CALTM:A Context-Aware Long-Term Time-Series Forecasting Model

Time series data plays a crucial role in intelligent transportation systems.Traffic flow forecasting represents a precise estimation of future traffic flow within a specific region and time interval.Existing approaches,including sequence periodic,regression,and deep learning models,have shown promising results in short-term series forecasting.However,forecasting scenarios specifically focused on holiday traffic flow present unique challenges,such as distinct traffic patterns during vacations and the increased demand for long-term forecastings.Consequently,the effectiveness of existing methods diminishes in such scenarios.Therefore,we propose a novel longterm forecasting model based on scene matching and embedding fusion representation to forecast long-term holiday traffic flow.Our model comprises three components:the similar scene matching module,responsible for extracting Similar Scene Features;the long-short term representation fusion module,which integrates scenario embeddings;and a simple fully connected layer at the head for making the final forecasting.Experimental results on real datasets demonstrate that our model outperforms other methods,particularly in medium and long-term forecasting scenarios.

Impact of ocean data assimilation on the seasonal forecast of the 2014/15 marine heatwave in the Northeast Pacific Ocean

A remarkable marine heatwave,known as the“Blob”,occurred in the Northeast Pacific Ocean from late 2013 to early 2016,which displayed strong warm anomalies extending from the surface to a depth of 300 m.This study employed two assimilation schemes based on the global Climate Forecast System of Nanjing University of Information Science(NUIST-CFS 1.0)to investigate the impact of ocean data assimilation on the seasonal prediction of this extreme marine heatwave.The sea surface temperature(SST)nudging scheme assimilates SST only,while the deterministic ensemble Kalman filter(EnKF)scheme assimilates observations from the surface to the deep ocean.The latter notably improves the forecasting skill for subsurface temperature anomalies,especially at the depth of 100-300 m(the lower layer),outperforming the SST nudging scheme.It excels in predicting both horizontal and vertical heat transport in the lower layer,contributing to improved forecasts of the lower-layer warming during the Blob.These improvements stem from the assimilation of subsurface observational data,which are important in predicting the upper-ocean conditions.The results suggest that assimilating ocean data with the EnKF scheme significantly enhances the accuracy in predicting subsurface temperature anomalies during the Blob and offers better understanding of its underlying mechanisms.

Imperative for long-term management and surveillance in Kawasaki disease

Kawasaki disease(KD)is a significant pediatric vasculitis known for its potential to cause severe coronary artery complications.Despite the effectiveness of initial treatments,such as intravenous immunoglobulin,KD patients can experience long-term cardiovascular issues,as evidenced by a recent case report of an adult who suffered a ST-segment elevation myocardial infarction due to previous KD in the World Journal of Clinical Cases.This editorial emphasizes the critical need for long-term management and regular surveillance to prevent such complications.By drawing on recent research and case studies,we advocate for a structured approach to follow-up care that includes routine cardiac evaluations and preventive measures.

How Do Deep Learning Forecasting Models Perform for Surface Variables in the South China Sea Compared to Operational Oceanography Forecasting Systems?

It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.

AI-based Correction of Wave Forecasts Using the Transformer-enhanced UNet Model

Grid forecasting can be used to effectively enhance the spatial and temporal density of forecast products,thereby improving the capability of short-term marine disaster forecasting and warnings in terms of proximity.The traditional method that relies on forecasters'subjective correction of station observation data for forecasting has been unable to meet the practical needs of refined forecasting.To address this problem,this paper proposes a Transformer-enhanced UNet(TransUNet)model for wave forecast AI correction,which fuses wind and wave information.The Transformer structure is integrated into the encoder of the UNet model,and instead of using the traditional upsampling method,the dual-sampling module is employed in the decoder to enhance the feature extraction capability.This paper compares the TransUNet model with the traditional UNet model using wind speed forecast data,wave height forecast data,and significant wave height reanalysis data provided by ECMWF.The experimental results indicate that the TransUNet model yields smaller root-meansquare errors,mean errors,and standard deviations of the corrected results for the next 24-h forecasts than does the UNet model.Specifically,the root-mean-square error decreased by more than 21.55%compared to its precorrection value.According to the statistical analysis,87.81%of the corrected wave height errors for the next 24-h forecast were within±0.2m,with only 4.56%falling beyond±0.3 m.This model effectively limits the error range and enhances the ability to forecast wave heights.

TianXing:A Linear Complexity Transformer Model with Explicit Attention Decay for Global Weather Forecasting

In this paper,we introduce TianXing,a transformer-based data-driven model designed with physical augmentation for skillful and efficient global weather forecasting.Previous data-driven transformer models such as Pangu-Weather,FengWu,and FuXi have emerged as promising alternatives for numerical weather prediction in weather forecasting.However,these models have been characterized by their substantial computational resource consumption during training and limited incorporation of explicit physical guidance in their modeling frameworks.In contrast,TianXing applies a linear complexity mechanism that ensures proportional scalability with input data size while significantly diminishing GPU resource demands,with only a marginal compromise in accuracy.Furthermore,TianXing proposes an explicit attention decay mechanism in the linear attention derived from physical insights to enhance its forecasting skill.The mechanism can reweight attention based on Earth's spherical distances and learned sparse multivariate coupling relationships,promptingTianXing to prioritize dynamically relevant neighboring features.Finally,to enhance its performance in mediumrange forecasting,TianXing employs a stacked autoregressive forecast algorithm.Validation of the model's architecture is conducted using ERA5 reanalysis data at a 5.625°latitude-longitude resolution,while a high-resolution dataset at 0.25°is utilized for training the actual forecasting model.Notably,the TianXing exhibits excellent performance,particularly in the Z500(geopotential height)and T850(temperature)fields,surpassing previous data-driven models and operational fullresolution models such as NCEP GFS and ECMWF IFS,as evidenced by latitude-weighted RMSE and ACC metrics.Moreover,the TianXing has demonstrated remarkable capabilities in predicting extreme weather events,such as typhoons.

Short-TermWind Power Forecast Based on STL-IAOA-iTransformer Algorithm:A Case Study in Northwest China

Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.

Regional Storm Surge Forecast Method Based on a Neural Network and the Coupled ADCIRC-SWAN Model

Timely and accurate forecasting of storm surges can effectively prevent typhoon storm surges from causing large economic losses and casualties in coastal areas.At present,numerical model forecasting consumes too many resources and takes too long to compute,while neural network forecasting lacks regional data to train regional forecasting models.In this study,we used the DUAL wind model to build typhoon wind fields,and constructed a typhoon database of 75 processes in the northern South China Sea using the coupled Advanced Circulation-Simulating Waves Nearshore(ADCIRC-SWAN)model.Then,a neural network with a Res-U-Net structure was trained using the typhoon database to forecast the typhoon processes in the validation dataset,and an excellent storm surge forecasting effect was achieved in the Pearl River Estuary region.The storm surge forecasting effect of stronger typhoons was improved by adding a branch structure and transfer learning.

Long-Term Load Forecasting of Southern Governorates of Jordan Distribution Electric System

Load forecasting is vitally important for electric industry in the deregulated economy. This paper aims to face the power crisis and to achieve energy security in Jordan. Our participation is localized in the southern parts of Jordan including, Ma’an, Karak and Aqaba. The available statistical data about the load of southern part of Jordan are supplied by electricity Distribution Company. Mathematical and statistical methods attempted to forecast future demand by determining trends of past results and use the trends to extrapolate the curve demand in the future.

Spatial and temporal synthesized probability gain for middle and long-term earthquake forecast and its preliminary application

The principle of middle and long-term earthquake forecast model of spatial and temporal synthesized probability gain and the evaluation of forecast efficiency (R-values) of various forecast methods are introduced in this paper. The R-value method, developed by Xu (1989), is further developed here, and can be applied to more complicated cases. Probability gains in spatial and/or temporal domains and the R-values for different forecast methods are estimated in North China. The synthesized probability gain is then estimated as an example.

