[Paper Review] ALTIS: Automated Loss Triage and Impact Scoring from Sentinel-1 SAR for Property-Level Flood Damage Assessment

Amogh Vinaykumar, Prem Kamasani|arXiv (Cornell University)|Mar 14, 2026

Flood Risk Assessment and Management0 citations

TL;DR

ALTIS is a five-stage pipeline that converts Sentinel-1 SAR data into property-level flood impact scores with confidence estimates, delivering a ranked triage list for claims management within 24–48 hours of a flood peak. It introduces Insurance-Grade Flood Triage (IGFT) and insurance-aligned metrics IRR and TES.

ABSTRACT

Floods are among the costliest natural catastrophes globally, yet the property and casualty insurance industry's post-event response remains heavily reliant on manual field inspection: slow, expensive, and geographically constrained. Satellite Synthetic Aperture Radar (SAR) offers cloud-penetrating, all-weather imaging uniquely suited to rapid post-flood assessment, but existing research evaluates SAR flood detection against academic benchmarks such as IoU and F1-score that do not capture insurance-workflow requirements. We present ALTIS: a five-stage pipeline transforming raw Sentinel-1 GRD and SLC imagery into property-level impact scores within 24-48 hours of flood peak. Unlike prior approaches producing pixel-level maps or binary outputs, ALTIS delivers a ranked, confidence-scored triage list consumable by claims platforms, integrating (i) multi-temporal SAR change detection using dual-polarization VV/VH intensity and InSAR coherence, (ii) physics-informed depth estimation fusing flood extent with high-resolution DEMs, (iii) property-level zonal statistics from parcel footprints, (iv) depth-damage calibration against NFIP claims, and (v) confidence-scored triage ranking. We formally define Insurance-Grade Flood Triage (IGFT) and introduce the Inspection Reduction Rate (IRR) and Triage Efficiency Score (TES). Using Hurricane Harvey (2017) across Harris County, Texas, we present preliminary analysis grounded in validated sub-components suggesting ALTIS is designed to achieve an IRR of approximately 0.52 at 90% recall of high-severity claims, potentially eliminating over half of unnecessary dispatches. By blending SAR flood intelligence with the realities of claims management, ALTIS establishes a methodological baseline for translating earth observation research into measurable insurance outcomes.

Motivation & Objective

• Formally define Insurance-Grade Flood Triage (IGFT) for ranking insured properties by expected damage using SAR imagery.
• Develop insurance-aligned evaluation metrics (IRR and TES) to assess dispatch reduction and high-severity claim recall.
• End-to-end implementation of ALTIS on Hurricane Harvey to provide a rapid, property-level triage baseline for insurers.

Proposed method

• Integrates multi-temporal SAR change detection (VV/VH intensity and InSAR coherence) with a HAND terrain constraint.
• Estimates flood depth through a physics-informed waterline approach by fusing flood extent with high-resolution DEMs and kriging-based depth uncertainty.
• Computes property-level severity via zonal statistics using parcel footprints and NFIP depth-damage curves.
• Produces a confidence-scored triage ranking output suitable for claims management platforms.
• Operates without pixel-level supervised training, GPU needs, or real-time hydrodynamic models, enabling 24–48 hour deployment.

Figure 1: Optical vs. SAR imagery over the Addicks sector, Harvey 2017. (a) Pre-event optical: clear conditions, parcel footprints visible. (b) Co-event optical: 100% cloud cover for five consecutive days. (c) Sentinel-2 multispectral attempt: severe cloud contamination. (d) Sentinel-1 VH SAR (30 Au

Experimental results

Research questions

• RQ1 How can SAR imagery be transformed from pixel-level flood maps into property-level triage rankings aligned with insurance workflows?
• RQ2 Can a depth-aware, property-level scoring system calibrated against NFIP claims reliably prioritize high-severity losses while reducing unnecessary field inspections?
• RQ3 What operational metrics best capture insurance benefits (dispatch reduction and recall) for SAR-based flood triage?
• RQ4 What is the performance of a multi-signal SAR fusion approach (amplitude, coherence, and depth constraints) in urban flood settings for insurance use?
• RQ5 How does the ALTIS pipeline perform in a real-world event (Hurricane Harvey) with 24–48 hour latency?

Key findings

• ALTIS demonstrates a plausible end-to-end pipeline with an estimated Inspections Reduction Rate (IRR) of approximately 0.52 at 90% recall of high-severity claims for Hurricane Harvey in Harris County.
• The pipeline provides property-level severity scores (Estimated Fractional Loss) by combining depth estimates with NFIP depth-damage curves.
• A novel Triage Efficiency Score (TES) is proposed to jointly optimize dispatch reduction, high-severity recall, and false-dispatch penalties.
• Stage-wise validation is grounded in validated sub-components and local flood-domain properties, using publicly available data and tools, with code and scripts released for baseline comparisons.
• The approach targets 24–48 hour post-event triage, leveraging cloud-based SAR processing and avoiding dependency on optical data during floods with cloud cover.

Figure 2: ALTIS five-stage pipeline. Sentinel-1 GRD products enter Stage 1 for preprocessing; the resulting $\sigma^{0}$ rasters and InSAR coherence layers feed Stage 2 change detection; flood extent drives Stage 3 kriging depth estimation; parcel intersection and HAZUS functions produce Stage 4 sev