Chang Liu

The spatiotemporal forecasting of temperature is a critical issue in meteorological prediction, with significant implications for fields such as agriculture and energy. With the rapid advancement of data-driven deep learning methods, deep learning-based spatiotemporal sequence forecasting models have seen widespread application in temperature spatiotemporal forecasting. However, statistical analysis reveals that temperature evolution varies across temporal and spatial scales due to factors like terrain, leading to a lack of existing temperature prediction models that can simultaneously learn both large-scale global features and small to medium-scale local features over time. To uniformly model temperature variations across different temporal and spatial scales, we propose the Multi-Scale Large Kernel Spatiotemporal Attention Neural Network (MSLKSTNet). This model consists of three main modules: a feature encoder, a multi-scale spatiotemporal translator, and a feature decoder. The core module of this network, Multi-scale Spatiotemporal Attention (MSSTA), decomposes large kernel convolutions from multi-scale perspectives, capturing spatial feature information at different scales, and focuses on the evolution of multi-scale spatial features over time, encompassing both global smooth changes and local abrupt changes. The results demonstrate that MSLKSTNet achieves superior performance, with a 35% improvement in the MSE metric compared to SimVP. Ablation studies confirmed the significance of the MSSTA unit for spatiotemporal forecasting tasks. We apply the model to the regional ERA5-Land reanalysis temperature dataset, and the experimental results indicate that the proposed method delivers the best forecasting performance, achieving a 42% improvement in the MSE metric over the widely used ConvLSTM model for temperature prediction. This validates the effectiveness and superiority of MSLKSTNet in temperature forecasting tasks.

High-resolution three-dimensional (3D) variations in ocean temperature and salinity fields are of great significance for ocean environment monitoring. Currently, AI-based 3D temperature and salinity field predictions rely on expensive 3D data, and as the prediction period increases, the stacking of high-resolution 3D data greatly increases the difficulty of model training. This paper transforms the prediction of 3D temperature and salinity into the prediction of sea surface elements and the inversion of subsurface temperature and salinity using sea surface elements, by leveraging the relationship between sea surface factors and subsurface temperature and salinity. This method comprehensively utilizes multi-source ocean data to avoid the issue of data volume caused by stacking high-resolution historical data. Specifically, the model first utilizes 1/4° low-resolution satellite remote sensing data to construct prediction models for sea surface temperature (SST) and sea level anomaly (SLA), and then uses 1/12° high-resolution temperature and salinity data as labels to build an inversion model of subsurface temperature and salinity based on SST and SLA. The prediction model and inversion model are integrated to obtain the final high-resolution 3D temperature and salinity prediction model. Experimental results show that the 20-day prediction results in the two sea areas of the coastal waters of China and the Northwest Pacific show good performance, accurately predicting ocean temperature and salinity in the vast majority of layers, and demonstrate higher resource utilization efficiency.

With the continuous advancement of sensing technology, applying large amounts of sensor data to practical prediction processes using artificial intelligence methods has become a developmental direction. In sensing images and remote sensing meteorological data, the dynamic changes in the prediction targets relative to their background information often exhibit more significant dynamic characteristics. Previous prediction methods did not specifically analyze and study the dynamic change information of prediction targets at spatiotemporal multi-scale. Therefore, this paper proposes a neural prediction network based on perceptual multi-scale spatiotemporal dynamic changes (PMSTD-Net). By designing Multi-Scale Space Motion Change Attention Unit (MCAU) to perceive the local situation and spatial displacement dynamic features of prediction targets at different scales, attention is ensured on capturing the dynamic information in their spatial dimensions adequately. On this basis, this paper proposes Multi-Scale Spatiotemporal Evolution Attention (MSEA) unit, which further integrates the spatial change features perceived by MCAU units in higher channel dimensions, and learns the spatiotemporal evolution characteristics at different scales, effectively predicting the dynamic characteristics and regularities of targets in sensor information.Through experiments on spatiotemporal prediction standard datasets such as Moving MNIST, video prediction dataset KTH, and Human3.6m, PMSTD-Net demonstrates prediction performance surpassing previous methods. We construct the GPM satellite remote sensing precipitation dataset, demonstrating the network’s advantages in perceiving multi-scale spatiotemporal dynamic changes in remote sensing meteorological data. Finally, through extensive ablation experiments, the performance of each module in PMSTD-Net is thoroughly validated.

Precipitation nowcasting pertains to the localized forecasting of rainfall over a brief time horizon, characterized by precise estimates of both coverage and intensity. This capability holds particular significance in various societal applications, including agriculture, aviation safety, and transportation. However, since traditional methods mainly by extrapolating radar echo in two-dimensional space, cannot accurately and sufficiently represent the spatiotemporal state of clouds in the vertical direction, the accuracy of precipitation nowcasting using weather radar has reached a bottleneck. A new deep learning precipitation nowcasting model called 3dCloudNet is designed and evaluated in this study. The 3dCloudNet incorporates historical three-dimensional radar echo sequences obtained from weather radar data to improve the accuracy and reliability of precipitation nowcasting. By capturing both horizontal and vertical motion patterns of clouds at various altitude levels, this model demonstrates an enhanced capability in detecting and distinguishing regions prone to severe convective weather events. The experimental results show that the model better captures clouds motion patterns and trends, and therefore has a noteworthy ability to detect and distinguish areas that may lead to severe convective weather. This study provides a step towards further improving the accuracy of precipitation nowcasting.

