunami source‑inversion case demonstrate that SC‑NOs achieve a better accuracy–cost trade‑off and enable near‑real‑time wave‑propagation forecasting from sparse observations.
By Abdolmehdi Behroozi, Chaopeng Shen, Daniel Kifer, Kathryn Lawson