Publications
Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia
Groundwater on the Kairouan Plain, Tunisia, exhibits diverse chemical characteristics primarily influenced by water–rock interaction, dolomite dissolution, evaporation, and ion exchange. Analysis revealed three distinct water types: Ca-Mg-SO4, Na-Cl, and mixed Ca-Mg-Cl/SO4, with ions following the order Na+ > Ca2+ > Mg2+ > K+ and SO42− > HCO3− > Cl−. While most groundwater is suitable for agriculture, irrigation water quality indices (IWQIs) indicate high-to-severe restrictions in some areas. Machine learning models, particularly ANN-HyC-9 and XGBoost regression, demonstrated high accuracy in predicting IWQIs, with R² values exceeding 0.823 for testing datasets. These findings provide critical insights for sustainable water resource management.
Monitoring Irrigation Consumption Using High Resolution NDVI Image Time Series: Calibration and Validation in the Kairouan Plain (Tunisia)
A novel approach using high-resolution NDVI image time series significantly improves the monitoring of irrigation consumption, offering unprecedented accuracy for water balance assessments in semi-arid agricultural regions. The study, conducted in Kairouan, Tunisia, leveraged the SAMIR software and FAO-56 dual crop coefficient model to estimate evapotranspiration and irrigation volumes with high precision. By normalizing SPOT5 time series data against a SPOT4 reference, researchers generated NDVI profiles that enabled robust calibration and validation at both plot and perimeter scales. Results demonstrated an average Nash efficiency of 0.57 for modeled versus observed evapotranspiration in barley and wheat plots, while aggregated irrigation volumes closely matched observed values (135 mm vs. 121 mm). This method holds promise for refining water resource management in semi-arid landscapes, though further improvements at finer timescales are needed.
Relationship between soil moisture and vegetation in the Kairouan plain region of Tunisia using low spatial resolution satellite data
A strong correlation exists between soil moisture and vegetation dynamics in the Kairouan plain, Tunisia. Researchers developed a semiempirical model using low-resolution satellite data (1991–2006) to predict normalized difference vegetation index (NDVI) values based on soil moisture profiles from prior months during the rainy season (October–May). Validated against rainfall events and Global Soil Wetness Project data, this approach offers a simple yet effective tool for modeling vegetation in semiarid regions. The study highlights how satellite-derived moisture data can serve as a reliable indicator of vegetation development, advancing our understanding of water-vegetation interactions in arid ecosystems.
You are here:
World Heritage Explorer > World Heritage Research > World Heritage Sites > Kairouan