Shipping Disruption Economic Impact During Geopolitical Events

Quantify the commodity market cost when conflicts reshape maritime traffic. Klarety fuses Sentinel-1 SAR with AIS-derived transit corridors to detect route deviations, queue buildups, and throughput losses within hours of an event. One prompt returns a time-series disruption report — the kind of analysis that takes a GIS team days.

Model your scenario

Geopolitical shipping disruption quantified from orbit

Klarety AI

Full disruption reports from one prompt

Klarety agents fuse SAR and AIS data and return economic cost estimates without any GIS setup.

SAR + AIS

Route deviation and throughput loss detection

Agents compute traffic flow deltas by comparing SAR vessel counts against pre-event AIS corridor baselines.

GIS Output

Deviation vectors for spatial trade analysts

Outputs route deviation polygons and flow delta vectors compatible with maritime GIS dashboards and trade route datasets.

SAR-based shipping disruption economic model

Klarety agents compare pre-event SAR vessel throughput baselines against real-time Sentinel-1 counts across affected corridors, compute daily tonnage loss estimates, and model extended voyage cost from route deviations. Output includes a time-series chart and economic cost table per corridor. Try it at klarety.ai.

Klarety AIModel shipping disruption for your scenario

analysis/disruption_economic_model.pyAgent code

python

import eeimport pandas as pdimport numpy as np
ee.Initialize()
# Red Sea / Bab el-Mandeb AOIaoi = ee.Geometry.Rectangle([42.5, 11.5, 44.5, 13.5])
def get_vessel_count(start, end):    """Count SAR vessel detections for a given period."""    s1 = (ee.ImageCollection('COPERNICUS/S1_GRD')          .filterBounds(aoi)          .filterDate(start, end)          .filter(ee.Filter.eq('instrumentMode', 'IW'))          .select('VV')          .mean())    vessel_mask = s1.gt(-10)    count = vessel_mask.reduceRegion(        reducer=ee.Reducer.sum(),        geometry=aoi, scale=100    ).get('VV').getInfo()    return int(count) if count else 0
# Baseline (pre-event) vs disruption periodbaseline_count = get_vessel_count('2025-10-01', '2025-12-31')disruption_count = get_vessel_count('2026-01-01', '2026-03-31')
# Throughput deltadelta_pct = (disruption_count - baseline_count) / baseline_count * 100
# Economic model: avg vessel = 50k DWT, avg freight $25/DWTavg_vessel_dw_tons = 50000freight_rate_usd_per_ton = 25daily_vessels_lost = (baseline_count - disruption_count) / 90
daily_revenue_loss = daily_vessels_lost * avg_vessel_dw_tons * freight_rate_usd_per_tonquarterly_loss = daily_revenue_loss * 90
print(f"Baseline vessel count (Q4 2025): {baseline_count}")print(f"Disruption period count (Q1 2026): {disruption_count}")print(f"Traffic delta: {delta_pct:.1f}%")print(f"Est. daily revenue loss: ${daily_revenue_loss:,.0f}")print(f"Est. quarterly economic impact: ${quarterly_loss/1e9:.2f}B")

output/disruption_impact_report.mdOutput report