Spatio-temporal Prediction Research Articles

Excess deaths and loss of life expectancy attributed to long-term NO2 exposure in the Chinese elderly

BackgroundEvidence linking nitrogen dioxide (NO2) air pollution to life span of high-vulnerability older adults is extensively scarce in low- and middle-income countries. This study seeks to quantify mortality risk, excess deaths, and loss of life expectancy (LLE) associated with long-term exposure to NO2 among elderly individuals in China. MethodsA nationwide dynamic cohort of 20352 respondents ≥65 years old were enrolled from the China Longitudinal Health and Longevity Survey during 2005–2018. Residential exposures to NO2 and co-pollutants were assessed by well-validated spatiotemporal prediction models. A Cox regression model with time-dependent covariates was utilized to quantify the association of all-cause mortality with NO2 exposure, controlling for confounders such as demographics, lifestyle, health status, and ambient temperature. NO2-attributable deaths and LLE were evaluated for the years 2010 and 2020 based on the pooled NO2-mortality relation derived from multi-national cohort investigations. Decomposition analyses were conducted to dissociate net shift in NO2-related deaths between 2010 and 2020 into four primary contributing factors. ResultsA total of 14313 deaths were recorded during follow-up of approximately 100 hundred person-years (median 3.6 years). We observed an approximately linear relationship (nonlinear P = 0.882) of NO2 exposure with all-cause death across a broad range from 6.6 to 95.7 μg/m3. Every 10-μg/m3 rise in yearly average NO2 concentration was linked to a hazard ratio (HR) of 1.045 (95% confidence interval [CI]: 1.031–1.059). In the updated meta-analysis of this study and 9 existing cohorts, we estimated a pooled HR of 1.043 (95% CI: 1.023–1.063) for each 10-μg/m3 growth in NO2. Reaching a 10-μg/m3 counterfactual target of NO2 concentration in China could avoid 0.33 (95% empirical CI: 0.19–0.49) million premature deaths and an LLE of 0.40 (95% empirical CI: 0.23–0.59) years in 2010, which greatly dropped to 0.24 (95% empirical CI: 0.14–0.36) million deaths and 0.21 (95% empirical CI: 0.12–0.31) years of LLE in 2020. The net fall in NO2-attributable deaths (–26.8%) between 2010 and 2020 was primarily driven by the declines in both NO2 concentration (–41.6%) and mortality rate (–27.1%) under population growth (+41.0%) and age structure transition (+0.9%). ConclusionsOur findings provide national evidence for increased risk of premature death and loss of life expectancy attributed to later-life NO2 exposure among the elderly in China. In an accelerated aging society, strengthened clean air actions should be formulated to minimize the health burden and regional inequality in NO2-attributable mortality.

Spatio-temporal evolution and prediction of carbon balance in the Yellow River Basin and zoning for low-carbon economic development

Studying the carbon effect of land use in watersheds is important for mitigating global warming, promoting coordinated emission reduction in different regions within the watersheds, and realizing high-quality development of the watersheds. Although a number of scholars have carried out relevant studies in the past, they mainly focused on carbon emissions, rarely involved the carbon balance formed by carbon sources and sinks, and lacked relevant studies on the development of low-carbon economy sub-region. Based on this, this study takes the Yellow River Basin as an example, explores the spatial and temporal evolution of carbon emissions from land use in counties in the Yellow River Basin from 1980 to 2020, and predicts the spatial pattern of carbon income and expenditure from land use under natural conditions in 2030 and 2060 using the PLUS model; and then superimposes on the main functional area planning, divides 735 counties in the Yellow River Basin into six low-carbon economic development subregions, and analyzes their economic development The model of their economic development is analyzed. The results show that: (1) the spatial and temporal differentiation of land use carbon balance in the Yellow River Basin has changed greatly over the past 40 years, (2) the spatial distribution pattern of land use carbon balance in the natural context in 2030 and 2060 is more similar to that in 1990, (3) the carbon emission reduction potentials and pattern optimization of the different low-carbon economic development subregions differ greatly, and they have different low-carbon economic development patterns. The results of this study provide a theoretical basis for scientifically and rationally formulating economic policies for low-carbon development in the counties of the Yellow River Basin, and also provide an important reference for related studies in other similar basins or regions in the world.

