Air quality forecasting has attracted increasing attention as global air pollution worsens. Spatiotemporal graph neural networks have become a leading paradigm, thanks to their ability to capture complex spatial and temporal dynamics in Air Quality Index (AQI) data. However, existing methods remain limited by weak modeling of long-range temporal dependencies and insufficient integration of meteorological factors. Building on a publicly available nationwide air quality dataset spanning eight years, we propose MADGCN, a Meteorology-Aware Decoupled Spatio-Temporal Convolutional Network that jointly addresses long-horizon temporal modeling and meteorological context fusion. MADGCN includes a dynamic causality discovery module grounded in Granger causality, which captures time-varying causal relationships between meteorological conditions and AQI dynamics. The inferred causal structures further guide a causal graph convolution module and a PatchMixer module, enabling effective spatial interaction modeling and multiscale temporal dependency learning. Extensive experiments against 16 strong baselines show that MADGCN achieves competitive performance for long-horizon air pollution forecasting and generalizes well under high-pollution regimes.

The storage and transmission of large-scale meteorological data have become a significant bottleneck hindering the in-depth development of meteorological research. This study proposes a novel meteorological data compression framework characterized by innovative thinking. It embeds the Mamba structure during the feature extraction stage and integrates a spatio-temporal channel attention mechanism to construct an entropy coding mechanism that facilitates the sharing of high-dimensional meteorological data channel information. The framework achieves a compression rate of 300x and, more importantly, preserves the essential spatio-temporal features of meteorological data. Validation on the ERA5 dataset demonstrates that the proposed method surpasses existing techniques in terms of both data compression efficiency and reconstruction accuracy. The accuracy of meteorological analyses based on compressed data is comparable to that of the original data, offering a highly practical solution to the challenges of storing meteorological big data. Our source code is publicly available online at https://github.com/cike0cop/MambaComp .

Unsupervised domain adaptation (UDA) aims to improve model performance in the target domain by leveraging labeled data from the source domain while not requiring labeled data in the target domain. It has been widely applied in cross-domain semantic segmentation of remote sensing images (RSIs). Despite some advancements in this area, challenges such as class confusion due to color and texture similarities, class imbalance due to significant scale variations and sample imbalance continue to impede progress in UDA for RSI segmentation. To address these challenges, we propose a novel self-supervised teacher-student network framework, including two innovative techniques: mask-enhanced class mix (MECM) and scale-based rare class sampling (SRCS). The MECM method applies a high proportion of masks to mixed images derived from both source-domain images and target-domain images, which encourages the model to infer the semantic information of masked areas from the surrounding context, enhancing cross-domain contextual semantic learning and improving the recognition accuracy of similar classes. Additionally, SRCS increases the sampling proportion of small-scale rare classes, mitigating the issue of class imbalance. Experiments show that our method outperforms existing UDA techniques in terms of PA, mF1, and mIoU, achieving state-of-the-art results on three public datasets. Notably, in the Potsdam IRRG to Vaihingen UDA scenario, our method’s performance on the key metric, mIoU, even surpasses that of supervised training, demonstrating the superiority of our approach. Codes are available athttps://github.com/Qiuyb-ai/UDA-With-ME-and-BS.

The traditional super-resolution dataset construction using artificial down-sampling techniques can result in information loss, insufficient diversity, and non-uniqueness. Furthermore, existing methods for image super-resolution are limited to single-modal images and cannot accommodate the complexities of multimodal images. This is problematic because diverse modal data requires individualized model design and training, which can hinder the exploitation of complementary relationships among multimodal data. In this article, we have addressed these issues by undertaking a two-step solution approach. In the first step, we constructed a super-resolution dataset that utilized remote-sensing images of tropical cyclones in “real cases.” This dataset comprises HR–LR image pairs originating from multiple sensors of varying satellite sources, resulting in multimodal data. However, the HR–LR image pairs suffer from an additional misalignment issue. Thus, in the second step, we designed a super-resolution network based on MAT to address the misalignment problem in multimodal environment. After numerous ablation experiments and comparison experiments, we have shown that our model is effective, with an improvement of 50% over the original baseline model, and an increase varying between 20% and 50% compared to other common super-resolution models. We have made our source code and data publicly available online at https://github.com/kleenY/MMTCSR .

Tropical cyclones (TC) are one of the extreme disasters that have the most significant impact on human beings. Unfortunately, intensity forecasting of TC has been a difficult and bottleneck in weather forecasting. Recently, deep learning‐based intensity forecasting of TC has shown the potential to surpass traditional methods. However, due to the Earth system’s complexity, nonlinearity, and chaotic effects, there is inherent uncertainty in weather forecasting. Besides, previous studies have not quantified the uncertainty, which is necessary for decision‐making and risk assessment. This study proposes an intelligent system based on deep learning, PTCIF, to quantify this uncertainty based on multimodal meteorological data, which, to our knowledge, is the first study to assess the uncertainty of TC based on a deep learning approach. In this study, probabilistic forecasts are made for the intensity of 6–24 hours. Experimental results show that our proposed method is comparable to the forecast performance of weather forecast centers in terms of deterministic forecasts. Moreover, reliable prediction intervals and probabilistic forecasts can be obtained, which is vital for disaster warning and is expected to be a complement to operational models.

