SuryaThejas-07

SuryaThejas-07 / Optimization_of_Airway_Scheduling

Public

AI-powered airport runway scheduler using Graph Neural Networks on real ADS-B data. Detects takeoff/landing events, enforces wake-turbulence separation, and benchmarks against FCFS, GA & MILP baselines with delay, throughput & safety metrics. Built with PyTorch & Streamlit.

19
0
100% credibility
Found Feb 28, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A research project that optimizes airport runway scheduling for aircraft arrivals and departures using real-world flight tracking data, providing visualizations and comparisons to traditional methods.

How It Works

1
🛫 Discover the scheduler

You stumble upon this clever tool for making airports run smoother by better planning plane landings and takeoffs.

2
💻 Get it ready

Download the files to your computer and follow easy steps to set everything up so it's good to go.

3
📊 Add plane tracking data

Pick a file with real airplane positions and times, like from public flight trackers, and tell the tool where the airport is.

4
🚀 Start the optimization

Hit go, and watch it smartly figure out the best order for planes on multiple runways while keeping everyone safe.

5
📈 See the dashboard

A friendly web page pops up filled with colorful charts, timelines, and maps showing what's happening.

6
🔍 Compare and explore

Play around with views of delays, safety gaps, and how different planning methods stack up.

✅ Enjoy optimized plans

You get clear schedules that cut wait times by up to 14% with perfect safety, ready to study or share.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Optimization_of_Airway_Scheduling?

This Python project builds an AI-powered airport runway scheduler that processes real ADS-B flight data to detect takeoffs and landings, then generates safe schedules enforcing wake-turbulence separation rules. Run a CLI command like `python -m agno_runway.main` on your CSV data, tweak airport coords or runway count, and get optimized schedules plus a Streamlit dashboard with Gantt charts, delay histograms, and throughput metrics. It benchmarks against FCFS, genetic algorithms, and MILP baselines, showing 14% less makespan on real datasets.

Why is it gaining traction?

It delivers instant value with a full pipeline—data ingestion, event detection, neural scoring, and multi-runway assignment—in under 100ms for 200+ flights, plus 10+ interactive visualizations for analysis. Developers dig the zero-setup GPU support via PyTorch and headless mode for batch benchmarking, beating naive baselines on delay, throughput, and 100% safety compliance. The hook: plug in OpenSky data and see throughput jump 16% without touching code.

Who should use this?

Aviation ML researchers prototyping AI-powered airport tools, air traffic sim builders needing quick baselines, or ops engineers at busy hubs like Dubai terminal testing against FCFS. Ideal for grad students in transportation AI or devs exploring ADS-B for scheduling apps.

Verdict

Grab it for research or proofs-of-concept—solid docs, CLI, and dashboard make it runnable today despite 16 stars and 1.0% credibility score signaling early-stage maturity. Train the model on custom data next; lacks tests but shines for rapid iteration.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.