A City Shared Bike Dispatch Approach Based on Temporal Graph Convolutional Network and Genetic Algorithm.

Public transportation scheduling aims to optimize the allocation of resources, enhance efficiency, and increase passenger satisfaction, all of which are crucial for building a sustainable urban transportation system. As a complement to public transportation, bike-sharing systems provide users with a solution for the last mile of travel, compensating for the lack of flexibility in public transportation and helping to improve its utilization rate. Due to the characteristics of shared bikes, including peak usage periods in the morning and evening and significant demand fluctuations across different areas, optimizing shared bike dispatch can better meet user needs, reduce vehicle vacancy rates, and increase operating revenue. To address this issue, this article proposes a comprehensive decision-making approach for spatiotemporal demand prediction and bike dispatch optimization. For demand prediction, we design a T-GCN (Temporal Graph Convolutional Network)-based bike demand prediction model. In terms of dispatch optimization, we consider factors such as dispatch capacity, distance restrictions, and dispatch costs, and design an optimization solution based on genetic algorithms. Finally, we validate the approach using shared bike operating data and show that the T-GCN can effectively predict the short-term demand for shared bikes. Meanwhile, the optimization model based on genetic algorithms provides a complete dispatch solution, verifying the model's effectiveness. The shared bike dispatch approach proposed in this paper combines demand prediction with resource scheduling. This scheme can also be extended to other transportation scheduling problems with uncertain demand, such as store replenishment delivery and intercity inventory dispatch.

Spatio-temporal communication network traffic prediction method based on graph neural network

The function of network traffic prediction plays an important role in many network operations such as security, path planning and congestion control etc. Most traditional traffic prediction methods only consider temporal correlation but ignore spatial correlation, which may result in limited accuracy. In this paper, we propose an effective traffic prediction method based on the graph multi-head attention convolution neural network model, termed as FlowDiviner, which combines graph convolutional network (GCN) and multi-head attention mechanism in its encoder-decoder architecture. Specifically, GCN is used to extract spatial correlation from complex network topologies and multi-head attention mechanism is used to capture dynamic temporal correlations based on monitored traffic behaviors. Meanwhile, a middle attention module is introduced between encoder and decoder to model the relationship between historical and future timesteps of traffic, thus it can alleviate the error accumulation and improve accuracy. The experiments based on both real-life dataset as well as synthetically generated traffic traces show that FlowDiviner can effectively obtain temporal and spatial correlation from the network historical traffic data, and the test results of all metrics are significantly improved from the baseline schemes.

MGAtt-LSTM: A multi-scale spatial correlation prediction model of PM2.5 concentration based on multi-graph attention

The increase in air pollution has posed numerous new challenges for human society, making the exploration of an effective method for predicting air pollutant concentrations highly significant. The current research faces several primary challenges: the neglect of non-Euclidean characteristics of site distribution on data and the strong spatiotemporal dependencies in the dispersion process of pollutants. To address these issues, this paper constructs a spatiotemporal hybrid prediction model – the MGAtt-LSTM method – for predicting PM2.5 concentrations, which employs the dynamic multi-graph attention module (MGAtt) to tackle spatial dependencies and Long Short-Term Memory networks (LSTM) to address temporal dependencies. Additionally, extensive experiments are conducted by using historical air pollutant monitoring data and meteorological data from the Beijing-Tianjin-Hebei region. The results demonstrate that the proposed MGAtt-LSTM model achieved superior performance in concentration prediction compared to existing benchmark models.

Machine Learning Techniques for Spatio-Temporal Air Pollution Prediction to Drive Sustainable Urban Development in the Era of Energy and Data Transformation

Sustainable urban development in the era of energy and digital transformation is crucial from a societal perspective. Utilizing modern techniques for analyzing large datasets, including machine learning and artificial intelligence, enables a deeper understanding of historical data and the efficient prediction of future events based on data from IoT sensors. This study conducted a multidimensional historical analysis of air pollution to investigate the impacts of energy transformation and environmental policy and to determine the long-term environmental implications of certain actions. Additionally, machine learning (ML) techniques were employed for air pollution prediction, taking spatial factors into account. By utilizing multiple low-cost air sensors categorized as IoT devices, this study incorporated data from various locations and assessed the influence of neighboring sensors on predictions. Different ML approaches were analyzed, including regression models, deep neural networks, and ensemble learning. The possibility of implementing such predictions in publicly accessible IT mobile systems was explored. The research was conducted in Krakow, Poland, a UNESCO-listed city that has had long struggle with air pollution. Krakow is also at the forefront of implementing policies to prohibit the use of solid fuels for heating and establishing clean transport zones. The research showed that population growth within the city does not have a negative impact on PMx concentrations, and transitioning from coal-based to sustainable energy sources emerges as the primary factor in improving air quality, especially for PMx, while the impact of transportation remains less relevant. The best results for predicting rare smog events can be achieved using linear ML models. Implementing actions based on this research can significantly contribute to building a smart city that takes into account the impact of air pollution on quality of life.

Construction of a Green and Low-Carbon Travel Order Prediction Model Based on Shared Bicycle Big Data

In the era of big data, traditional analysis methods are insufficient to meet the growing demand for green and low-carbon travel orders in shared bicycle systems. To address this issue, a new order demand forecasting model, named the “convolutional neural network (CNN)”—“long short-term memory (LSTM)” model (CNN-LSTM), is proposed by integrating CNN and LSTM techniques. The research further validates the spatiotemporal prediction performance of this model. The experimental results demonstrate that LSTM exhibits favorable prediction performance in terms of time feature analysis, as evidenced by the overlapping of the true value (TV) and predicted value (PV) curves. Notably, LSTM achieves an impressively low mean squared error (MSE) value of 0.0063, which is significantly lower compared to CNN (0.0082) and XGBoost (0.0074). Upon incorporating date and weather characteristics, the predictive performance improves significantly, achieving an outstanding MSE value of 0.0043. However, when it comes to spatial feature analysis, the LSTM algorithm alone proves inadequate, obtaining a MSE value of 0.0084. Thus, by employing the CNN-LSTM combination model, a lower MSE value of 0.0066 is achieved, outperforming the comparison algorithms. Overall, the CNN-LSTM model exhibits strong predictive capabilities regarding the temporal and spatial requirements of shared bicycles. This model plays a key role in accurately forecasting order demands, facilitating urban transportation planning and management, as well as guiding the planning and location of non-motorized vehicle stops.

Precipitation data merging via machine learning: Revisiting conceptual and technical aspects

The development of accurate precipitation products of high spatio-temporal coverage is crucial for a wide range of applications. In this context, precipitation data merging (PDM), which entails the blending of satellite-based estimates with ground-based measurements, holds a prominent position, while currently there is an increasing trend in the deployment of machine learning (ML) algorithms in such endeavors. In the light of recent advances in the field, this work discusses key aspects of the PDM problem associated with: a) the conceptual formulation of the problem, that is closely related to the training of ML models and their predictive capacity, b) the selection of products fused, that is associated with the latency of final product and operational applicability of the method, c) the efficiency of single-step and two-step merging approaches, with the former one treating the problem via only regression algorithms, and the latter one via the combined use of classification and regression algorithms. By formulating PDM as a spatio-temporal prediction problem, we define and assess two different training strategies for the ML models, termed as full and per time step strategy, which entail the building of a single or several ML models, respectively. Furthermore, the performance of the full training strategy, which allows the development of predictions in both spatial and temporal dimensions, is assessed in the context of single-step and two-step merging. In each of the three scenarios, three popular ensemble tree-based ML algorithms are employed, i.e., the random forest, gradient boosting and extreme gradient boosting algorithm, resulting in nine merged products. To provide empirical evidence, we employ a datacube composed by ground-based daily precipitation observations, satellite-based and reanalysis estimates, as well as auxiliary covariates, from 1009 uniformly distributed cells (representative of a sampling area of 25 × 25 km), over four countries around the world (Australia, USA, India and Italy). The large-scale experiment indicates that: (i) full training strategy is a competitive alternative to the per time step strategy, since it enables the development of methods with improved accuracy, with respect to performance metrics and reproduction of statistics, but also with higher predictive capability and operational applicability, (ii) two-step merging enables a much better reproduction of precipitation occurrence characteristics, as reflected in the improvement of relevant categorical metrics, the reproduction of probability and autocorrelation coefficient, (iii) no significant difference was noticed in the performance of different ML algorithms.

