Heteroscedastic Neural Networks for Path Loss Prediction with Link-Specific Uncertainty
–arXiv.org Artificial Intelligence
Traditional and modern machine learning-based path loss models typically assume a constant prediction variance. We propose a neural network that jointly predicts the mean and link-specific variance by minimizing a Gaussian negative log-likelihood, enabling heteroscedastic uncertainty estimates. We compare shared, partially shared, and independent-parameter architectures using accuracy, calibration, and sharpness metrics on blind test sets from large public RF drive-test datasets. The shared-parameter architecture performs best, achieving an RMSE of 7.4 dB, 95.1 percent coverage for 95 percent prediction intervals, and a mean interval width of 29.6 dB. These uncertainty estimates further support link-specific coverage margins, improve RF planning and interference analyses, and provide effective self-diagnostics of model weaknesses.
arXiv.org Artificial Intelligence
Dec-1-2025
- Country:
- Europe
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- France (0.04)
- United Kingdom > Wales
- Merthyr Tydfil (0.04)
- Belgium > Brussels-Capital Region
- North America > Canada (0.05)
- Europe
- Genre:
- Research Report (1.00)
- Industry:
- Government (0.47)
- Technology: