Geospatial Feature-Based Path Loss Prediction at 1800 MHz in Covenant University Campus with Tree Ensembles, Kernel-Based Methods, and a Shallow Neural Network

Abstract

This paper investigates within-scene path loss prediction at 1.8 GHz in a smart-campus micro-urban environment using multivariate machine-learning (ML) models. We leverage an open measurement campaign from Covenant University (Nigeria) comprising three routes with per-sample geospatial predictors—longitude, latitude, altitude, elevation, Tx–Rx distance, and clutter height—and train Random Forests (RF), Gradient Boosting (GB), Support Vector Regression (SVR), Gaussian Processes (GP), and a shallow neural network (NN). A unified pipeline with 5-fold cross-validation (CV), seeded reproducibility, and Optuna-driven hyperparameter search is adopted; performance is reported as RMSE/MAE/R2 (mean ± sd). To contextualize feature reliability, we include Pearson correlation heatmaps and Variance Inflation Factors (VIFs), a systematic ablation of predictors, and TreeSHAP beeswarm analyses on held-out splits. We also evaluate spatially aware validation (blocked CV within route and leave-one-route-out checks) to mitigate optimism due to spatial autocorrelation. Results show that multivariate ML consistently outperforms classical empirical formulas (COST-231, ECC-33) in this campus setting, with RF achieving the lowest errors across routes (RMSE ≈ 2.14/2.16/2.95 dB for X/Y/Z, respectively), while GB ranks second and kernel methods (SVR/GP) and the NN trail closely behind. Ablation confirms that distance plus coordinates drive the largest gains, with terrain/clutter providing route-dependent refinements. SHAP analyses align with these findings, highlighting stable, interpretable contributions of geospatial covariates. Spatial CV increases absolute errors moderately but preserves model ranking, supporting the robustness of conclusions. Overall, scenario-aware, multivariate ML yields material accuracy gains for smart-campus planning at 1.8 GHz.