Spatiotemporal Mechanism-Based Spacetimeformer Network for InSAR Deformation Prediction and Identification of Retrogressive Thaw Slumps in the Chumar River Basin

The increasing incidence of retrogressive thaw slumps (RTSs) in permafrost regions underscores the need for detailed spatial and temporal analysis using InSAR technology to monitor and predict dynamic changes in the process of RTSs. Nevertheless, current InSAR deformation forecasting methods employing deep learning strategies such as the traditional long short-term memory (LSTM) and recent transformer models encounter difficulties in effectively capturing temporal features. Moreover, they are limited in their ability to directly integrate spatial information. In this paper, an innovative deep learning approach named Spacetimeformer is proposed for predicting medium- and short-term InSAR deformation of RTSs in the Chumar River area. This method employs a transformer architecture with a spatiotemporal attention mechanism, which enhances the long-term prediction capabilities of time series models and dynamic spatial modeling. It is applicable to multivariate InSAR spatiotemporal deformation prediction problems. The findings include a list of 72 RTSs compiled based on derived InSAR deformation maps and Sentinel-2 optical images, of which 64 have an average deformation rate exceeding 10 mm/year, indicating signs of permafrost degradation. The density distribution of the displacement maps predicted by the Spacetimeformer model aligned well with the InSAR deformation maps obtained from the small baseline subset (SBAS) method, with the overall prediction deviation controlled within 20 mm. In addition, the point-scale prediction results were compared with LSTM and transformer models. This study indicates that the Spacetimeformer network achieved good results in predicting the deformation of RTSs, with a root mean square error of 1.249 mm. The Spacetimeformer method for deformation prediction with the spacetime mechanism presented in this study can serve as a general framework for multivariate deformation prediction based on InSAR results. It can also quantitatively assess the spatial deformation characteristics and deformation trends of RTSs.

Residual Spatiotemporal Convolutional Neural Network Based on Multisource Fusion Data for Approaching Precipitation Forecasting

Approaching precipitation forecast refers to the prediction of precipitation within a short time scale, which is usually regarded as a spatiotemporal sequence prediction problem based on radar echo maps. However, due to its reliance on single-image prediction, it lacks good capture of sudden severe convective events and physical constraints, which may lead to prediction ambiguities and issues such as false alarms and missed alarms. Therefore, this study dynamically combines meteorological elements from surface observations with upper-air reanalysis data to establish complex nonlinear relationships among meteorological variables based on multisource data. We design a Residual Spatiotemporal Convolutional Network (ResSTConvNet) specifically for this purpose. In this model, data fusion is achieved through the channel attention mechanism, which assigns weights to different channels. Feature extraction is conducted through simultaneous three-dimensional and two-dimensional convolution operations using a pure convolutional structure, allowing the learning of spatiotemporal feature information. Finally, feature fitting is accomplished through residual connections, enhancing the model’s predictive capability. Furthermore, we evaluate the performance of our model in 0–3 h forecasting. The results show that compared with baseline methods, this network exhibits significantly better performance in predicting heavy rainfall. Moreover, as the forecast lead time increases, the spatial features of the forecast results from our network are richer than those of other baseline models, leading to more accurate predictions of precipitation intensity and coverage area.

Long-term navigation for autonomous robots based on spatio-temporal map prediction

The robotics community has witnessed a growing demand for long-term navigation of autonomous robots in diverse environments, including factories, homes, offices, and public places. The core challenge in long-term navigation for autonomous robots lies in effectively adapting to varying degrees of dynamism in the environment. In this paper, we propose a long-term navigation method for autonomous robots based on spatio-temporal map prediction. The time series model is introduced to learn the changing patterns of different environmental structures or objects on multiple time scales based on the historical maps and forecast the future maps for long-term navigation. Then, an improved global path planning algorithm is performed based on the time-variant predicted cost maps. During navigation, the current observations are fused with the predicted map through a modified Bayesian filter to reduce the impact of prediction errors, and the updated map is stored for future predictions. We run simulation and conduct several weeks of experiments in multiple scenarios. The results show that our algorithm is effective and robust for long-term navigation in dynamic environments.

