Development of Remote Sensing Based Models for Surface Water Quality

The objectives of this paper were to develop, evaluate, and apply the remote sensing based models for Canadian Water Quality Index (CWQI) and turbidity for the Bow River of Alberta. We used 31 scenes of Landsat-5 TM satellite data to establish the relationship between the planetary reflectance and the monthly ground measured data for the period of 5 years (i. e. 2006-2010). The four spectral bands (i. e. blue, green, red, and near infrared) were used to obtain the most suitable models from 26 different band combinations. The co-efficients of determination on the basis of red band were 0.91 for the CWQI model and 0.82 for the turbidity model. The best-fit models were validated with ground measured data and found that: 72% of the data showed 100% matching for the CWQI model and 83% of the data for the turbidity model. The Landsat-5 TM based CWQI and turbidity models were applied on all the scenes to obtain five CWQI classes (i. e. excellent, good, fair, marginal and poor), and six classes of turbidity (i. e. 0-10 NTU, 10-20 NTU, 20-30 NTU, 30-40 NTU, 40-50 NTU, > 50 NTU). On the basis of percentages obtained for CWQI and turbidity classes, the ranks of years in terms of water quality from best to worst were: 2009, 2006, 2008, 2010, and 2007 respectively. The variation of river water quality in different years of interest was associated with the climatic changes. The most deteriorated water quality noted in two natural sub-regions included mixed grass and dry mixed grass, which could be related to irrigation-based farming.