EUVIMEDEUVIMED entdecken
Crossref

Change Detection in River Point Bars Using Multimodal Remote Sensing Data and Machine Learning

Journal of Superintelligence and Computing · 24.01.2026

DOI: 10.66967/jsc.2026.v2i101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Superintelligence and Computing, online erschienen am 24.01.2026. Die Arbeit nennt 55 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the temporal evolution and geometric variability of point bars along the Nun River in Kolokuma/Opokuma Local Government Area, Bayelsa State, Nigeria, using remote sensing, machine learning, and geospatial techniques over a 20-year period (2003–2023). Multi-temporal Landsat imagery, rainfall records, and sediment data were integrated to quantify morphometric changes and assess their controlling factors. Object-Based Image Analysis (OBIA) and Support Vector Machine (SVM) classification were applied to delineate and characterise point bars, while geometric parameters (length, area, width, and perimeter) and shape indices (aspect ratio, circularity, compactness, and form factor) were computed to evaluate morphological trends. Results indicate significant spatio-temporal variability, with mean point bar length increasing from 1.32 km in 2003 to 3.42 km in 2013 before decreasing to 2.36 km in 2023. The mean surface area expanded from 0.0758 km² to 0.2555 km² and subsequently stabilised at 0.1560 km². Regression analysis revealed a strong rainfall–morphology relationship (R² = 0.9963), indicating an average increase of 273.7 m² in point bar area per millimetre of rainfall. Sedimentological analyses showed predominantly medium- to fine-grained textures, reflecting dynamic depositional conditions. The results demonstrate that hydroclimatic variability, sediment supply, and anthropogenic modifications are primary drivers of morphodynamic change. This research highlights the effectiveness of integrating remote sensing and machine learning for fluvial geomorphic analysis and provides a quantitative basis for understanding sedimentary processes and river evolution in tropical deltaic environments.

Zitieren

APA

(2026). Change Detection in River Point Bars Using Multimodal Remote Sensing Data and Machine Learning. Journal of Superintelligence and Computing. https://doi.org/10.66967/jsc.2026.v2i101

Vancouver

Change Detection in River Point Bars Using Multimodal Remote Sensing Data and Machine Learning. Journal of Superintelligence and Computing. 2026. doi:10.66967/jsc.2026.v2i101

BibTeX
@article{euvimed2026,
  title = {Change Detection in River Point Bars Using Multimodal Remote Sensing Data and Machine Learning},
  journal = {Journal of Superintelligence and Computing},
  year = {2026},
  doi = {10.66967/jsc.2026.v2i101}
}
Kostenlos starten →