ABSTRACT
Abstract Adequate availability of data directly influences the quality of hydrological studies. In this sense, procedures for filling gaps of observations are often applied in order to improve the length of hydrological series. One technique that can be used is the Artificial Neural Network (ANN), which process information from input data creating an output. This study aims to evaluate the application of ANN to fill missing data from monthly average streamflow series at Rio do Carmo Basin in the state of Minas Gerais, Brazil. A 26-years series (from 1989 to 2012) was used for ANN modelling while the two proceeding years, 2013 and 2014, were used to simulate failures pursuant to evaluating the performance of the ANN. The ANN construction was performed by the software WEKA that uses the multilayer perceptron model with sigmoidal activation functions. Four types of ANN were generated: five attributes and two (MLP1) or five (MLP2) neurons; and with three attributes and one (MLP3) or three (MLP4) neurons. The best-fit model to ANN was the MLP1, verified by Pearson correlation coefficients (0.9824), and coefficient of determination r² (0.9646). The model used five attributes, four input data (year, month, streamflow data from Acaiaca and Fazenda Paraíso stations) and one output data (streamflow from Fazenda Oriente station), that considered the temporal variation of streamflow. Hence, the utilization of the ANN generated by the WEKA was adequate and can be considered a simple approach, not requiring great computational programming knowledge.
Subject(s)
Linear Models , Stream Flow , Neural Networks, ComputerABSTRACT
Abstract The aim of this work is to evaluate the performance of upflow anaerobic fixed bed reactors filled with espresso coffee capsules to treat sanitary sewage. Three reactors (R1, R2 and R3) were constructed in blue PVC pipes measuring 30 cm height and 150 mm diameter and filled with coffee capsules made of aluminum and plastic. The sewage from the pre-treatment phase of the wastewater treatment plant of the Federal University of Lavras fed the system. Temperature, pH, alkalinity and volatile acids concentration, COD, TS, TVS and TSS of the influent and effluent were analyzed to evaluate the reactors performances. Statistics tests were run in the software Statistica 10. Changes occurred in the organic loading rates caused two different operating phases, one at an OLR of 2.1 kg COD m-3d-1 and another at 4.0 kg COD m-3d-1. The average temperature during the monitoring period was 18°C. In spite of the operating conditions variations, the reactors showed satisfactory performances, presenting COD efficiency removals up to 80% in both phases. The capsules characteristics were similar to other materials used as support. Hence, it is possible to utilize coffee capsules as support material in anaerobic reactors, providing satisfactory pollutants removal efficiencies.