Artificial Neural Networks for Filling Missing Streamflow Data in Rio do Carmo Basin, Minas Gerais, Brazil

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.

Use of Coffee Capsules as Support Material in Upflow Anaerobic Fixed Bed Reactors

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.

Relação entre padrões de uso e ocupação do solo e qualidade da água em uma bacia hidrográfica urbana / Relationship between patterns of use and occupation of soil and water quality in an urban watershed

RESUMO O uso e a ocupação do solo alteram sensivelmente os processos físico-químicos e biológicos dos sistemas naturais. Dessa forma, os mananciais de superfície são integradores dos fenômenos ocorrentes sobre a área da bacia hidrográfica. Assim, os objetivos do trabalho foram explorar a variabilidade temporal e espacial da qualidade da água e avaliar as possíveis relações entre os padrões de uso e ocupação do solo da bacia hidrográfica do Ribeirão Vermelho. Foram coletadas amostras de água em dois períodos (verão e inverno) e em 15 seções ao longo do curso d'água. Verificou-se forte influência temporal e espacial na qualidade das águas, e foram apresentadas no período de inverno as maiores concentrações de nutrientes (Cl-, P, NO3 -), condutividade elétrica e matéria orgânica. Esses valores interferem nos valores do Índice de Qualidade da Água, que varia entre 84 e 9 no período do verão e 66 e 6 no inverno. Quanto à trofia dos mananciais, foram encontrados valores médios de Índice de Estado Trófico de 30 no período chuvoso e de 93 no inverno. No tocante aos padrões de uso do solo, observaram-se fortes relações na qualidade da água nos dois períodos avaliados; a principal fonte de contaminação são as áreas urbanas. O Ribeirão Vermelho e seus afluentes apresentam forte influência das formas de uso e ocupação do solo confirmada pela entrada de matéria orgânica e de nutrientes nos sistemas hídricos por meio do lançamento de esgoto doméstico sem tratamento e pela agropecuária na rede de drenagem da bacia.

ABSTRACT Land use significantly alters the physicochemical and biological processes of natural systems. Thus, surface water sources are integrators of phenomena occurring on the catchment area. In this way, the study aimed to explore the spatial and temporal variability of water quality, and to assess the possible relationships between patterns of land use of the Ribeirão Vermelho basin. Water samples were collected in two periods (summer and winter) and in 15 sections along the watercourse. There has been strong temporal and spatial influence on water quality, and winter period showed the highest nutrient concentrations (Cl-, P, NO3 -), electrical conductivity and organic matter. These values influence the values of the Water Quality Index, ranging from 84 to 9 in the summer period and 66 to 6 in the winter. With respect to trophic conditions of water sources, average values of Trophic State Index of 30 were verified during the rainy season and 93 in winter. Regarding land use patterns, strong relationships in water quality in both periods were observed, the main source of contamination are urban areas. Ribeirão Vermelho and its effluent have shown strong influence of the forms of land use and occupation evidenced by the input organic matter and nutrients in water systems through domestic sewage release untreated and by agriculture in the drainage system of the basin.