This work introduces a new AI identification model, applied to the forecasting of Hydro-Climate series. Unlike most currently used models, based solely on the study of the historical data, this approach proposes the use of delayed "explaining" variables feeding an unknown nonlinear system. An optimal combination of two different models (Neural Networks and Vector Quantization) "explains" the desired variables, yielding the prediction output. The method is applied to the prediction of a Brazilian river inflow, with immediate use into future energy availability forecasts.

In the face of global warming, research on carbon removal to mitigate the effects of climate change has been carried out. The use of constructed wetlands for wastewater treatment is known, however the quantity of studies about carbon sequestration of this system is still limited. Thus, the systematic and literature review aimed to expose the characteristics of constructed wetlands in relation to greenhouse gas emissions. The bases used were Scopus, Springer and Google Schoolar and the selected terms were related to constructed wetlands and GHG. It was concluded that the horizontal subsurface flow CWs has the potential to become a carbon sink, due to the carbon retained in the plants, and may emit less N2O than the vertical subsurface flow CW; about the emission of CH4, it is important to know the species of plant adopted due to its influence on methane emissions.