The distribution of treated water over a water distribution system faces di erentrnlosses. In these distribution systems, a signi cant percentage of water is lost duernto leakages. There are plenty of researches that were proposed to tackle this waterrnresource wastage. Most of them, however, focus on large bursts and single leakagerndetection and localization.rnThis thesis proposed a leak detection and localization approach that uses hydraulicrnmodeling and classi cation approaches for detection, and a statistical approach forrnlocalization. The general term used in identifying and locating leaks is LeakagernDetection and Localization. The detection system aims at detecting small leakagesrn(i.e., below 5% of the total supply). The localization phase of this thesis also aimsrnat localizing multiple leakages.rnThe proposed approach is applied on Hanoi water network benchmark by doingrndi erent experiments. A realistic dataset is produced based on a benchmark datasetrnprocedure (i.e., LeakDB). The detection and localization results under well-knownrncalibrated hydraulic conditions are almost perfect (i.e., 100% for detection and 90rnfor localization). The introduction of demand and noise uncertainty, however, a ectsrnthe accuracy of the detection of small leakages. The localization methodology hasrnshown e ectiveness in locating two and three leaks that are presented simultaneouslyrnin 9 of 20 cases on average accurately, and 11 of 20 cases at least one of them.