Non-stationary time series (TS) analysis has gained an explosive interest over the recent decades in different applied sciences. In fact, several decomposition methods were developed in order to extract various components (e.g., seasonal, trend and abrupt components) from the non-stationary TS, which allows for an improved interpretation of the temporal variability. The wavelet transform (WT) has been successfully applied over an extraordinary range of fields in order to decompose the non-stationary TS into time-frequency domain. For this reason, the WT method is briefly introduced and reviewed in this paper. In addition, this latter includes different research and applications of the WT to non-stationary TS in seven different applied sciences fields, namely the geo-sciences and geophysics, remote sensing in vegetation analysis, engineering, hydrology, finance, medicine, and other fields, such as ecology, renewable energy, chemistry and history. Finally, five challenges and future works, such as the selection of the type of wavelet, selection of the adequate mother wavelet, selection of the scale, the combination between wavelet transform and machine learning algorithm and the interpretation of the obtained components, are also discussed.

High-resolution remote sensing scene classification (HR-RSSC) plays an increasingly important role since it aims to enhance the scene semantic understanding. Recently, convolutional neural networks (CNNs) proved their effectiveness in learning powerful feature representations for various visual recognition tasks. However, in the RS domain, the performance of CNN is still limited due to the lack of sufficient labeled data. In this letter, we propose an HR-RSSC method based on CNN transfer learning (TL) for feature extraction (FE) and deep forest (DF) for classification. In fact, we extract deep features from the last convolutional layer in order to avoid the use of the fully connected layers (FCLs) which need many parameters to tune. Moreover, we train a DF model that is based on ensemble learning that can achieve better performances than single classifiers and is easy to train with few parameters. We evaluate the proposed method on two RS image data sets. Compared to full-training, fine-tuning, and state-of-the-art CNN TL methods, the results demonstrate the effectiveness of the DF model for HR-RSSC based on CNN TL in terms of overall accuracy and training time.

Satellite image time-series (SITS) methods have contributed notably to detection of global change over the last decades, for instance by tracking vegetation changes. Compared with multi-temporal change detection methods, temporally highly resolved SITS methods provide more information in a single analysis, for instance on the type and consistency of change. In particular, SITS decomposition methods show a great potential in extracting various components from non-stationary time series, which allows for an improved interpretation of the temporal variability. Even though many case studies have applied SITS decomposition methods, a systematic comparison of common algorithms is still missing. In this study, the seasonal trend loess (STL), breaks for additive season and trend (BFAST) and multi-resolution analysis-wavelet transform (MRA-WT) were explored in order to evaluate their performance in modelling, monitoring and detecting land-cover changes with pronounced seasonal variations from simulated normal difference vegetation index time series. The selected methods have all proven their ability to characterize the non-stationary vegetation dynamics along with different physical processes driving the vegetation dynamics. Our results indicated that BFAST is the most accurate method for the examined simulated dataset in terms of RMSE, whereas MRA-WT showed a great potential for the extraction of multi-level vegetation dynamics. Considering the computational efficiency, both STL and MRA-WT outperformed BFAST.