The extensive amount of Satellite Image Time Series (SITS) data brings new opportunities and challenges for land cover analysis. Many supervised machine learning methods have been applied in SITS, but the labeled SITS samples are time- and effort-consuming to acquire. It is necessary to analyze SITS data with an unsupervised learning method. In this paper, we propose a new unsupervised learning method named Deep Temporal Iterative Clustering (DTIC) to deal with SITS data. The proposed method jointly learns a neural network’s parameters and the resulting features’ cluster assignments, which uses a standard clustering algorithm, K-means, to iteratively cluster the features produced by the feature extraction network and then uses the subsequent assignments as supervision to update the network’s weights. We apply DTIC to the unsupervised training of neural networks on both SITS datasets. Experimental results demonstrate that DTIC outperforms the state-of-the-art K-means clustering algorithm, which proves that the proposed approach successfully provides a novel idea for unsupervised training of SITS data.

This study focused on improving the clustering performance of hyperspectral imaging (HSI) by employing the Generalized Orthogonal Matching Pursuit (GOMP) algorithm for feature extraction. Hyperspectral remote sensing imaging technology, which is crucial in various fields like environmental monitoring and agriculture, faces challenges due to its high dimensionality and complexity. Supervised learning methods require extensive data and computational resources, while clustering, an unsupervised method, offers a more efficient alternative. This research presents a novel approach using GOMP to enhance clustering performance in HSI. The GOMP algorithm iteratively selects multiple dictionary elements for sparse representation, which makes it well-suited for handling complex HSI data. The proposed method was tested on two publicly available HSI datasets and evaluated in comparison with other methods to demonstrate its effectiveness in enhancing clustering performance.

With the advancement of remote sensing satellite technology, the acquisition of Satellite Image Time-Series (SITS) data has significantly increased, providing new opportunities and challenges for land cover analysis. Traditional unsupervised clustering methods often struggle with the complexity of these data due to limitations in scalability and generalization capabilities. In response, this paper proposes a new unsupervised learning approach called deep temporal joint clustering (DTJC) designed for efficient pixel-wise clustering of SITS data. DTJC optimizes the reconstruction of temporal information along with clustering objectives, which not only preserves the temporal dynamics of the original data but also creates a feature space conducive to clustering. Experimental results show that DTJC achieves optimal clustering performance across four publicly available multi-spectral SITS datasets, including TimeSen2Crop, Cerrado Biome, Reunion Island, and Imperial datasets. Compared to traditional K-means and projection algorithms, DTJC significantly improves clustering accuracy, especially in environments with complex geographical distributions. Leveraging the principles of the K-means clustering algorithm, DTJC showcases remarkable performance improvements over traditional optimized K-means and projection algorithms in land cover analysis, heralding a new era in the unsupervised learning landscape of SITS data. The DTJC method greatly enhances the efficiency of SITS data analysis without the need for labeled data, making it a powerful tool for automated land cover classification and environmental monitoring.

This study seeks to overcome the limitations of traditional gas well production peak forecasting approaches, particularly in the context of handling multi-dimensional features, complex dynamic behaviors, and non-linear relationships. Accordingly, a deep learning-based multi-scale adaptive fusion perception network is proposed in this work. Specifically, a time-series processing framework based on multi-scale decomposition is first constructed, where wavelet transform is employed to perform multi-scale decomposition of the gas well production data, thereby effectively extracting both long-term trends and short-term fluctuations. Subsequently, a multi-dimensional feature collaborative encoding and adaptive fusion module is designed. This module jointly encodes the multi-dimensional features in gas well production forecasting. By utilizing a dual-path PatchTST encoder, it captures the long-term trends and short-term fluctuations within the time-series data. Finally, to enhance the accuracy of gas well production peak forecasting, a personalized multi-loss training function is developed. This mixed loss function balances the robustness to outliers with the control of percentage errors, effectively mitigating the sensitivity of conventional loss functions to outliers. Systematic experiments conducted on real gas well production samples demonstrate that the proposed model outperforms existing state-of-the-art models across various evaluation metrics. Furthermore, quantile accuracy analysis reveals that the proposed model consistently achieves the highest proportion of qualifying samples under error thresholds ranging from 5% to 20% while exhibiting stable adaptability across different production scenarios, including low, typical, and high production rates. The proposed method provides a high-precision, effective solution for gas well production peak forecasting, offering reliable decision support for production process optimization.