Accurately characterizing subsurface lithological heterogeneity in tropical granitic terrains remains challenging because conventional electrical resistivity tomography (ERT) and induced polarization (IP) inversions often smooth abrupt boundaries, obscure weathered interfaces, and underrepresent clay–moisture contrasts. This study develops an integrated geophysical framework for approximating inversion-derived chargeability patterns using depth-referenced ERT–IP collocation, conservative outlier filtering, and stratified sampling to construct a robust dataset representative of residual soils, weathered and fractured granite, and moisture-bearing weak zones. Machine learning and deep learning (ML/DL) methods were applied to capture nonlinear resistivity–IP relationships governing lithological transitions. CatBoost achieved the strongest standalone performance (R 2 = 0.942 train; 0.945 test), marginally surpassing random forest, while the stacked ensemble achieved the highest predictive performance (test R 2 = 0.947). The one-dimensional convolutional neural network with global average pooling performed comparably to the artificial neural network while effectively representing depth-dependent resistivity–IP relationships. All ML/DL models yielded RMSE ≈ 0.76–1.09 msec (< 10%), confirming high predictive fidelity. ML/DL-derived and CatBoost-regressed 2D chargeability models reproduced inversion-defined structures and preserved the spatial expression of clay-rich horizons, fracture-controlled weak zones, and lithological interfaces. The results are relevant to geoengineering assessments, where relatively competent bedrock generally occurs below ~ 30–33 m and may provide favorable conditions for deep foundation development, subject to geotechnical verification. They also provide useful insights for hydrogeological evaluations by identifying weathered/fractured zones extending to ~ 41 m that may represent favorable groundwater targets. K-means clustering analysis (KMCA) further supported lithological discrimination by grouping materials into coherent residual-soil-to-weathered-granite domains. The integrated inversion–ML/DL–KMCA workflow provides a cost-effective and geologically consistent framework for approximating inversion-derived chargeability patterns and supporting subsurface characterization in complex crystalline terrains.
12 November 2026 in Journal of Collective Sciences and Sustainability
Rainfall in the Sudano-Sahelian zone of northeastern Nigeria is confined to a short monsoon season, yet daily relationships between surface meteorological conditions and rainfall occurrence are rarely documented for Maiduguri. This exploratory two-year (2023–2024) diagnostic study examined surface conditions associated with wet days in Maiduguri using daily NASA POWER (MERRA-2-based) estimates of 2-m air temperature, 2-m relative humidity, 10-m wind speed and precipitation for 2023–2024 with a number of samples (n = 731). A wet day was defined as a day with a daily rainfall exceeding 1 mm, as rainfall alone cannot confirm thunder or lightning, whereas wet days were not treated as thunderstorm events. The methods used included descriptive statistics, Spearman and point-biserial correlations adjusted for serial dependence, correlations of depersonalized anomalies, and logistic regression with seasonal harmonics and cross-year validation. In June–September, 94.8% of the total rainfall and 89.4% of the 142 wet days contribute, and the number of wet days increases from 56 in 2023 to 86 in 2024. Relative humidity showed the strongest association with wet-day occurrence (rpb = 0.65; 95% CI: 0.57–0.72), which weakened but persisted after the seasonal cycle was removed (r = 0.28; 95% CI: 0.17–0.38). The negative wind-speed association (rpb = -0.31) was no longer evident after depersonalization, indicating a shared seasonal pattern instead of a direct physical relationship. Moreover, surface variables provided only marginal improvements in out-of-sample discrimination beyond seasonality. The findings describe associations, not causal effects or a validated warning tool, and justify further work combining station, lightning and upper-air observations.