371 3.4. Validation of MT-DInSAR-derived deformation with total station monitoring Ground validation of InSAR over TSFs is often constrained by sparse instrumentation and differing sampling frequencies. Here, MT-DInSAR-derived vertical velocities were compared against total station measurements from eight active control points monitored between June 2023 and July 2025. This comparison is used as a consistency check rather than a formal calibration, as total station accuracy may be influenced by monument stability and survey conditions. Figure 3 shows that four points (5, 6, 7, and 9) lie close to the 1:1 line, with RMSE values of 3.06, 6.66, 7.15, and 4.43 mm/year, all within the typical InSAR validation range of 3-10 mm/year (Chen et al., 2021; Cigna et al., 2021). Three of these points are in the West zone, indicating good agreement despite high local variability. Crest points show greater scatter, likely due to active crest raising and maintenance on the area, while Point 4 in the Toe shows poor agreement, possibly because low coherence dominates where true deformation is small. Figure 3 – Comparison of vertical deformation velocities from total station control points and MTDInSAR 3.5. LightGBM model forecast performance Chronological split selection was based on the sensitivity analysis in Table 4. The 70-15-15 split was selected because it gave the lowest test MAE (2.961) and lowest test RMSE (4.533), while maintaining a positive KGE (0.198). The 60-25-15 split achieved the highest KGE (0.385), but with slightly higher test MAE (2.976) and RMSE (4.60). The 65-20-15 split showed similar test errors but weaker generalisation, and the 75-15-10 split performed worst overall, with the highest test errors and a negative KGE (-0.040). Therefore, 70-15-15 was adopted for subsequent zone-specific evaluation. Table 4 – Chronological split sensitivity analysis: mean MAE, RMSE and KGE across zones MAE RSME KGE Training Validation Test Training Validation Test 70-15-15 1.602 1.416 2.961 2.207 1.942 4.533 0.198 75-15-10 1.184 1.064 3.014 1.645 1.422 4.840 -0.040 60-25-15 1.206 1.217 2.976 1.666 1.654 4.601 0.385 65-20-15 0.775 0.683 2.965 1.095 0.989 4.580 0.235 3.4.2 Zone-wise test performance Zone-wise test performance is summarised in Table 5 for models trained with and without meteorological predictors. This comparison was used to assess whether external weather improved one-step deformation forecasts. Overall, the effect of meteorological data was not consistent across sectors. The Toe showed the clearest improvement when meteorological variables were included, with RMSE decreasing from
RkJQdWJsaXNoZXIy MTM0Mzk2