Comparison of Long-Term Forecasting of June-August Rainfall over Changjiang-Huaihe Valley

In terms of an Artificial Neural Network (ANN) established is a long-term prediction model for June-August flood/drought in the Changjiang-Huaihe Basins and a regression forecasting expression is formulated with the aid of the same factors and sample size for comparison. Results show that the ANN is superior in predictions and fittings due to its higher self-adaptive learning recognition and nonlinear mapping especially in the years of severe flood and drought. This shows great promise in using ANN in the research of flood/drought prediction on a long-range basis.

Hybrid LEAP modeling method for long-term energy demand forecasting of regions with limited statistical data

An accurate long-term energy demand forecasting is essential for energy planning and policy making. However, due to the immature energy data collecting and statistical methods, the available data are usually limited in many regions. In this paper, on the basis of comprehensive literature review, we proposed a hybrid model based on the long-range alternative energy planning (LEAP) model to improve the accuracy of energy demand forecasting in these regions. By taking Hunan province, China as a typical case, the proposed hybrid model was applied to estimating the possible future energy demand and energy-saving potentials in different sectors. The structure of LEAP model was estimated by Sankey energy flow, and Leslie matrix and autoregressive integrated moving average (ARIMA) models were used to predict the population, industrial structure and transportation turnover, respectively. Monte-Carlo method was employed to evaluate the uncertainty of forecasted results. The results showed that the hybrid model combined with scenario analysis provided a relatively accurate forecast for the long-term energy demand in regions with limited statistical data, and the average standard error of probabilistic distribution in 2030 energy demand was as low as 0.15. The prediction results could provide supportive references to identify energy-saving potentials and energy development pathways.

Machine Learning-Based Two-Stage Data Selection Scheme for Long-Term Influenza Forecasting

One popular strategy to reduce the enormous number of illnesses and deaths from a seasonal influenza pandemic is to obtain the influenza vaccine on time.Usually,vaccine production preparation must be done at least six months in advance,and accurate long-term influenza forecasting is essential for this.Although diverse machine learning models have been proposed for influenza forecasting,they focus on short-term forecasting,and their performance is too dependent on input variables.For a country’s longterm influenza forecasting,typical surveillance data are known to be more effective than diverse external data on the Internet.We propose a two-stage data selection scheme for worldwide surveillance data to construct a longterm forecasting model for influenza in the target country.In the first stage,using a simple forecasting model based on the country’s surveillance data,we measured the change in performance by adding surveillance data from other countries,shifted by up to 52 weeks.In the second stage,for each set of surveillance data sorted by accuracy,we incrementally added data as input if the data have a positive effect on the performance of the forecasting model in the first stage.Using the selected surveillance data,we trained a new longterm forecasting model for influenza and perform influenza forecasting for the target country.We conducted extensive experiments using six machine learning models for the three target countries to verify the effectiveness of the proposed method.We report some of the results.

Study of Holocene glacier degradation in central Asia by isotopic methods for long-term forecast of climate changes

This article presents a summary of our studies of Holocene moraines and glaciers of the Tien-Shan, Pamir, and Himalaya moun- mills with the purpose of providing pattern regularity of the Holocene glaciation decomposition. We developed a method for ob- taining reliable radiocarbon dating of moraines with the use of autochthonous organic matter dispersed in fine-grained morainic material, as well there were shown new possibilities of isotope-oxygen and isotope-uranium analysis for the Holocene glaciations dynamics. We found that Holocene glaciations disintegrate stadiaUy according to the decaying principle, and seven main stages may be distinguished. We achieved the absolute dating of the first three stages, identifying these periods as 8,000, 5,000, and 3,400 years ago. The application of the above-mentioned isotope methods of the Holocene glaciations and moraines study will allow re- searchers to improve the offered model of the Holocene glaciations disintegration; it will be great contribution to salvation of the problem of long-term climatic and glaciations forecast.

