Abstract

Estimation of Chlorophyll-a Concentration using Refined Neural Network (Case Study: Lake Kasumigaura)

Chlorophyll-a has been became one of clinical in-water constituents to represent water quality. Many researchers have used neural network method to estimate chlorophyll-a concentration in the water body. However, a few number of water samples limits the use of neural network, meaning that those number is insufficient to train the neural network model and makes the result is not reliable. One of famous interpolation method, that is Inverse Distance Weighting (IDW), is utilized in this study to enrich water samples dataset over non-station points. The data from those non-station points would further be used to train the neural network model. After the training, the neural network method was refined by using the water samples over stations such that the accuracy in chlorophyll-a estimation was increased. MERIS images are used in this study. Based on statistical analysis, RMSE value before and after the refinement is decreased from 6,7872 mg m^-3 to 6,5606 mg m^-3.

http://jurnal.mapin.or.id/index.php/jpji/article/view/3