HOTA: Hierarchical Overlap-Tiling Aggregation for Large-Area 3D Flood Mapping

2025-07-10

AI Summary

Existing flood monitoring products struggle to simultaneously achieve wide-area coverage and high spatial resolution, while commonly lacking water depth information. This paper proposes HOTA, a multi-scale inference framework that integrates SegFormer-based semantic segmentation, multispectral Sentinel-2 imagery, digital elevation model (DEM) differencing, and a hierarchical overlapping tiling aggregation strategy—enabling, for the first time, plug-and-play 3D flood mapping without retraining. Innovatively, we introduce a dual-constraint water depth estimation algorithm enforcing zero-depth boundaries and volumetric conservation, ensuring both local detail fidelity and global consistency at kilometer-scale extents. Evaluated on the Kempsey flood event in Australia, HOTA achieves an IoU of 84% for flood extent (11 percentage points higher than U-Net) and an average absolute error of <0.5 m at water depth boundaries—significantly enhancing both disaster response timeliness and mapping accuracy.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Floods are among the most frequent natural hazards and cause significant social and economic damage. Timely, large-scale information on flood extent and depth is essential for disaster response; however, existing products often trade spatial detail for coverage or ignore flood depth altogether. To bridge this gap, this work presents HOTA: Hierarchical Overlap-Tiling Aggregation, a plug-and-play, multi-scale inference strategy. When combined with SegFormer and a dual-constraint depth estimation module, this approach forms a complete 3D flood-mapping pipeline. HOTA applies overlapping tiles of different sizes to multispectral Sentinel-2 images only during inference, enabling the SegFormer model to capture both local features and kilometre-scale inundation without changing the network weights or retraining. The subsequent depth module is based on a digital elevation model (DEM) differencing method, which refines the 2D mask and estimates flood depth by enforcing (i) zero depth along the flood boundary and (ii) near-constant flood volume with respect to the DEM. A case study on the March 2021 Kempsey (Australia) flood shows that HOTA, when coupled with SegFormer, improves IoU from 73% (U-Net baseline) to 84%. The resulting 3D surface achieves a mean absolute boundary error of less than 0.5 m. These results demonstrate that HOTA can produce accurate, large-area 3D flood maps suitable for rapid disaster response.

Problem

• Large-area 3D flood mapping lacks spatial detail and depth accuracy
• Existing methods trade coverage for resolution or ignore flood depth
• Need for timely, high-resolution flood extent and depth data for disaster response

Innovation

• Hierarchical Overlap-Tiling Aggregation for multi-scale inference
• SegFormer with dual-constraint depth estimation module
• DEM differencing method for refining flood depth