Currently, the Congo Basin represents the most important center in terms of biodiversity concentration, especially with the increasing deforestation observed in the Amazon. The available climate models are mostly at larger scales, and few of them focus on specific areas of the Congo Basin, such as the locality of Makokou in Gabon. A new approach is therefore needed to predict temperatures changes in this particular region. Although some work focus on temperature prediction, most do not use deep learning algorithms. This contribution aims to compare the predictions of a Long Short-Term Memory (LSTM) model with those from the combination of Wavelet Transform and LSTM (WT-LSTM). The developed LSTM model includes two LSTM layers, two Dropout layers (with a rate of 50 %) and a Dense layer to outpout the predicted value. The WT-LSTM model shows superior results compared to the LSTM model, with a root mean square error of 0.45 °C, a mean absolute error of 0.35 °C, and a Spearman correlation coefficient of 0.97 °C. These results highlight the importance of using advanced approaches to improve climate forecasts in areas crucial for biodiversity conservation. The increased accuracy of predictions could help better anticipate and mitigate the impacts of of local climate change, thereby contributing to the sustainable management of this ecologically sensitive region.

In many fields, different elements (mechanical, electronic, electromechanical, etc.) come into play independently to ensure the overall operation of devices/machines: electrical cables, gears, bearings, pulleys, etc. In maintenance operations, the signals from these different elements in operation are often a mixture of multiple contributions, the level of complexity of which may vary, for example, depending on the measurement point, during the data acquisition stage. There may be a number of reasons for wanting to access only the signal from a particular component (e.g., to monitor service life, diagnose the faulty part and/or predict the time remaining before a serious breakdown), rather than all the contributions measured. It is therefore essential to have a range of tools to enable us to remove harmful signals (sometimes called noise). This article presents some techniques for separating discrete and random components.