Abstract
Abstract. Water salinity is a complex issue in coastal and estuarine areas. Currently, remote sensing techniques have been widely used to monitor water quality changes, ranging from river to oceans. The salinity of Karun River has been increasing due to some critical factors, therefore, This study aimed at building regression models to ascertain the water salinity through the relationship between the reflectance of the Landsat-8 OLI and In situ measurements. A total of 102 observed samples were divided into 70% training and 30% test from June 2013 to July 2018 along the Karun River. Spectral signature analysis showed that band 1 - Coastal/Aerosol (0.433–0.453 μm), band 2 - Blue (0.450–0.515 μm) and band 3 - Green (0.525–0.600 μm) are sensitive to salinity . Furthermore, to have a comprehensive investigation, the Support Vector Regression (SVR) method was applied. The outcomes related to the quality of the SVR depend on several factors e.g. proper setting of the SVR meta-parameters, therefore, to deal with this issue Genetic Algorithm (GA) was applied. The SVR model resulted in values of R2 and RMSE for test data which are respectively obtained to be 0.7 and 390 μs cm−1. Eventually, Karun water salinity maps were prepared by SVR method to demonstrate the Karun water salinity on 1 February 2015 and 5 September 2018.
Highlights
The Karun River is the largest river in Iran which is located in the south west of Iran between longitudes 48° 15 ́ and 52° 15 ́east, latitude 30° 17 ́ and 33° 49 ́north (Keshavarzi et al, 2015)
Spectral signature analysis proved that bands 1, 2 and 3 are the best for modeling water salinity
The Genetic Algorithm (GA) is used to determine the Support Vector Regression (SVR) meta-parameters including the loss function Ɛ, the error penalty factor C and σ parameters, which are obtained to be1 × 10−9, 1099 and 0.96, respectively
Summary
The Karun River is the largest river in Iran (approximately 67,500 km2) which is located in the south west of Iran between longitudes 48° 15 ́ and 52° 15 ́east , latitude 30° 17 ́ and 33° 49 ́north (Keshavarzi et al, 2015). Karun River supplies water demands of 16 cities and sink into the Persian Gulf (Naddafi et al, 2007), Figure 1 shows the location of the case study. Karun River is polluted because of adverse climate condition and regional physiography, industrial sources, domestic and urban sewerage, irrigation of agricultural land, fish hatchery, hospital sewage and high tide level of Persian Gulf (Naddafi et al, 2007). Landsat 8 Operational Land Imager (OLI) data was used to retrieve the water salinity map for the case of Karun River since it is free, but it has an acceptable spatial, temporal and spectral resolution. Previous attempts at salinity modeling by OLI have implemented different band combinations, e.g. OLI bands 2, 3, 4, and 7 (Nguyen et al, 2018).Recently, many authors provided a water salinity model, which is calculated using various regression models, e.g. Geographically Weighted Regression (GWR) technique (Xie et al, 2013), Spatially Weighted Optimization Model (SWOM) technique (Khadim et al, 2017) and Multiple Linear Regression (MLR), Decision Trees (DT) and Random Forest (RF) techniques (Nguyen et al, 2018)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
