SaeroSense새로센스
  1. Home
  2. Work
  3. Flood depth prediction

Case study · Signals & sensors

Flood depth prediction

A fast, data-driven surrogate for urban flood simulation: statistical features from multi-resolution SWMM outputs and maximum-depth (H_max) rasters, compressed with PCA and modeled with CatBoost, predict flood depth with very low error.

Sector
Urban infrastructure · climate risk
Context
Applied R&D
Service
Signals & sensors
Delivered by
Saerosense founding team

Business result

Planners can explore many more rainfall scenarios, because a trained surrogate predicts flood depth without rerunning the slow physics simulation each time.

Client type

Applied R&D

Where this applies for you

Climate-risk, insurance and urban-planning teams that rely on slow simulations.

Technical result

  • 30 to 120 mmulti-resolution inputSWMM outputs and H_max rasters

The problem

Physics-based urban flood simulations are accurate but slow, which limits how many rainfall scenarios planners can explore. A data-driven surrogate has to reproduce both the depth values and their spatial pattern.

What we built

We summarized rainfall, duration and location features from multi-resolution (30 to 120 m) simulation data, reduced them to 100 principal components and trained CatBoost (1,000 iterations, depth 6). Validation checked both error metrics and whether the predicted spatial distribution matches the simulated H_max.

Workflow

How it works, step by step.

The pipeline in 5 stages, from ingest to validate. Each stage has a clear input, a clear output and a reason to exist.

  1. 01

    Ingest

    Multi-resolution (30 to 120 m) SWMM outputs and H_max rasters.

    • SWMM
    • Rasters
  2. 02

    Engineer

    Statistical summaries plus rainfall, duration and location features.

    • Feature engineering
  3. 03

    Compress

    PCA reduces the features to 100 components.

    • PCA
  4. 04

    Model

    CatBoost regressor: 1,000 iterations, depth 6.

    • CatBoost
  5. 05

    Validate

    80/20 split; error metrics and spatial agreement with H_max.

    • RMSE
    • MAE

Results

What it produced.

Key findings

  • Strong linear correlation between actual and predicted depth values.
  • Predicted spatial distribution matches the simulated Hmax with high fidelity.
  • Consistent performance across all test scenarios.
  • Validated on an 80/20 train/test split.

Stack & techniques

  • CatBoost
  • PCA
  • SWMM
  • Geospatial rasters
  • Python

Delivered by members of the Saerosense founding team. Client names are withheld unless public. References are available on request.

Start a project

Have a similar problem?

Send a few lines about your data and the outcome you want. We reply within 1 business day with an honest read and a proposed scoping plan.

Send us a message contact@saerosense.com Seoul based · available throughout US business hours