Detecting hydrocarbon reservoirs from a seismic survey is a complex task, requiring specialized professionals and long time. Consequently, many authors today seek to automate this task by using deep neural networks. Following the success of deep convolutional networks, CNNs, in the identification of objects in images and videos, CNNs have been used as detectors of geological events in seismic images. Training a deep neural network, however, requires hundreds of thousands of labeled data, that is, samples that we know the response that the network must provide. If we treat seismic data as images, the hydrocarbon reservoirs usually constitute a small sub-image unable to provide so many samples. The methodology proposed in this dissertation treats the seismic data as a set of traces and the sample that feeds the neural network are fragments of a onedimensional signal resembling a sound or voice signal. A labeled reservoir seismic image usually provides the required number of labeled one-dimensional samples for training. Another important aspect of our proposal is the use of a recurrent neural network. The influence of a hydrocarbon reservoir on a seismic trace occurs not only in its location but throughout the trace that follows. For this reason, we propose the use of a Long Short-Term Memory, LSTM, network to characterize regions that present gas signatures in seismic images. This dissertation further details the implementation of the proposed methodology and test results on the Netherlands F3-Block public seismic data. The results on this data set, evaluated by sensitivity, specificity, accuracy and AUC indexes, are all excellent, above 95 percent.