AI

Robust Ranking of Port Impacts from Impending Tropical Cyclones: A Two-Stage Recommendation System

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 06/11/2026, 05:03:25 UTC.

Briefings

A two-stage recommendation system using AIS data for 37 Gulf of Mexico ports and 31 tropical cyclones identified Wide & Deep Learning as the most accurate model for ranking port impacts. The system selects candidate ports by proximity to landfall and ranks them by estimated impact days, achieving 85.5% agreement with observed rankings for Hurricane Nicole and 55.5% for Hurricane Ian. This framework helps authorities prioritize inspections and resource allocation during impending cyclones.

Key points

• The study uses a two-stage framework to select candidate ports by proximity to expected landfall, then ranks them by estimated impact days using AIS-derived data.
• Wide & Deep Learning model achieved the highest ranking agreement with observed port rankings, exceeding distance-based baselines by 85.5% for Hurricane Nicole and 55.5% for Hurricane Ian.

Context

This research addresses the challenge of predicting port disruptions during tropical cyclones by leveraging AIS data and machine learning to rank affected ports. The Gulf of Mexico region serves as the study area for the 37 ports and 31 cyclones analyzed.

Limitations

The study relies on AIS data for 37 ports and 31 TCs in the Gulf of Mexico region. Results are limited to the specific study period and may not generalize to other regions or future events without additional validation.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 06/11/2026, 05:51:04 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeiao3v5tulwxuivpjfga7l3oa5teqfkgiaq6xrq75srpzpanekzsta