STBGRN: A Traffic Prediction Model Based on Spatiotemporal Bidirectional Gated Recurrent Units and Graph Convolutional Residual Networks

With the development of society and the advancement of urbanization, the development of intelligent transportation system has attracted much attention. Efficient and accurate traffic flow prediction is one of the core tasks in the research of intelligent transportation system. Most of the existing spatiotemporal traffic flow prediction models do not make full use of various periodic spatiotemporal dynamic characteristics of traffic flow, and it is difficult to effectively capture the complex spatiotemporal changes of traffic flow. To accurately predict the traffic flow of complex urban network, this paper proposes a traffic prediction model (STBGRN) based on spatiotemporal bidirectional gated cycle unit (ST-BiGRU) and graph convolution residual network (GCN-ResNet). The spatiotemporal information in traffic data is learned using the spatiotemporal bidirectional GRU coupled with the forward and backward information of the current time step, and the topology structure of the traffic network is captured by the graph convolution residual network, which is combined to complete the prediction task of the urban traffic network. In this paper, STBGRN was tested on two real data sets, SZ-taxi and Los-loop, and compared with other baseline methods, the RMSE index reached 3.857 and 5.461, and the MAE index reached 2.702 and 3.781, respectively. Accuracy index is 72.66% and 91.35%, R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document} index is 0.858 and 0.845, var index is 0.858 and 0.849. The experimental results show that STBGRN model can obtain spatiotemporal dependence from complex traffic data, and can be used in spatiotemporal traffic data processing.

Performance of the neural network-based prediction model in closed-loop adaptive optics.

Adaptive optics (AO) technology is an effective means to compensate for atmospheric turbulence, but the inherent delay error of an AO system will cause the compensation phase of the deformable mirror (DM) to lag behind the actual distortion, which limits the correction performance of the AO technology. Therefore, the feed-forward prediction of atmospheric turbulence has important research value and application significance to offset the inherent time delay and improve the correction bandwidth of the AO system. However, most prediction algorithms are limited to an open-loop system, and the deployment and the application in the actual AO system are rarely reported, so its correction performance improvement has not been verified in practice. We report, to our knowledge, the first successful test of a deep learning-based spatiotemporal prediction model in an actual 3 km laser atmospheric transport AO system and compare it with the traditional closed-loop control methods, demonstrating that the AO system with the prediction model has higher correction performance.

Hierarchical Predictions of Fine-to-Coarse Time Span and Atmospheric Field Reconstruction for Typhoon Track Prediction

The prediction of typhoon tracks in the Northwest Pacific is key to reducing human casualties and property damage. Traditional numerical forecasting models often require substantial computational resources, are high-cost, and have significant limitations in prediction speed. This research is dedicated to using deep learning methods to address the shortcomings of traditional methods. Our method (AFR-SimVP) is based on a large-kernel convolutional spatio-temporal prediction network combined with multi-feature fusion for forecasting typhoon tracks in the Northwest Pacific. In order to more effectively suppress the effect of noise in the dataset to enhance the generalization ability of the model, we use a multi-branch structure, incorporate an atmospheric reconstruction subtask, and propose a second-order smoothing loss to further improve the prediction ability of the model. More importantly, we innovatively propose a multi-time-step typhoon prediction network (HTAFR-SimVP) that does not use the traditional recurrent neural network family of models at all. Instead, through fine-to-coarse hierarchical temporal feature extraction and dynamic self-distillation, multi-time-step prediction is achieved using only a single regression network. In addition, combined with atmospheric field reconstruction, the network achieves integrated prediction for multiple tasks, which greatly enhances the model’s range of applications. Experiments show that our proposed network achieves optimal performance in the 24 h typhoon track prediction task. Our regression network outperforms previous recurrent network-based typhoon prediction models in the multi-time-step prediction task and also performs well in multiple integration tasks.

