Traditional forecasting models for bridge conditions, such as ARIMA and Markov chains, often fail to adequately capture nonlinear and dynamic relationships among critical variables like age, traffic patterns, and environmental factors, leading to suboptimal maintenance decisions, increased long-term maintenance costs, and heightened safety risks. This study addresses these limitations by developing recurrent neural network (RNN) models utilizing Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures with a TimeDistributed output layer. This novel approach enables accurate forecasting of the Bridge Health Index (BHI) and condition ratings for key components—deck, superstructure, and substructure—while effectively modeling temporal dependencies. Applied to bridge data from Georgia, USA, the regression models (BHI) achieved R² values exceeding 0.84, while the classification models (components condition ratings) demonstrated accuracy between 84.78% and 87.54%. By modeling complex temporal trends in bridge deterioration, our method processes time-dependent data from multiple bridges simultaneously, revealing intricate relationships that influence bridge performance within a state’s inventory. These results provide actionable insights for maintenance planning, optimized resource allocation, and reduced risks of unexpected failures. This research establishes a robust framework for bridge performance prediction, ensuring improved infrastructure safety and resilience amid aging assets and constrained maintenance budgets.

This study investigates the aquifer properties of the Lokoja Formation in the southern Bida Basin using grain-size analysis and empirical estimation methods. Although groundwater is the primary water source in the region, previous studies have focused mainly on lithostratigraphy and depositional settings, leaving a gap in quantitative hydrogeological characterization. This work provides a detailed grain-size-based estimation of porosity and hydraulic conductivity for the Lokoja Formation, offering a cost-effective alternative where pumping test data is limited. Twelve sandstone samples were analyzed to determine grain-size distribution, sorting, and gradation, and the Vukovic and Soro model was applied to estimate hydraulic properties. Porosity ranges from 28% to 43%, while hydraulic conductivity spans 0.59–11.60 m day ⁻¹ (mean = 4.45 m day ⁻¹ ), indicating moderate to high permeability. Effective grain size (d ₁₀ ) shows a very strong positive correlation with K (R ² = 0.944), confirming it as the primary control on aquifer performance. These results demonstrate that the Lokoja Formation contains productive groundwater zones, particularly in coarser, better-graded intervals, but spatial heterogeneity necessitates site-specific evaluation. The findings fill a critical data gap in regional hydrogeology and provide practical guidance for borehole siting and sustainable groundwater management.