Performance of different modeling techniques in testing the impact of environmental variables on eel landing in Ichkeul Lake, a RAMSAR Wetland and UNESCO biosphere reserve

Advanced modeling techniques, including Random Forest (RF) and Cubist model (CB), were used to assess the relationship between environmental factors and European eels (Anguilla anguilla) abundance and to provide insights into the lake's ecological status while considering climate change and anthropogenic influences. A comprehensive dataset, attained through extensive environmental and biological monitoring for the period 2010–2020, was employed. The performance of the models is carried out using key metrics including the root mean square error (RMSE), coefficient of determination (R²), and mean estimation error (MAE). In addition, a sensitivity analysis was conducted to ascertain the relative significance of the thirteen input variables in shaping the predictions of the models. The precision of the CB and RF models in predicting eel landings surpassed that of Multiple Regression. In the training dataset, the CB model achieved R2=0.55, RMSE=7.68 tons, and MSE=6.20 tons, and the RF model...