Learning spatiotemporal dependencies using adaptive hierarchical graph convolutional neural network for air quality prediction

Air quality prediction has garnered significant attention from both governmental bodies and the general public due to its close connection with people’s daily lives. Learning spatio-temporal dependencies within air quality data are crucial for accurate air quality forecasting. Graph Convolutional Network (GCN) has been widely utilized in spatiotemporal data prediction due to its remarkable ability of capturing non-Euclidean spatial dependencies among nodes. However, previous research on Spatiotemporal Graph Neural Networks (ST-GNNs) has either utilized graph adjacency matrices predefined by heuristic rules or learned through trainable parameters. These approaches fail to accurately represent the true spatial relationships between stations and adaptively capture the required multi-level spatial dependencies for prediction. To address these limitations, this paper proposes an Adaptive Hierarchical Graph Convolutional Neural Network (AHGCNN) for PM2.5 prediction. More specially, an adaptive hierarchical graph convolutional structure is initially developed for dynamically extracting multi-level spatial dependencies. Then, a hierarchical aggregation scheme is designed to consolidate the unique topological structures of graph neural networks across different levels. Finally, a unified Adaptive Hierarchical Graph Convolution Gated Recurrent Unit (AHGC-GRU) model is proposed by integrating Gated Recurrent Unit (GRU) with hierarchical graph convolution in an effort to capture spatiotemporal dependencies of air quality data. Extensive experiments are conducted on real-world datasets, and the results demonstrate that the proposed model outperforms existing models.

Towards spatio-temporal prediction of cavitating fluid flow with graph neural networks

In this article, we present a deep learning-based surrogate model for spatio-temporal prediction of cavitating fluid flow. Specifically, we introduce a finite element-inspired rotation equivariant hypergraph neural network for inferring and predicting dynamical behaviors of cavitating flow. We generate ground-truth spatial–temporal data by simulating a full-order variational system based on homogeneous mixture-based cavitation theory. We consider the flow past a NACA0012 hydrofoil to examine the predictive ability of the proposed graph neural network for cavitation dynamics. Results demonstrate that the network achieves stabilized and accurate temporal predictions of the system states, successfully forecasting the evolution patterns of individual cavitation events. Additionally, comparisons of predicted fluid loading coefficients are in good agreements with the ground-truth values. We also discuss some challenges encountered in the long-term prediction of flow patterns across multiple cavitation events. The proposed framework has implications for design optimization, active control and development of a physics-based digital twin of a cavitating marine propeller.

Spatio-temporal prediction of total energy consumption in multiple regions using explainable deep neural network

Energy consumption forecasting is essential for energy system integration and management. However, existing studies mainly focus on temporal features of energy consumption, which neglects the spatial correlation of variables with time information. Capturing the spatio-temporal relationships helps to improve forecasting accuracy and further promote energy dispatch. To tackle this problem, an explainable Convolutional Neural Network-Long Short Term Memory forecasting model is employed to effectively predict the total energy consumption by capturing the spatial and temporal features of multivariate time series. In the model, the autoencoder is used to achieve the nonlinear dimensionality reduction and transfer the data to a low-dimensional space. Furthermore, a Convolutional Neural Network is used to extract more effective features from the decoded data, and long short-term memory is employed to identify the temporal dependencies between extracted features and total energy consumption. Shapley additive explanation is introduced to interpret the outputs of the black-box model. The superior performance of the proposed method with high accuracy and good adaptability is verified by the comparisons with conventional forecasting models. This method provides an insight into the regional energy consumption analyzing contributions of weather variables to energy consumption, which helps administers in understanding regional energy performance for enhancing energy efficiency.

Spatiotemporal variation and prediction of NPP in Beijing-Tianjin-Hebei region by coupling PLUS and CASA models

