J.O. Ehiorobo

Flooding along the River Niger remains a persistent hydrological and humanitarian challenge, exacerbated by data scarcity, climate intensification, and rapid land-cover transformation. This study advances a sustainable framework for flood prediction and risk mapping by integrating geospatial technologies with deep learning in data-limited riparian environments. The study focused on the Agenebode–Idah corridor, delineated by a 20 km buffer on either side of the River Niger. The research aimed to design, train, and validate a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN– LSTM) model capable of representing both the spatial complexity and temporal evolution of flood dynamics. The overarching purpose was to enhance anticipatory flood governance and inform climate-resilient development strategies across vulnerable communities of the lower Niger Basin. Methodologically, the study employed a multi-source geospatial architecture integrating CHIRPS rainfall, ERA5 soil moisture and temperature, SRTM topography, Sentinel-1 SAR inundation data, and Landsat-derived land-use/land-cover information. The CNN component extracted geomorphological and hydrological features, including elevation, slope, vegetation, and proximity to rivers, while the LSTM component learned the sequential dependencies of hydroclimatic variables over time. Model calibration and validation employed rigorous statistical and spatial metrics, including ROC–AUC, F1- score, RMSE, and confusion matrix analysis, alongside geospatial overlays between predicted and observed flood masks. The framework simulated both historical flood dynamics (2000–2024) and flood probabilities (2026–2035), allowing for a comprehensive spatiotemporal risk assessment. Results revealed that the hybrid CNN–LSTM achieved high predictive fidelity (ROC– AUC = 0.92; F1 = 0.86; RMSE = 0.081), outperforming baseline machine-learning and hydrodynamic models. Spatial analyses identified chronic flood hotspots in Agenebode, Anegbete, Ifeku Island, Ogurugu, and Idah. Forward projections indicated a 34% spatial expansion of high-risk zones by 2035, primarily across cropland and peri-urban settlements. The study concludes that coupling AI-driven deep learning with geospatial intelligence enhances flood forecasting capacity in data-scarce regions, providing a replicable, operational blueprint for early warning systems, spatial planning, and adaptive water governance in the face of accelerating climate variability.

In this study, the potential of Ikpoba river dam being used as a multipurpose dam was evaluated. Before the evaluation, the flow regime behaviour of the river was modelled and predicted using adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) in MATLAB software. The river daily discharge, temperature and precipitation data sets from 1991 to 1995 were used for the prediction. In applying ANFIS using hybrid algorithm, five different models: model-1, model-2, model-3, model-4 and model-5 were created using 1995 data sets as the target outputs in all the five models. Only discharge data sets for 1994; 1994 and 1993; 1994, 1993 and 1992; 1994, 1993, 1992 and 19991 were used as the input data sets for model-1 to model-4 respectively. Model-5 was created by indexing monthly temperature and precipitation into model-4 to see the effect of climate change on the models. ANN was also applied to the same models as created with ANFIS. In ANN, three training algorithms; Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG) and Bayesian Regularization (BR) were used. Five performance evaluation criteria namely coefficient of correlation (R), coefficient of determination (R2), mean square error (MSE), modelling efficiency (E) and index of agreement (IOA) were used for comparative analysis.The results of both ANFIS and ANN using the five performance evaluation criteria (R, R2, MSE, E and IOA) showed that model-5 (when the effect of climate change was incorporated) performed better than the other four models. The training phase in model-5 of ANFIS showed an over-estimation of 0.043% of the observed target output sets while an over-estimation of 0.044% was observed in the testing phase. The training phase in model-5 of ANN (LM) showed an over-estimation of 0.11% of the observed target output sets while an over-estimation of 0.14% was observed in the testing phase. The training phase in model-5 of ANN (SCG) showed an over-estimation of 0.21% of the observed target output sets while an over-estimation of 0.31% was observed in the testing phase. The training phase in model-5 of ANN (BR) showed an over-estimation of 0.17% of the observed target output sets while an over-estimation of 0.19% was observed in the testing phase. It was therefore concluded that ANFIS performed better than ANN in all the five models and that ANN (LM) performed best followed by ANN (BR) and ANN (SCG) in the ANN models. When the potential of Ikpoba dam being used as a multipurpose dam was evaluated, it was discovered that the dam with ultimate water pumping capacity of 160 x 106 liters/day could also be utilized to produce 5.26MW of power monthly (with discharge of 31.9m3/s) using a hydropower plant. The annual volume of water in the reservoir available for this hydropower scheme is 0.523 x 106m3