The contribution of this paper is twofold. First, a new data driven approach for predicting the Covid-19 pandemic dynamics is introduced. The second contribution consists in reporting and discussing the results that were obtained with this approach for the Brazilian states, with predictions starting as of 4 May 2020. As a preliminary study, we first used an Long Short Term Memory for Data Training-SAE (LSTM-SAE) network model. Although this first approach led to somewhat disappointing results, it served as a good baseline for testing other ANN types. Subsequently, in order to identify relevant countries and regions to be used for training ANN models, we conduct a clustering of the world’s regions where the pandemic is at an advanced stage. This clustering is based on manually engineered features representing a country’s response to the early spread of the pandemic, and the different clusters obtained are used to select the relevant countries for training the models. The final models retained are Modified Auto-Encoder networks, that are trained on these clusters and learn to predict future data for Brazilian states. These predictions are used to estimate important statistics about the disease, such as peaks and number of confirmed cases. Finally, curve fitting is carried out to find the distribution that best fits the outputs of the MAE, and to refine the estimates of the peaks of the pandemic. Predicted numbers reach a total of more than one million infected Brazilians, distributed among the different states, with São Paulo leading with about 150 thousand confirmed cases predicted. The results indicate that the pandemic is still growing in Brazil, with most states peaks of infection estimated in the second half of May 2020. The estimated end of the pandemics (97% of cases reaching an outcome) spread between June and the end of August 2020, depending on the states.
A new sampling and analytical design for measurement of ambient ozone is presented. The procedure is based on ozone absorption and decoloration (at 600 nm) of indigotrisulfonate dye, where ozone adds itself across the carbon-carbon double bond of the indigo. A mean relative standard deviation of 8.6% was obtained using samplers exposed in triplicate, and a correlation coefficient (r) of 0.957 was achieved in parallel measurements using the samplers and a commercial UV ozone instrument. The devices were evaluated in a measurement campaign, mapping spatial and temporal trends of ozone concentrations in a region of southeast Brazil strongly influenced by seasonal agricultural biomass burning, with associated emissions of ozone precursors. Ozone concentrations were highest in rural areas and lowest at an urban site, due to formation during downwind transport and short-term depletion due to titration with nitric oxide. Ozone concentrations showed strong seasonal trends, due to the influences of precursor emissions, relative humidity and solar radiation intensity. Advantages of the technique include ease and speed of use, the ready availability of components, and excellent sensitivity. Achievable temporal resolution of ozone concentrations is 8 hours at an ambient ozone concentration of 3.8 ppb, or 2 hours at a concentration of 15.2 ppb.
A new simple method for determination of ozone in ambient air is presented. The reaction employed is based on the known ozonolysis of indigo dye. The indigotrisulfonate molecule contains one carbon-carbon double bond (C C), which reacts with ozone and generates isatinsulfonates and sulfoanthranilate. The quantitatively formed sulfoanthranilate presents fluorescence (λ ex 245 nm, λ em 400 nm). Ozone was collected using two cellulose filters coated with 40 μL of 1.0 × 10 − 3 mol L − 1 of indigotrisulfonate. The analytical response was linear in the range 0-150 ppbv ozone, and a detection limit of 7 ppbv was achieved using a sampling time of 15 min and an optimum sampling air flow rate of 0.4 L min − 1. There was no interference from sulfur dioxide, formaldehyde or nitrogen dioxide. The ozonolysis mechanism and the reaction products are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.