@misc{oai:mie-u.repo.nii.ac.jp:00012933,
 author = {KASSAMBARA, BARRY},
 month = {Mar},
 note = {application/pdf, The Niger Inner Delta (NID), a wetland that was selected as an International Important Wetland under the Ramsar Convention (on February 1st, 2004) still can be considered a hotspot of biodiversity in the Sahel. The Niger River as the main source of water for the NID is also used for urban life and irrigation. Therefore, the sustainable use of water to ensure the environmental flow in the NID is under discussion. Owing to climate change and population increase over the past three decades with a very large expansion of irrigated land upstream, the inhabitants have witnessed that their ecosystem is under threat (Cisse, 2009), and a significant reduction of its resources has occurred. 
 The main objective of this study is to develop different models to forecast efficiently the water-level in the Niger Inner Delta, based on the climate condition and the changing river flow. 
  We evaluate the performance of different models established with empirical (Artificial Neural Network and Regressions) or Conceptual Variable Source Area (Water Balance Method WBM) approaches. The results of evaluation and validation based on determination coefficient (R2), Root Mean Squared Error (RMSE) and Nash-Sutcliffe Efficiency (NSE) show that all the models have good results however the Lavenberg-Marqardt Artificial Neural Network (ANN) with 15 hidden layers has the best fitting for the validation and the Bayesian Regularization ANN with 80 in testing periods. 
 Therefore, although the WBM using Variable Source Area concept doesn’t fit as well as the other models, it has the merit to estimate and forecast the wet area surrounding the water body of the delta and the monthly outflow (Qout) from the NID., GRADUATE SCHOOL OF BIORESOURCES, MIE UNIVERSITY, 110p},
 title = {Hydrological Modelling for the Conservation of the Niger Inner Delta in Mali},
 year = {2019}
}