Predictive Modeling for Safe Navigation of UAVs Near High Voltage Transmission Lines

High Voltage Transmission (Tx) line inspection using Unmanned Aerial Vehicles (UAVs) is rapidly increasing. Tx lines generate high Electric (E) and Magnetic (H) fields, leading to Electromagnetic Interference (EMI) in UAV sensors. This paper focuses on predicting distance between Tx line and UAV during surveillance operations to navigate and operate UAVs drones safely. Various machine learning (ML) models such as Linear Regression, Random Forest Regression, Support Vector Regression, Decision Tree Regression, Gradient Boosting Regression, Multi Layer Perceptron Regression, and K-Nearest Neighbors Regression are deployed to forecast the distance based on historical data. The study uses input features such as E-field, H-field, and Line Voltage rating, and the 3D distance between the Tx line and the UAV as target variable. Decision Tree Regression (DTR) model yielded the lowest Root Mean Square Error (RMSE) of 7.573 and Mean Absolute Error (MAE) of 4.026 with a runtime of 0.998 ms.