Forecasting geostationary infrared brightness temperature sequences from historical observations is a significant and challenging task. By analyzing these predictions, cloud evolution, convective activity, and atmospheric radiative states can be revealed in advance, offering high potential value in domains such as weather nowcasting, energy management, and disaster monitoring. Recently, artificial intelligence techniques have provided valuable insights into this task. However, as a nascent research area, the lack of a standardized, high-quality benchmark has significantly impeded progress. Moreover, training existing deep learning models for this task remains computationally expensive due to the complexity of their network architectures and modeling mechanisms. To address these challenges, we introduce a new benchmark, FY4ABT, and propose a lightweight prediction model, WavePredNet. Specifically, FY4ABT comprises three sub-datasets designed to respectively evaluate prediction performance under short-term, medium-term, and long-term scenarios. Meanwhile, WavePredNet effectively captures multi-scale dynamics, including both low- and high-frequency components with low computational costs while delivering exceptional performance.

Photovoltaic (PV) power forecasting is critical for the operation of solar power plants and the coordination of energy within power grids. This work aims to predict future PV power time series by leveraging multimodal data. While recent studies have incorporated numerical modalities such as satellite image sequences and numerical weather prediction (NWP) time series, they often overlook textual modalities—such as the spatio-temporal context of PV plants—and the potential of pretrained large language models (LLMs). In this paper, we build upon existing numerical inputs and further explore the use of spatio-temporal text prompts, generated based on plant coordinates and forecast start time, to enhance the forecasting process. We propose PV-LLM, a satellite-text-prompted framework that integrates a pretrained LLM to improve PV power forecasting. The framework consists of three key components: Text Prompt Construction, Modality-Specific Encoding, and Adaptive Prompt Tuning. First, the Text Prompt Construction module generates spatio-temporal prompts that offer high-level semantic guidance. Next, the Modality-Specific Encoding module encodes each modality according to its unique characteristics, capturing modality-specific patterns while managing varying context lengths. Finally, the Adaptive Prompt Tuning module fine-tunes the LLM to integrate multimodal embeddings, while an adaptive gating mechanism retains its pretrained knowledge. We validate the effectiveness of the proposed framework on a real-world dataset containing multiple PV plants. Experimental results demonstrate that our approach outperforms existing state-of-the-art methods.

Using pre-trained large language models (LLMs) as a backbone for time series prediction has recently attracted growing research interest. Existing approaches typically split time series into patches, map them to the token space of LLMs via a Tokenizer, process the tokens through a frozen or fine-tuned LLM backbone, and then reconstruct numerical forecasts using a Detokenizer. However, the actual effectiveness of LLMs for time series forecasting remains under debate. We observe that when trained and evaluated on small datasets, the Tokenizer–Detokenizer components often overfit to the specific data distribution, thereby masking the intrinsic predictive capability of the LLM backbone. To investigate the inherent potential of LLMs in this context, we design three models with identical architectures but distinct pre-training strategies. By leveraging large-scale pre-training, we obtain more unbiased Tokenizer–Detokenizer pairs that are seamlessly integrated with the LLM backbone. Through controlled experiments, we evaluate the zero-shot and few-shot forecasting performance of the LLM, offering insights into its true capabilities. Our extensive experiments reveal that, although the LLM backbone shows some promise, its performance remains limited and does not consistently surpass that of models specifically trained on large-scale time series data. Our source code is publicly available in the repository: https://github.com/SiriZhang45/LLM4TS.

Precipitation nowcasting plays a pivotal role in urban planning and disaster mitigation, where extending forecast horizons offers critical advantages for proactive decision-making. Most data-driven methods focus on modeling radar echo sequences through end-to-end spatiotemporal predictive learning, yielding precise short-term predictions; however, they fundamentally neglect the inherent physical mechanism governing precipitation system. Moreover, approaches relying solely on single-modality radar observations suffer from persistent information bottlenecks, severely limiting their temporal generalizability for extended forecasting. To address these challenges, we propose PiMMNet, a Physics-informed Multi-Modal Network. It is constructed based on the advection-diffusion principle from fluid dynamics, explicitly modeling the precipitation evolution as a spatiotemporal transport processes characterized by the deterministic advection and the stochastic source. We carefully design a multi-model motion estimation network and a motion-guided diffusion model to describe the deterministic and stochastic terms, respectively. The core innovation of our method lies in jointly estimating a physics-constrained velocity field from multi-modal inputs (radar and satellite data). In this case, we naturally align the motion evolution among modalities into a unified representation, inherently mitigating cross-modal distribution biases. Experimental evaluations on two real-world multi-modal meteorological datasets demonstrate the efficacy of our approach, showcasing significant improvements in accuracy and robustness for longer-range precipitation nowcasting. Our code are available at https://github.com/DeminYu98/PiMMNet.

