The accuracy in predicting the typhoon track can be key to minimizing their frequent disastrous effects. This article aims to study the accuracy of typhoon trajectory prediction obtained by combining several algorithms based on current deep-learning techniques. The combination of a Convolutional Neural Network with Long Short-Term Memory (CNN+LSTM), Patch Time-Series Transformer (CNN+PatchTST) and Transformer (CNN+Transformer) were the models chosen for this work. These algorithms were tested on the best typhoon track data from the China Meteorological Administration (CMA), ERA5 data from the European Centre for Medium-Range Weather Forecasts (ECMWF), and structured meteorological data from the Zhuhai Meteorological Bureau (ZMB) as an extension of existing studies that were based only on public data sources. The experimental results were obtained by testing two complete years of data (2021 and 2022), as an alternative to the frequent selection of a small number of typhoons in several years. Using the R-squared metric, results were obtained as significant as CNN+LSTM (0.991), CNN+PatchTST (0.989) and CNN+Transformer (0.969). CNN+LSTM without ZMB data can only obtain 0.987, i.e., 0.004 less than 0.991. Overall, our findings indicate that appropriately augmenting data near land and ocean boundaries around the coast improves typhoon track prediction.

An energy supply and demand forecasting system can help decision-makers grasp more comprehensive information, make accurate decisions and even plan a carbon-neutral future when adjusting energy structure, developing alternative energy resources and so on. This paper presents a hierarchical design of an energy supply and demand forecasting system based on web crawler and a grey dynamic model called GM(1,1) which covers all the process of data collection, data analysis and data prediction. It mainly consists of three services, namely Crawler Service (CS), Algorithm Service (AS), Data Service (DS). The architecture of multiple loose coupling services makes the system flexible in more data, and more advanced prediction algorithms for future energy forecasting works. In order to make higher prediction accuracy based on GM(1,1), this paper illustrates some basic enhanced methods and their combinations with adaptable variable weights. An implementation for testing the system was applied, where the model was set up for coal, oil and natural gas separately, and the enhanced GM was better with relative error about 9.18% than original GM on validation data between 2010 and 2020. All results are available for reference on adjusting of energy structure and developing alternative energy resources.

Pseudo-label-based deep clustering has emerged as a compelling paradigm for unsupervised visual learning, yet two fundamental limitations impede its effectiveness: (1) pseudo-label noise, where unreliable hard assignments generated in early training accumulate and propagate errors across iterations; and (2) confidence-insensitive pseudo-label supervision, where one-hot pseudo-labels are treated with equal importance despite substantial differences in their reliability, increasing the influence of uncertain samples, particularly those near cluster boundaries. To address both issues simultaneously, we propose PSPLC—a Progressive Sample-Weighted Pseudo-Label Clustering framework with three synergistic modules. First, a MoCo-based contrastive pre-training module extracts discriminative feature representations. Second, a progressive sample-weighted pseudo-label training module (the core contribution) iterates an expectation step—which progressively expands a high-confidence sample set outward from calibrated cluster centres and assigns one-hot pseudo-labels with continuous confidence weights derived from a global–local confidence mechanism—with a maximisation step that jointly optimises a clustering consistency loss, a confidence-weighted one-hot pseudo-label loss, and an entropy balance loss. Third, a semi-supervised boosting module (PSPLC-Boost) identifies reliable samples via nearest-neighbour semantic consistency and jointly fine-tunes the feature extractor and clustering head with a FixMatch-inspired strategy. Extensive experiments on five benchmarks (STL-10, CIFAR-10, CIFAR-20, ImageNet-10, ImageNet-Dogs-15) show that PSPLC achieves state-of-the-art performance among purely unsupervised methods, and PSPLC-Boost surpasses all competitors on all five datasets across all three metrics.