Abstract
The use of GIS and machine learning techniques to map sand bars along the Niger River in the Niger Delta, Nigeria, spanning the period from 1974 to 2024. It integrates DEM, Landsat series satellite imagery obtained from the USGS. Rainfall data from 1983 to 2023, sourced from the Center for Hydrometeorology and Remote Sensing, supplements the analysis. Object-Based Image Analysis is employed to identify and map sand bars, while Support Vector Machines automate classification to ensure precision and recall metrics. ArcGIS 10.5 tracks temporal changes, revealing significant morphological shifts influenced by both natural processes and human activities. Statistical analysis of sand bar area indicated varied trends: a mean area decline from 183.66 km² in 1974 to 67.53 km² in 2004, followed by fluctuations and a slight increase to 140.27 km² by 2024. From 1974 to 1984, the sand bar decreased by 35%, indicating a period of erosion, while from 2004 to 2014, there was a surprising increase of 100.55%, followed by a more stable period with a 3.57% increase from 2014 to 2024. Spatial autocorrelation analysis confirmed positive correlations between sand bar characteristics and elevation, reflecting localized influences on sand bar dynamics. Moreover, rainfall patterns exhibited a strong correlation (R² = 0.7576) with sand bar changes, underscoring the role of climatic variability in sediment transport and deposition processes. Grain size analysis reveals that medium to coarse sands dominate sandbar composition, influencing their stability and susceptibility to environmental changes. Comparisons with global trends highlight similarities in sandbar dynamics across riverine environments.