Long-term time series forecasting (LTSF) aims to predict future values for a long time based on historical data. The period term is an essential component of the time series, which is complex yet important for LTSF. Although existing studies have achieved promising results, they still have limitations in modeling dynamic complicated periods. Most studies only focus on static periods with fixed time steps, while very few studies attempt to capture dynamic periods in the time domain. In this paper, we dissect the original time series in time and frequency domains and empirically find that changes in periods are more easily captured and quantified in the frequency domain. Based on this observation, we propose to explore dynamic period features using rotation in the frequency domain. To this end, we develop the frequency-based rotation network (FRNet), a novel LTSF method to effectively capture the features of the dynamic complicated periods. FRNet decomposes the original time series into period and trend components. Based on the complex-valued linear networks, it leverages a period frequency rotation module to predict the period component and a patch frequency rotation module to predict the trend component, respectively. Extensive experiments on seven real-world datasets consistently demonstrate the superiority of FRNet over various state-of-the-art methods. The source code is available at https://github.com/SiriZhang45/FRNet.

Satellite image sequence prediction aims to precisely infer future satellite image frames with historical observations, which is a significant and challenging dense prediction task. Though existing deep learning models deliver promising performance for satellite image sequence prediction, the methods suffer from quite expensive training costs, especially in training time and GPU memory demand, due to the inefficiently modeling for temporal variations. This issue seriously limits the lightweight application in satellites such as space-borne forecast models. In this article, we propose a lightweight prediction framework TinyPredNet for satellite image sequence prediction, in which a spatial encoder and decoder model the intra-frame appearance features and a temporal translator captures inter-frame motion patterns. To efficiently model the temporal evolution of satellite image sequences, we carefully design a multi-scale temporal-cascaded structure and a channel attention-gated structure in the temporal translator. Comprehensive experiments are conducted on FengYun-4A (FY-4A) satellite dataset, which show that the proposed framework achieves very competitive performance with much lower computation cost compared to state-of-the-art methods. In addition, corresponding interpretability experiments are conducted to show how our designed structures work. We believe the proposed method can serve as a solid lightweight baseline for satellite image sequence prediction.

Online class-incremental continual learning is a specific task of continual learning. It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic forgetting issue, i.e., forgetting historical knowledge of old classes. Existing replay-based methods effectively alleviate this issue by saving and replaying part of old data in a proxy-based or contrastive-based replay manner. Although these two replay manners are effective, the former would incline to new classes due to class imbalance issues, and the latter is unstable and hard to converge because of the limited number of samples. In this paper, we conduct a comprehensive analysis of these two replay manners and find that they can be complementary. Inspired by this finding, we propose a novel replay-based method called proxy-based contrastive replay (PCR). The key operation is to replace the contrastive samples of anchors with corresponding proxies in the contrastive-based way. It alleviates the phenomenon of catastrophic forgetting by effectively addressing the imbalance issue, as well as keeps a faster convergence of the model. We conduct extensive experiments on three real-world benchmark datasets, and empirical results consistently demonstrate the superiority of PCR over various state-of-the-art methods11https://github.com/FelixHuiweiLin/PCR.

With the advance of acquisition techniques, plentiful higherorder tensor data sets are built up in a great variety of fields such as computer vision, neuroscience, remote sensing and recommender systems. The real-world tensors often contain missing values, which makes tensor completion become a prerequisite to utilize them. Previous studies have shown that imposing a low-rank constraint on tensor completion produces impressive performances. In this paper, we argue that low-rank constraint, albeit useful, is not effective enough to exploit the local smooth and piecewise priors of visual data. We propose integrating total variation into low-rank tensor completion (LRTC) to address the drawback. As LRTC can be formulated by both tensor unfolding and tensor decomposition, we develop correspondingly two methods, namely LRTC-TV-I and LRTC-TVII, and their iterative solvers. Extensive experimental results on color image and medical image inpainting tasks show the effectiveness and superiority of the two methods against state-of-the-art competitors.