• Bolisetti Durga Charan Naidu
• Mr M Tilak
• Mrs B S R D Lakshmi
• Mrs K V D Padmavathi

A recent study highlights that a significant number of aviation accidents could be avoided if pilots opted for a "go-around" — a decision to abort the landing and attempt it again. To support this critical in-flight decision, researchers have developed a machine learning-based system capable of predicting the likelihood of a hard landing. This system, tested on data from over 58,000 commercial flights, demonstrated high accuracy in identifying potentially unsafe landings. Such predictive technology holds promise for improving flight safety and reducing accident rates within the aviation sector. I propose a cockpit-integrated machine learning solution designed to assist pilots in deciding whether to initiate a go-around based on the forecasted chance of experiencing a hard landing. Our model adopts a hybrid approach, incorporating time-dependent aircraft parameters into a neural network to enhance prediction accuracy.

E-Pilot, Hard Landing Prediction, Soft Landing, Flight Safety, Logistic Regression, Data Preprocessing, TensorFlow

"AN EFFECTIVE E-PILOT SYSTEM TO PREDICT HARD LANDING AND SOFT-LANDING CONDITIONS DURING THE APPROACH PHASE OF COMMERCIAL FLIGHTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.h605-h609, May-2025, Available :http://www.jetir.org/papers/JETIR2505860.pdf

"AN EFFECTIVE E-PILOT SYSTEM TO PREDICT HARD LANDING AND SOFT-LANDING CONDITIONS DURING THE APPROACH PHASE OF COMMERCIAL FLIGHTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. pph605-h609, May-2025, Available at : http://www.jetir.org/papers/JETIR2505860.pdf