Accurate precipitation forecasting plays an important role in disaster prevention and mitigation. Currently, precipitation forecasting mainly depends on numerical weather prediction and radar observation. However, ground-based radar observation has limited coverage and is easily influenced by the environment, resulting in the limited coverage of precipitation forecasts. The infrared observations of geosynchronous earth orbit (GEO) satellites have been widely used in precipitation estimation due to their extensive coverage, continuous monitoring, and independence from environmental influences. In this study, we propose a multi-channel satellite precipitation forecasting network (MCSPF-Net) based on 3D convolutional neural networks. The network uses real-time multi-channel satellite observations as input to forecast precipitation for the future 4 h (30-min intervals), utilizing the observation characteristics of GEO satellites for wide coverage precipitation forecasting. The experimental results showed that the precipitation forecasting results of MCSPF-Net have a high correlation with the Global Precipitation Measurement product. When evaluated using rain gauges, the forecasting results of MCSPF-Net exhibited higher critical success index (0.25 vs. 0.21) and correlation coefficients (0.33 vs. 0.23) and a lower mean square error (0.36 vs. 0.93) compared to the numerical weather prediction model. Therefore, the multi-channel satellite observation-driven MCSPF-Net proves to be an effective approach for predicting near future precipitation.

Satellite remote sensing can provide observation information of the sea surface, and using the sea surface information to reconstruct the subsurface temperature (ST) and subsurface salinity (SS) information has significant application values. This study proposes an intelligent algorithm based on Dual Path Convolutional Neural Networks (DP-CNNs) to reconstruct the ST and SS. The DP-CNN can integrate known information including sea surface temperature (SST), sea surface salinity (SSS), and sea surface height (SSH) to reconstruct the ST and SS. The reconstruction model based on DP-CNN can solve the problem of detail information loss in traditional CNN (Convolutional Neural Network) models. This study performs experiments for the South China Sea under different seasons using reanalysis data. The experimental results show that the DP-CNN models have higher reconstruction accuracy than the CNN models, and this proves that DP-CNNs effectively mitigate the loss of detailed information in the CNN models. Compared with the ground truth data, the ST/SS reconstruction results of the DP-CNN model exhibited a high coefficient of determination (0.93/0.86) and a low root mean square error (around 0.31 °C/0.05 PSU). Therefore, the DP-CNN models can be used as an effective approach to reconstruct ST and SS using sea surface information.

Convolution-based recurrent neural networks and convolutional neural networks have been used extensively in spatiotemporal prediction. However, these methods tend to concentrate on fixed-scale spatiotemporal state transitions and disregard the complexity of spatiotemporal motion. Through statistical analysis, we found that the distribution of the spatiotemporal sequence and the variety of spatiotemporal motion state transitions exhibit some regularity. In light of these statistics and observations, we propose the Multi-scale Spatiotemporal Neural Network (MSSTNet), an end-to-end neural network based on 3D convolution. It can be separated into three major child modules: a distribution feature extraction module, a multi-scale motion state capture module, and a feature decoding module. Furthermore, the MSST unit is designed to model multi-scale spatial and temporal information in the multi-scale motion state capture module. We first conduct the experiments on the MovingMNIST dataset, which is the most commonly used dataset in the field of spatiotemporal prediction, MSSTNet can achieve state-of-the-art results for this dataset, and ablation experiments demonstrate that the MSST unit has positive significance for spatiotemporal prediction. In addition, this paper applies the model to valuable precipitation nowcasting, due to efficiently capturing the multi-scale information of distribution and motion, the new MSSTNet model can predict the real-world radar echo more accurately.

Geosynchronous satellite observation images have the advantages of a wide observation range and high temporal resolution, which are critical for understanding atmospheric motion and change patterns. The realization of geosynchronous satellite observation image prediction will provide significant support for short-term forecasting, including precipitation forecasting. Here, this paper proposes a deep learning method for predicting satellite observation images that can perform the task of predicting satellite observation sequences. In the study of predicting the observed images for Band 9 of the FY-4A satellite, the average mean square error of the network’s 2-h prediction is 4.77 Kelvin. The network’s predictive performance is the best among multiple deep learning models. We also used the model to predict Bands 10–14 of the FY-4A satellite and combined the multi-band prediction results. To test the application potential of the network prediction performance, we ran a precipitation area detection task on the multi-band prediction results. After 2 h of prediction, the detection results from satellite infrared images still achieved an accuracy of 0.855.