Kouyaté, F.F.KouyatéAminzadeh, MiladMiladAminzadehKossi François GuedjeMadani, KavehKavehMadaniShokri, NimaNimaShokri2025-01-092025-01-092024-12AGU24 Annual Meeting (2024)https://tore.tuhh.de/handle/11420/53095We carried out a research focusing on forecasting water levels in the Bani River in Africa, a significant tributary of the Niger River that is vital for agriculture in Mali, Côte d'Ivoire, and Burkina Faso. Our region confronts issues due to political instability that hampers data collection. To address these challenges, we employed satellite data and machine learning methods. We evaluated two satellite rainfall products, CHIRPS and PERSIANN-CDR, to identify which delivers the most precise information for our area. Subsequently, we implemented machine learning models to predict water level variations, improving our management strategies and resilience against environmental changes. This method not only enhances the precision of water level forecasts but also aids in better resource management in politically unstable areas.enTechnology::624: Civil Engineering, Environmental Engineering::624.1: Structural Engineering::624.15: Geotechnical EngineeringConference Posterhttps://agu.confex.com/agu/agu24/meetingapp.cgi/Paper/1631964Conference Poster