Vessel Transit Recovery After Shipping Disruptions

Measure how quickly global shipping lanes return to normal after closures or conflicts. Klarety agents combine SAR vessel counts at choke points with known route baselines to compute recovery velocity, throughput recovery rate, and estimated normalization date. Shippers and insurers receive daily progress reports.

Monitor recovery

Shipping recovery metrics from daily SAR vessel counts

Klarety AI

Recovery timeline forecasts from satellite data

Klarety agents compute throughput recovery rates against pre-disruption baselines and return normalization timeline estimates.

SAR - Sentinel-1

Daily choke-point vessel counting and recovery curves

Agents run daily Sentinel-1 passes over key straits and compute rolling vessel count recovery curves against historical baselines.

GIS Output

Recovery data for logistics GIS dashboards

Export daily throughput metrics and recovery trajectory data for supply chain visibility platform integration.

SAR recovery curve modeling for disrupted shipping lanes

Klarety agents compute weekly SAR vessel counts at disrupted choke points, fit a sigmoid recovery curve to the post-disruption time series, and estimate the date at which throughput returns to 90% of baseline. Output is a recovery curve chart, weekly throughput table, and normalization date estimate with confidence interval.

Klarety AITrack shipping recovery in your route

analysis/shipping_recovery_curve.pyAgent code

python

import eeimport numpy as npfrom scipy.optimize import curve_fit
ee.Initialize()
# Suez Canal / Bitter Lakes choke pointaoi = ee.Geometry.Rectangle([32.3, 29.9, 32.7, 30.3])
def weekly_vessel_count(start, end):    s1 = (ee.ImageCollection('COPERNICUS/S1_GRD')          .filterBounds(aoi)          .filterDate(start, end)          .filter(ee.Filter.eq('instrumentMode', 'IW'))          .select('VV').mean())    count = s1.gt(-10).reduceRegion(        ee.Reducer.sum(), aoi, 100    ).get('VV').getInfo()    return int(count or 0)
# Pre-disruption baseline (weekly avg)baseline = weekly_vessel_count('2025-07-01', '2025-09-30')baseline_wk = baseline / 13.0
# Post-disruption recovery weeksweeks = list(range(1, 13))week_dates = [('2026-01-01','2026-01-07'), ('2026-01-08','2026-01-14'),              ('2026-01-15','2026-01-21'), ('2026-01-22','2026-01-28'),              ('2026-01-29','2026-02-04'), ('2026-02-05','2026-02-11'),              ('2026-02-12','2026-02-18'), ('2026-02-19','2026-02-25'),              ('2026-02-26','2026-03-04'), ('2026-03-05','2026-03-11'),              ('2026-03-12','2026-03-18'), ('2026-03-19','2026-03-25')]
counts = [weekly_vessel_count(s, e) for s, e in week_dates]recovery_pct = [c / baseline_wk * 100 for c in counts]
# Sigmoid recovery fit: R(t) = L / (1 + exp(-k*(t - t0)))def sigmoid(t, L, k, t0):    return L / (1 + np.exp(-k * (t - t0)))
t = np.array(weeks, dtype=float)try:    popt, _ = curve_fit(sigmoid, t, recovery_pct, p0=[100, 0.4, 6], maxfev=5000)    L, k, t0 = popt    t90 = t0 + np.log(9) / k  # 90% recovery point    print(f"Baseline (wk avg): {baseline_wk:.0f} vessels")    print(f"Sigmoid fit: L={L:.1f}%, k={k:.2f}, t0={t0:.1f}")    print(f"Estimated 90% recovery: Week {t90:.1f} ({t90:.0f} weeks post-disruption)")except Exception as e:    print(f"Fit error: {e}")
for wk, pct in zip(weeks, recovery_pct):    print(f"Week {wk:>2}: {pct:5.1f}% of baseline")

output/shipping_recovery_report.mdOutput report