Water　quality　assessment　is　very　important　for　monitoring　water　sources　and　main　canal,　which　is　beneficial　to　offer　strategies　for　the　management　of　water　quality　and　environment.　This　paper　proposes　a　water　quality　assessment　method　based　on　a　sparse　autoencoder　network.　In　the　proposed　approach,　a　representation　model　is　firstly　learned　via　a　sparse　autoencoder　trained　by　unlabeled　water　monitoring　data　acquired　from　DanJiangKou　reservoir,　then　a　softmax　classifier　is　trained　using　a　small　set　of　labeled　classification　data　based　on　the　China　Surface　Water　Environmental　Quality　Standard　(GB3838-2002)　expressed　by　the　sparse　autoencoder.　The　combined　model　is　finally　used　to　evaluate　the　water　quality.　Experimental　results　show　that　the　proposed　method　in　this　paper　is　of　high　robustness　and　accuracy　of　water　quality　assessment,　and　has　a　good　prospect　of　practical　applications.　©　2015　IEEE.