Water Quality Index from Tiete River

Data from WQI (response variable) and 9 physical, chemical, and biological parameters (independent variables), namely: hydrogen potential (pH), dissolved oxygen (do), biochemical oxygen demand (bod), thermotolerant coliforms (tc), total nitrogen (tn), total phosphorus (tp), total solids (ts), turbidity (turb), temperature (temp) were obtained from reports issued by the Environmental Company of the State of São Paulo (CETESB). Annual report available at the link (https://cetesb.sp.gov.br/aguas-interiores/publicacoes-e-relatorios/). On this website the documents are available only in Portuguese and from 1978. The WQI used presents a range between 0 and 100, divided into ranges of values and by color: very bad (0 and ≤ 19, purple); bad (> 19 and ≤ 36, red); medum (> 36 and ≤ 51, yellow); good (> 51 and ≤ 79, green) and excellent (> 79, blue). Its object of study data obtained from 78 measurement points located on the Tiete River and its tributaries, from 1994 to 2019. The database is part of the doctoral thesis, which addresses the use of machine learning techniques in classifying and predicting water quality indicators. CRediT authorship contribution statement: Mario Elias Carvalho do Nascimento: Conceptualization, Software, Formal analysis, Investigation, Data Curation. Ralpho Rinaldo dos Reis: Supervision, Project administration. For any inquiries, please contact [e-mail]. The .csv will be updated as required to correct issues or to add data from additional surveys. Please check for updated versions periodically. Data description: ugrhi: Water Resources Management Units macro_land_use: Classified according to macro land use agriculture, conservation, industrialization, and industrial measurement_points: Measurement points located on the Tiete River and its tributaries pH: hydrogen potential [ ] do: dissolved oxygen [mg/L] bod: biochemical oxygen demand [mg/L] tc: thermotolerant coliforms [NMP/100ml] tn: total nitrogen [mg/L] tp: total phosphorus [mg/L] ts: total solids [mg/L] turb: turbidity [UNT] temp: temperature [ºC] wqi: Range of water quality index [ ] classification: Water quality classes [very_bad, bad, medium, good, excelent]