Search

It is crucial to monitor algal blooms in freshwater reservoirs through an examination of chlorophyll-a (Chla) concentrations, as they indicate the trophic condition of these waterbodies. Traditional monitoring methods, however, are expensive and time-consuming. Addressing this hindrance, we conducted a comprehensive investigation using several machine learning models for Chla modeling. To this end, we used in situ collected water sample data and remote sensing data from the Sentinel-2 satellite, including spectral bands and indices, for large-scale coverage. This approach allowed us to conduct a comprehensive analysis and characterization of the Chla concentrations across 149 freshwater reservoirs in Ceará, a semi-arid region of Brazil. The implemented machine learning models included k-nearest neighbors, random forest, extreme gradient boosting, the least absolute shrinkage, and the group method of data handling (GMDH); in particular, the GMDH approach has not been previously explored in this context. The forward stepwise approach was used to determine the best subset of input parameters. Using a 70/30 split for the training and testing datasets, the best-performing model was the GMDH model, achieving an R2 of 0.91, an MAPE of 102.34%, and an RMSE of 20.4 μg/L, which were values consistent with the ones found in the literature. Nevertheless, the predicted Chla concentration values were most sensitive to the red, green, and near-infrared bands. [ABSTRACT FROM AUTHOR]

Abstract: This paper deals with the analysis and comparison of 7 (seven) numerical methods for the assessment of effectiveness in determining the parameters for the Weibull distribution, using wind speed data collected in Camocim and Paracuru cities, State of Ceará, in the northeast region of Brazil, in the period from August 2004 to April 2006, obtained by the Department of Infrastructure of the State of Ceará. One method is not well known, namely the equivalent energy method, and its performance is compared to the others. By using the methods of analysis of variance, RMSE (root mean square error), and chi-square tests to compare the proposed methods, this study aims to determine which ones are effective in determining the parameters of the Weibull distribution for the available data, in an attempt to establish acceptable criteria to a better utilization of wind power in the State of Ceará, which is a national prominence in the use of renewable sources for electricity generation in Brazil. [Copyright &y& Elsevier]

This work introduces a new approach for the evaluation of numerical methods used in calculating the Weibull parameters for the prediction of wind resource. In this evaluation, power is a key issue since it proves to be quite relevant in predicting the feasibility of a given site for efficient use of wind energy. Previous knowledge of such information is important for the decision process on the technical feasibility of installing industrial wind farms. The paper performed a statistical analysis of seven mathematical methods to estimate the shape parameter k and the scaling parameter c of the Weibull distribution. Wind speed and wind power data collected in two coastal cities (Icapuí and Camocim), State of Ceará, in the northeast region of Brazil were used. The methods used in the development of this research are the graphical method, maximum likelihood method, modified maximum likelihood method, empirical method, moment method, energy pattern factor method and the equivalent energy method. Comparative analysis of efficiency and accuracy involves the application of the following statistical tests: analysis of variance (R2), root mean square error (RMSE), and chi-square (X 2). The use of power as a parameter to be evaluated in this study by analyzing the Weibull distribution, is something different from what has been discussed in the literature, and indicates that methods which are well evaluated when the wind speed is used as a comparison factor can change position when ranked by power. It is important to emphasize that the values of k and c were calculated directly from the values of wind power (not the wind speed, as usual), and subsequently it was statistically tested the adequacy of the values in the prediction of wind speed and wind power. The presented results indicate that the values generated for the shape and scale parameters provided differences considering the databases formed by wind speed and wind power, namely the graphical method. The wind power data produced accurate results when submitted to statistical tests. [ABSTRACT FROM AUTHOR]