Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility

• URL: http://arxiv.org/abs/2607.25148v1
• Date: Mon, 27 Jul 2026 23:46:25 GMT
• Title: Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility
• Abstract summary: Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions.<n>We develop a physics-informed training framework for CNN-LSTM models that predict urban flood depths at 15 min intervals over a 128x128 spatial grid.
• Score: 4.789111524845274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. We develop a physics-informed training framework for CNN-LSTM models that predict urban flood depths at 15 min intervals over a 128x128 spatial grid. Three differentiable penalty terms are embedded into the loss: (i) a gravity loss penalizing depth increases against the water-surface-elevation gradient, (ii) a continuity loss enforcing local mass conservation with rainfall-adaptive thresholds, and (iii) a topography-aware false-alarm penalty modulated by the topographic wetness index (TWI). We evaluate on the Norfolk, Virginia flood dataset spanning two storm events (August 2017 and September 2022, 300 samples), with all variants trained on identical splits and robustness assessed over repeated random splits and leave-one-storm-out tests. A road-proximal evaluation restricted to a TWI-derived street mask quantifies street-level skill. The physics-constrained model achieves near-zero gravity violations (order 1e-6) and the highest street-channel recall (0.77 +/- 0.09 vs 0.44 +/- 0.10 for the unconstrained baseline), the capability most relevant to traffic routing, and its advantage more than doubles on a held-out storm; a uniform false-alarm variant attains 16% lower mean absolute error but suppresses street recall to 0.25. The TWI-modulated penalty reconciles this trade-off: it improves on the uniform variant on every metric, recovering 60% higher street recall at the lowest MAE among constrained variants and the best street-level F1. These results expose a fundamental tension between aggregate pixel-level error and application-specific physical plausibility, and show that terrain-aware loss modulation offers a principled resolution.

Related papers

• Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning [9.679297769625286]
  Railway engineers need simulation models that predict vehicle responses across operating scenarios that cannot be tested exhaustively.<n>We present a multifidelity railway-bogie response-correction method that treats multibody simulation histories as low-fidelity information and roller-rig measurements as high-fidelity evidence.
  arXiv  Detail & Related papers  (2026-09-10T07:56:53Z)
• DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings [19.819705029025908]
  Pluvial flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States.<n>We present DELUGE, a multimodal deep learning framework for daily pluvial flood damage prediction at 1 km resolution and national scale.
  arXiv  Detail & Related papers  (2026-07-17T15:27:47Z)
• Advanced Flood Prediction with Physics-Guided Deep Learning: Combining UNet, FNO, and SAR/Optical Imagery [0.3186130813218338]
  This work introduces a physics-guided deep learning framework that integrates multi-modal remote sensing and depth-averaged shallow water equations.<n>The proposed hybrid architecture combines a UNet to capture fine-scale spatial details with a Fourier Neural Operator (FNO) to model basin-scale hydraulic interactions.<n>The model achieves an Intersection over Union of 0.82 and an F1 score of 0.90 for flood extent prediction, outperforming UNet-only and FNO-only baselines.
  arXiv  Detail & Related papers  (2026-06-02T19:14:04Z)
• Multi-Quantile Regression for Extreme Precipitation Downscaling [2.2165845825140695]
  Deep super-resolution networks for precipitation downscaling achieve strong bulk skill yet systematically under-predict heavy-tail events that drive flood risk.<n>We demonstrate that the primary obstacle is the loss function, not the data.<n>We resolve this with Q-SRDRN, a multi-quantile super-resolution network trained with pinball loss at tau in 0.50, 0.95, 0.99, 0.999.
  arXiv  Detail & Related papers  (2026-05-12T21:17:26Z)
• FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing [0.0]
  Predictive policing systems that allocate patrol resources based solely on predicted crime risk can unintentionally amplify racial disparities through feedback driven data.<n>We present FASE, Stemporal Event Graph framework, which integrates crime prediction with fairness constrained patrol allocation and a closed loop deployment feedback simulator.<n>We show that allocation level fairness alone do not eliminate feedback induced bias in retraining data, highlighting the need for fairness interventions across the full pipeline.
  arXiv  Detail & Related papers  (2026-04-19T21:22:45Z)
• When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models [54.08784776767683]
  We present Physical-Conditioned World Model Attack (PhysCond-WMA), the first white-box world model attack that perturbs physical-condition channels.<n>PhysCond-WMA induces semantic, logic, or decision-level distortion while preserving perceptual fidelity.
  arXiv  Detail & Related papers  (2026-02-21T07:22:37Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses [68.68514648185828]
  Trajectory prediction is essential for the safety and efficiency of planning in autonomous vehicles.<n>Current models often fail to fully capture complex traffic rules and the complete range of potential vehicle movements.<n>This study introduces three novel loss functions: Offroad Loss, Direction Consistency Error, and Diversity Loss.
  arXiv  Detail & Related papers  (2024-11-29T14:47:08Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Automating global landslide detection with heterogeneous ensemble deep-learning classification [44.99833362998488]
  Landslides threaten infrastructure, including roads, railways, buildings, and human life. Hazard-based spatial planning and early warning systems are cost-effective strategies to reduce the risk to society from landslides. Deep learning models have recently been applied for landside mapping using medium- to high-resolution satellite images as input.
  arXiv  Detail & Related papers  (2023-09-12T10:56:16Z)
• Do We Need Zero Training Loss After Achieving Zero Training Error? [76.44358201918156]
  We propose a direct solution called emphflooding that intentionally prevents further reduction of the training loss when it reaches a reasonably small value. We experimentally show that flooding improves performance and, as a byproduct, induces a double descent curve of the test loss.
  arXiv  Detail & Related papers  (2020-02-20T12:50:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.