arXiv subjects

Yuya Kawakami

Publications and source records attributed to Yuya Kawakami.

3 recordsLinked to original sources

arXiv2026

DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings

Pluvial (rainfall-driven) flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States and is harder to predict than its riverine and coastal counterparts, with existing approaches limited to coarse resolution, regional domains, or computationally intensive process-based models unsuitable for daily continental-scale use. We present DELUGE, a multimodal deep learning framework for daily pluvial flood damage prediction at ~1 km resolution and national scale, trained on spatially and temporally corrected NFIP claims (2017-2022) and structured around the hazard, exposure, and vulnerability components of disaster risk. Rather than blanket coverage of the Conterminous United States (CONUS), we model the top 100 highest-claim 75 km cells, distributed nationwide and accounting for ~81% of total pluvial flood claims. Our architectural novelty is a pair of parametric modules in the hydrometeorology branch, a Value Modulator and a Temporal Modulator, conditioned on terrain descriptors and AlphaEarth foundation-model embeddings, that expose directly inspectable hydrological response parameters and provide architecture-level interpretability-by-design. Under a spatial block holdout, DELUGE outperforms tuned Random Forest, XGBoost, and LightGBM baselines by 9% to 30% on a dollar-weighted area under the precision-recall curve (PR-AUC), a metric that emphasizes the rare, high-cost claims of greatest operational interest. Beyond DELUGE, we argue this interpretable conditioning scheme is a transferable pattern for integrating foundation-model embeddings into other geospatial prediction tasks.

cs.LG↗

arXiv2025

ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasets

Ensemble datasets are ever more prevalent in various scientific domains. In climate science, ensemble datasets are used to capture variability in projections under plausible future conditions including greenhouse and aerosol emissions. Each ensemble model run produces projections that are fundamentally similar yet meaningfully distinct. Understanding this variability among ensemble model runs and analyzing its magnitude and patterns is a vital task for climate scientists. In this paper, we present ClimateSOM, a visual analysis workflow that leverages a self-organizing map (SOM) and Large Language Models (LLMs) to support interactive exploration and interpretation of climate ensemble datasets. The workflow abstracts climate ensemble model runs - spatiotemporal time series - into a distribution over a 2D space that captures the variability among the ensemble model runs using a SOM. LLMs are integrated to assist in sensemaking of this SOM-defined 2D space, the basis for the visual analysis tasks. In all, ClimateSOM enables users to explore the variability among ensemble model runs, identify patterns, compare and cluster the ensemble model runs. To demonstrate the utility of ClimateSOM, we apply the workflow to an ensemble dataset of precipitation projections over California and the Northwestern United States. Furthermore, we conduct a short evaluation of our LLM integration, and conduct an expert review of the visual workflow and the insights from the case studies with six domain experts to evaluate our approach and its utility.

cs.HC↗

arXiv2024

HexTiles and Semantic Icons for MAUP-Aware Multivariate Geospatial Visualizations

We introduce HexTiles, a domain-agnostic hexagonal-tiling based visual encoding design for multivariate geospatial data. Multivariate geospatial data have presented a challenge due to the graph schema associated with geospatial maps, on which most geospatial data is presented. With HexTiles, we design a multivariate geospatial visualization design that leverages semantic icons to (1) simplify the process of interpreting interactions between multivariate geospatial data, and (2) put the visualization designer in the driver's seat to guide user attention to specific variables and interactions. Additionally with HexTiles, we attempt to explicitly mitigate effects of the Modifiable Areal Unit Problem (MAUP) for interpreting geospatial data, by proposing a confidence encoding for each of the information channels in HexTiles. We calculate weighted variances of the variables in each HexTile to provide a confidence value for each tile, which can be used to interpret the variability of the data within the corresponding geospatial area, an information that can be lost in geospatial visualizations. To validate our approach, we gather quantitative and qualitative feedback from a user study and document domain expert feedback from ecologists and hydrologists experienced in designing geospatial visualizations.

cs.HC↗