Hybrid Deep Learning Architectures for Multi-Horizon Precipitation Forecasting in Mountainous Regions: Systematic Comparison of Component-Combination Models in the Colombian Andes

Forecasting monthly precipitation in mountainous terrain poses challenges that push conventional deep learning approaches to their limits: convective processes operate locally while orographic effects span entire drainage basins. We compare three architecture families on precipitation prediction across the Colombian Andes: ConvLSTM (convolutional recurrent), FNO-ConvLSTM (spectral–temporal), and GNN-TAT (graph attention LSTM). Using CHIRPS v2.0 and SRTM topography for Boyacá department (61 × 65 grid, 3965 nodes), we evaluate 39 configurations across feature bundles (BASIC, KCE elevation clusters, and PAFC autocorrelation lags) and horizons from 1 to 12 months. GNN-TAT matches ConvLSTM accuracy (R2: 0.628 vs. 0.642; RMSE: 82.29 vs. 79.40 mm) with 95% fewer parameters (∼98K vs. 2.1M). Across configurations, GNN-TAT produces a lower mean RMSE (92.12 vs. 112.02 mm; p=0.015) and a 74.7% lower variance. The explicit graph structure, with edges weighted by elevation similarity, appears to reduce sensitivity to hyperparameter choices. Pure FNO struggles with precipitation’s spatial discontinuities (R2=0.206), though adding a ConvLSTM decoder recovers much of the lost skill (R2=0.582). Elevation clustering improves GNN-TAT significantly (p=0.036) but not ConvLSTM, suggesting that feature design should match the spatial encoding paradigm. ConvLSTM achieves peak accuracy on local patterns; GNN-TAT provides robust predictions with interpretable spatial reasoning. These complementary strengths motivate stacking ensembles that combine grid-based and graph-based representations.