Tropical cyclones (TC) bring enormous harm to human beings, and it is crucial to accurately forecast the intensity of TCs, but the progress of intensity forecasting has been slow in recent years, and tropical cyclones are an extreme weather phenomenon with short duration, and the sample size of TC intensity series is small and short in length. In this paper, we devolop a tensor ARIMA model based on feature reconstruction to solve the problem, which represents multiple time series as low-rank Block Hankel Tensor(BHT), and combine the tensor decomposition technique with ARIMA for time series prediction. The method predicts the sustained maximum wind speed and central minimum pressure of TC 6-24 hours in advance, and the results show that the method exceeds the global numerical model GSM operated by the Japan Meteorological Agency (JMA) in the short term. We further checked the prediction results for a TC, and the results show the validity of the method.

Tropical cyclones (TCs) generally carry large amounts of water vapor and can cause large-scale extreme rainfall. Passive microwave (PMW) rainfall (PMR) estimation of TC with high spatial and temporal resolution is crucial for disaster warning of TC, but remains a challenging problem due to low temporal resolution of microwave sensors. This study attempts to solve this problem by directly predicting PMW rainfall images (PMRIs) from satellite infrared (IR) images of TC. We develop a generative adversarial network (GAN) to simulate PMRI using IR images and establish the mapping relationship between TC cloud-top brightness temperature and PMR, and the algorithm is named tropical cyclone rainfall (TCR)-GAN. Meanwhile, a new dataset that is available as a benchmark, Dataset of TC IR-to-Rainfall Prediction (TCIRRP), was established, which is expected to advance the development of artificial intelligence in this direction. The experimental results show that the algorithm can effectively extract key features from IR. The end-to-end deep learning approach shows potential as a technique that can be applied globally and provides a new perspective TC precipitation prediction via satellite, which is expected to provide important insights for real-time visualization of TC rainfall globally in operations.

Tropical cyclone (TC) is one of the major meteorological disasters in the world, which seriously threatens the safety of human life and property. In this study, we adopt the tropical cyclone best track archive and the global tropical cyclone exposure data sets, using the ensemble machine learning approach for exposed to the TCs of the population and asset to estimate. To the best of our knowledge, this research is the first hazards assessment study using machine learning methods to estimate the exposure of tropical cyclones to population and property end-to-end. In particular, we validated our model using data from the country most affected by tropical cyclones. The results depicted a 10% improvement over traditional methods. The correlation coefficient r between the predicted value and the exposure data is 0.813, demonstrating a strong correlation between the predicted results and the great potential of machine learning to solve the problem of hazards assessment. However, there is still uncertainty in assessing the impact of tropical cyclones, especially the impact caused by high wind speeds.

Cyclone, especially tropical cyclones, are one of the most significant meteorological disasters in the world, which seriously threaten the safety of life and property. The ability to accurately identify the type and intensity of cyclones is crucial for disaster prevention. This article proposes the use of dual branches Convolutional Neural Network (CNN) model, based on Global Forecast System Analysis (GFS) to identify cyclones, including tropical cyclones, extratropical cyclones and subtropical cyclones, a total of 11 types of cyclone-related phenomena. The model can learn spatial information and extract crucial features, and merge at the end to achieve end-to-end prediction output. The results indicate that the model's identify accuracy of tropical cyclones and extratropical cyclones exceeds 90%, and the identify accuracy of cyclones disturbances and subtropical cyclones is also more than 75%, the model does not require expert knowledge, and the speed of operation fast.

The accurate estimation of tropical cyclone (TC) size is one of the key steps in TC forecasting and disaster warninglmanagement. In this study, we proposed the use of deep convolutional neural networks (CNN) to estimate the size of tropical cyclone. To the best of our knowledge, this is the first study to estimate the size of tropical cyclones using deep learning methods; we use about 1,000 tropical cyclones which contain about 30,000 infrared remote sensing images as the data set. Compared with the best track archives, the mean error of our proposed model is 24nmi, the error is even smaller than the Multiplatform Tropical Cyclone Surface Winds Analysis (MTCSWA) operated by National Oceanic and Atmospheric Administration(NOAA), which shows the great potential of deep learning in estimating the size of tropical cyclones.

The prediction of tropical cyclones (TCs) is a valuable and challenging task. As a research hotspot of deep learning, generative adversarial network (GAN) has obtained promising results in TC prediction recently. However, different kinds of GAN applied in meteorology usually focus on how to generate high-quality images, but ignore how GAN learns the physical characteristics in the training process. This paper visualizes the intermediate results of GAN in the training process, and shows the process of learning the physical characteristics of data distribution similar to TC images for GAN. The core method in this paper is deep convolutional generative adversarial networks (DCGAN). In order to obtain prediction results with interpretable physical characteristics, we propose two training strategies for DCGAN, namely the long short-term training method and training parameters selection according to physical characteristics. Experimental results show that the DCGAN model and two strategies proposed in this paper have good performance in the visual prediction of TCs.