Assis' water quality index maps generation by classical methods and based on artificial intelligence

• Grant number: 14/26025-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2015
• End date: December 31, 2015
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Ramon Juliano Rodrigues
• Grantee: Edson Marcelino Alves
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

The use of geoprocessing techniques can be a useful tool to find solutions for environmental problems as they permit, for example, to map the water quality along rivers. Thus, this project aims to determine the Water Quality Index (WQI) in ten points along two rivers located in Assis-SP and generate a water quality map using Geographic Information System (GIS). The following water quality factors will be analyzed to determine the WQI: dissolved oxygen, fecal coliform, pH, biochemical oxygen demand, total nitrogen, total phosphorus, turbidity, total solids and temperature change. In order to simplify the determination of this index, reduce costs and chemical waste generation, this project also aims the calibration of an Artificial Neural Network (ANN) to determine the WQI value from spectrophotometric water standards. For this purpose, UV-Vis spectral analysis between 190 and 800nm will be performed on each collected sample in order to train the network and obtain a single layer as output, corresponding to the WQI value. The correlation method used will be based on a supervised learning, "Multilayer Perceptron", with a backpropagation learning algorithm.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

ALVES, EDSON MARCELINO; RODRIGUES, RAMON JULIANO; CORREA, CAROLINE DOS SANTOS; FIDEMANN, TIAGO; ROCHA, JOSE CELSO; LEMOS BUZZO, JOSE LEONEL; NETO, PEDRO DE OLIVA; FERNANDEZ NUNEZ, EUTIMIO GUSTAVO. Use of ultraviolet-visible spectrophotometry associated with artificial neural networks as an alternative for determining the water quality index. ENVIRONMENTAL MONITORING AND ASSESSMENT, v. 190, n. 6, JUN 2018. (14/26025-2)