Neural Network Approach to Modelling Transport System Resilience for Major Cities: Case Studies of Lagos and Kano (Nigeria)

Congestion has become part of everyday urban life, and resilience is very crucial to traffic vulnerability sustainable mobility. This research employed a neural network as an adaptive artificially-intelligent application study the complex domains transport system in Nigerian cities (Kano Lagos). The input criteria train check models for are demographic variables, geospatial data, parameters, infrastructure inventories. training targets were set congestion elements (traffic volume, saturation degree indices), which line with relevant design standards obtained from literature. A multi-layer feed-forward back-propagation model involving input–output curve fitting (nftool) MATLAB R2019b software wizard was used. Three algorithms—including Levenberg–Marquardt (LM), Bayesian Regularization (BR), Scaled Conjugate Gradient (SCG)—were selected simulation. LM converged easily Mean Squared Error (MSE) (2.675 × 10−3) regression coefficient (R) (1.0) city Lagos. Furthermore, algorithm provided better fit overall validation Kano analysis MSE (4.424 10−1) R (1.0). offers modern method simulation discrete prediction.