Physics-based hydrodynamic models are essential for accurate flood prediction but are computationally expensive, limiting their applicability for real-time forecasting and probabilistic analyses. Conversely, pure machine learning (ML) models offer both computational efficiency and accuracy but often lack interpretability. To address this gap, we propose SGUnet, a physics-informed ML model and a hybrid theory-guided data science approach, for rapid, high-resolution flood mapping. It utilizes a neural network with U-Net architecture and integrates subgrid-based coarse-grid hydrodynamic model predictions as initial estimates, upskilling them to achieve fine-grid model accuracy. Unlike traditional hydrodynamic models, the subgrid method embeds fine-scale topographic details within coarse-grid cells, enhancing both computational efficiency and predictive accuracy. SGUnet processes flood depth raster patches (512 × 512 pixels) and corresponding digital elevation models as inputs. It functions as a deep learning-based corrector, refining flood predictions from numerical simulators. Trained through supervised learning, SGUnet learns to correct deviations in coarse-grid predictions using fine-grid model outputs as target values. The model is evaluated across three large Australian watersheds—Wollombi, Chowilla, and Burnett River—using HEC-RAS flood simulations with subgrid formulation. SGUnet reduces root mean squared error by a factor of 4.5–5.3 compared to coarse-grid models, achieves a critical success index exceeding 0.9 for flood extent mapping, and delivers a 50x speed-up over fine-grid hydrodynamic models. Furthermore, SGUnet outperforms a state-of-the-art ML-based upskilling model in depth and extent predictions. By effectively correcting flood artifacts from coarse-grid models, SGUnet achieves near fine-grid accuracy with significantly reduced computational cost, demonstrating its potential for real-time flood risk assessment.

@en

Infiltration models are crucial components of rainfall-runoff models based on shallow water equations, combined with direct-rainfall for flooding simulations. While the original Horton’s model is frequently used, various modifications have been proposed to deal with its limitations for intermittent rainfall patterns. We evaluate two modifications, from well-known Storm Water Management Model or SWMM and from Diskin and Nazimov, against the original Horton’s model both theoretically and with numerical experiments. We find the formulation from Diskin and Nazimov as most suitable for real-world applications. In this paper, we describe an adaptation of the Diskin and Nazimov infiltration model through a Surface Detention Box model to integrate it into a shallow water equation solver, that accounts for detailed topographic information using a sub-grid approach. The Surface Detention Box model in this paper is generalized to account for sources and sinks other than infiltration. We verify the efficiency of our implementation for a catchment in Australia with intermittent and extreme rainstorms. We also demonstrate the accuracy, efficiency and the precise volume conservation of our method for high-resolution grids and large computational time steps, enabled by the predictor–corrector solver. In conclusion, we present a robust and efficient scheme for practical flood simulations, including various sources and sinks such as rainfall and infiltration. Our approach is a strong foundation for operational flood forecasting with high resolution Digital Terrain Models.@en

Environmental sustainability is a major concern for urban and rural development. Actors and stakeholders need economic, effective and efficient simulations in order to predict and evaluate the impact of development on the environment and the constraints that the environment imposes on development. Numerical simulation models are usually computation expensive and require expert knowledge. We consider the problem of hydrological modelling and simulation. With a training set consisting of pairs of inputs and outputs from an off-the-shelves simulator, We show that a neural network can learn a surrogate model effectively and efficiently and thus can be used as a surrogate simulation model. Moreover, we argue that the neural network model, although trained on some example terrains, is generally capable of simulating terrains of different sizes and spatial characteristics.

@en