WSEAS Transactions on Environment and Development
Print ISSN: 1790-5079, E-ISSN: 2224-3496
Volume 16, 2020
Prediction of some physico-chemical parameters of water in Alton Reservoir, Suffolk, England
Authors: , , , ,
Abstract: Predict water quality variables such as Chlorophyll-a (CHL), Algae, Turbidity and Total Suspended Solids (TSS) are important for the analysis of freshwater ecosystems, that are significant not only for human populations but also essential for plant and animal diversity. However, monitoring all these variables from space is a very challenging task, which becomes particularly difficult when dealing with cyanobacteria blooms, because in high concentrations, they form scum on the water surface, which is a concern for public health due to the production of toxins. This article describes empirical algorithms to estimate these variables using LandSat-8 and Sentinel-2 images, multi-spectral instrument data, the Landsat spatial resolution (30 m) and imagery from the Sentinel-2 sensor, with a resampled 10 m spatial resolution can be used for environmental monitoring. These images, analyzed by Wavelets Neural Networks can be very useful to estimate physico-chemical and biological parameters of water. This approach is applied in Alton water reservoir, Suffolk, UK using spatial and temporal scales. The Alton Reservoir is the largest in Suffolk, with a perimeter of over 8 miles (13 km). This article presents techniques based on wavelets neural networks and fuzzy neural networks, namely the radial basis function, the adaptive neuro-fuzzy inference system and Least Square Estimat, which are well suited to predict data sequences stemming from real-world applications techniques. The prediction behavior shows good forecasts as (NMSE = 0.00004; MARE = 0.00078, MSE =0.00013) for test data, results showed that the predicted values have good accurate. This article contributes to improving efficiency to monitor water quality parameters and confirm the reliability and accuracy of the approaches proposed for monitoring water reservoirs.
Search Articles
Keywords: Wavelet transform, water reservoir, time series analysis, chemico physical parameters, deep learning, remote sensing.
Pages: 119-131
DOI: 10.37394/232015.2020.16.12