mlsanityData to 14 Oct 2026

Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations

arXiv 2605.13761 ↗First posted 13 May 2026cs.LG cs.CEcited by 1

Not on the map. Why?

Abstract (arXiv)

AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-dimensional shallow water equation (SWE) solvers still require ~ 55 minutes per 96-hour run on a ~ 4.2-million-active-cell metropolitan basin (the Des~Plaines River basin at 30,m resolution), making such workloads prohibitive at native resolution. We present the Conditional Latent Dynamics Network (CLDNet): a low-dimensional latent neural ODE driven by rainfall, paired with a coordinate-based decoder conditioned on static terrain (elevation, slope, Manning roughness) that reconstructs depth and discharge at arbitrary query points. Pointwise decoding decouples memory from grid size and handles irregular watersheds natively, enabling metropolitan-scale training on a single compute node and direct queries at exact gauge coordinates without raster snapping. We evaluate CLDNet on a synthetic 250,000-cell Texas benchmark and on a new Des~Plaines case study of 114 real-rainfall Stage~IV storms whose reference simulator we validate against United States Geological Survey (USGS) gauges at the April~2013 flood-of-record (Nash--Sutcliffe efficiency 0.57--0.94 on mean-recentered water-surface elevation). CLDNet roughly halves the relative root-mean-squared error of an unconditional baseline, outperforms regular-grid VAE--ConvLSTM and FNO baselines on the Texas benchmark (both presuppose a Cartesian grid and do not apply to the irregular Des~Plaines watershed), reaches a critical success index of ≈ 86% at the 0.5,m inundation threshold, and produces a full 96-hour basin-wide forecast in ~ 29 seconds -- a ~ 115× speedup.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 46 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

22 of 46 references.

References · 22

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  6. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  7. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  8. 2024SOAP: Improving and Stabilizing Shampoo using Adamcited by 192
  9. 2022Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learningcited by 44
  10. 2020Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEscited by 40
  11. 2023An Ensemble Score Filter for Tracking High-Dimensional Nonlinear Dynamical Systemscited by 38
  12. 2021Physics-informed neural networks for the shallow-water equations on the spherecited by 32
10 more
  1. 2024Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Datacited by 22
  2. 2024Derivative-enhanced Deep Operator Networkcited by 19
  3. 2024LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observationscited by 11
  4. 2023Accurate, scalable, and efficient Bayesian optimal experimental design with derivative-informed neural operatorscited by 10
  5. 2023Rapid Flood Inundation Forecast Using Fourier Neural Operatorcited by 9
  6. 2024Sequential infinite-dimensional Bayesian optimal experimental design with derivative-informed latent attention neural operatorcited by 9
  7. 2025Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimationcited by 7
  8. 2026LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamicscited by 4
  9. 2026From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstructioncited by 2
  10. 2026Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Historiescited by 0