Vegetation productivity is crucial for human production and livelihoods. Understanding net primary productivity (NPP) in historical contexts and predicting its future fluctuations is imperative for assessing the environmental sustainability of a region. However, relatively few researches have been conducted on predicting NPP, requiring further development and refinement of NPP prediction methods and models. This study introduces a novel approach that discretely couples the PLUS and CASA models for NPP prediction, and it validates the applicability of this approach in the research area. The objective of our study is to analyze the spatiotemporal patterns of NPP change in the Beijing-Tianjin-Hebei (BTH) region from 2001 to 2020, predict NPP under three different climate scenarios (SSP 1-2.6, SSP 2-4.5, SSP 5-8.5) in 2030, and identify an appropriate path for the future development of this region. The results indicate:(1) From 2001 to 2020, NPP in the research area has shown a gradual improvement trend and maintained a certain spatial distribution pattern in general. (2) The study discovered a correlation coefficient of 0.83 and an RMSE of 102.86 between predicted and actual NPP for 2020. This suggests that the method introduced in our study is suitable for predicting NPP in the research area. (3) NPP in the study area is predicted to decline in 2030 compared with 2020 under all three scenarios. Moreover, the SSP 1-2.6 scenario, representing a low-emission scenario, is suitable for the BTH region compared with other climate scenarios. This research sheds light on NPP variations in the BTH region over the past 20 years and the next 10 years, offering a scientific basis for relevant departments to formulate future policies.

A novel attention enhanced deep neural network for hypersonic spatiotemporal turbulence prediction

High Reynolds number turbulent flow of hypersonic vehicles exhibits multi-scale flow structures and non-equilibrium high-frequency characteristics, presenting a significant challenge for accurate prediction. A deep neural network integrated with attention mechanism as a reduced order model for hypersonic turbulent flow is proposed, which is capable of capturing spatiotemporal characteristics from high-dimensional numerical turbulent data directly. The network model leverages encoder–decoder architecture where the encoder captures high-level semantic information of input flow field, Convolutional Long Short-Term Memory network learns low-dimensional characteristic evolution, and the decoder generates pixel-level multi-channel flow field information. Additionally, skip connection structure is introduced at the decoding stage to enhance feature fusion while incorporating Dual-Attention-Block that automatically adjusts weights to capture spatial imbalances in turbulence distribution. Through evaluating the time generalization ability, the neural network effectively learns the evolution of multi-scale high-frequency turbulence characteristics. It enables rapid prediction of high Reynolds number turbulence evolution over time with reasonable accuracy while maintaining excellent computational efficiency.

Spatiotemporal dynamics of forest fires in the context of climate change: a review.

Forest fires are sudden, destructive, hazardous, and challenging to manage and rescue, earning them a place on UNESCO's list of the world's eight major natural disasters. Currently, amid global warming, all countries worldwide have entered a period of high forest fire incidence. Due to global warming, the frequency of forest fires has accelerated, the likelihood of large fires has increased, and the spatial and temporal dynamics of forest fires have shown different trends. Therefore, the impact of climate change on the spatiotemporal dynamics of forest fires has become a hot issue in the field of forest fire research in recent years. Therefore, it is of great significance and necessity to conduct a review of the research in this area. This review delves into the interactions and impacts between climate change and the spatiotemporal dynamics of forest fires. To address this issue, scholars have mainly adopted the following research methods: first, statistical analysis methods, second, the establishment of spatiotemporal prediction models for meteorology and forest fires, and third, the coupling of climate models with forest fire risk forecasting models. The statistical analysis method relies on the analysis of historical meteorological and fire-related data to study the effects of climate change and meteorological factors on fire occurrence. Meanwhile, forest fire prediction models utilize technical tools such as remote sensing. These models synthesize historical meteorological and fire-related data, incorporating key meteorological factors such as temperature, rainfall, relative humidity, and wind. The models revealed the spatial and temporal distribution patterns of fires, identified key drivers, and explored the interactions between climate change and forest fire dynamics, culminating in the construction of predictive models. With the deepening of the study, the coupling of climate models and fire risk ranking systems became a trend in the prediction of forest fire risk trends. Moreover, as the climate warms, the increased frequency of extreme weather events like heatwaves, droughts, snow and ice storms, and El Niño-Southern Oscillation (ENSO) has accelerated forest fire occurrences and raised the risk of major fires. This review offers valuable technical insights by comprehensively analyzing the spatial and temporal characteristics of forest fires, elucidating key meteorological drivers, and exploring potential mechanisms. These insights serve as a scientific foundation for preventive measures and effective forest fire management. In the face of a changing climate, this synthesis contributes to the development of informed strategies to mitigate the escalating threat of forest fires.