Long-Term Electricity Demand Forecasting for Malaysia Using Artificial Neural Networks in the Presence of Input and Model Uncertainties

Electricity demand is also known as load in electric power system.This article presents a Long-Term Load Forecasting(LTLF)approach for Malaysia.An Artificial Neural Network(ANN)of 5-layer Multi-Layered Perceptron(MLP)structure has been designed and tested for this purpose.Uncertainties of input variables and ANN model were introduced to obtain the prediction for years 2022 to 2030.Pearson correlation was used to examine the input variables for model construction.The analysis indicates that Primary Energy Supply(PES),population,Gross Domestic Product(GDP)and temperature are strongly correlated.The forecast results by the proposed method(henceforth referred to as UQ-SNN)were compared with the results obtained by a conventional Seasonal Auto-Regressive Integrated Moving Average(SARIMA)model.The R^(2)scores for UQ-SNN and SARIMA are 0.9994 and 0.9787,respectively,indicating that UQ-SNN is more accurate in capturing the non-linearity and the underlying relationships between the input and output variables.The proposed method can be easily extended to include other input variables to increase the model complexity and is suitable for LTLF.With the available input data,UQ-SNN predicts Malaysia will consume 207.22 TWh of electricity,with standard deviation(SD)of 6.10 TWh by 2030.

Clinical manifestations,diagnosis and long-term prognosis of adult autoimmune enteropathy:Experience from Peking Union Medical College Hospital

BACKGROUND Autoimmune enteropathy(AIE)is a rare disease whose diagnosis and long-term prognosis remain challenging,especially for adult AIE patients.AIM To improve overall understanding of this disease’s diagnosis and prognosis.METHODS We retrospectively analyzed the clinical,endoscopic and histopathological characteristics and prognoses of 16 adult AIE patients in our tertiary medical center between 2011 and 2023,whose diagnosis was based on the 2007 diagnostic criteria.RESULTS Diarrhea in AIE patients was characterized by secretory diarrhea.The common endoscopic manifestations were edema,villous blunting and mucosal hyperemia in the duodenum and ileum.Villous blunting(100%),deep crypt lymphocytic infiltration(67%),apoptotic bodies(50%),and mild intraepithelial lymphocytosis(69%)were observed in the duodenal biopsies.Moreover,there were other remarkable abnormalities,including reduced or absent goblet cells(duodenum 94%,ileum 62%),reduced or absent Paneth cells(duodenum 94%,ileum 69%)and neutrophil infiltration(duodenum 100%,ileum 69%).Our patients also fulfilled the 2018 diagnostic criteria but did not match the 2022 diagnostic criteria due to undetectable anti-enterocyte antibodies.All patients received glucocorticoid therapy as the initial medication,of which 14/16 patients achieved a clinical response in 5(IQR:3-20)days.Immunosuppressants were administered to 9 patients with indications of steroid dependence(6/9),steroid refractory status(2/9),or intensified maintenance medication(1/9).During the median of 20.5 months of followup,2 patients died from multiple organ failure,and 1 was diagnosed with non-Hodgkin’s lymphoma.The cumulative relapse-free survival rates were 62.5%,55.6%and 37.0%at 6 months,12 months and 48 months,respectively.CONCLUSION Certain histopathological findings,including a decrease or disappearance of goblet and Paneth cells in intestinal biopsies,might be potential diagnostic criteria for adult AIE.The long-term prognosis is still unsatisfactory despite corticosteroid and immunosuppressant medications,which highlights the need for early diagnosis and novel medications.

Nonlinear Differential Equation of Macroeconomic Dynamics for Long-Term Forecasting of Economic Development

In this article we derive a general differential equation that describes long-term economic growth in terms of cyclical and trend components. Equation is based on the model of non-linear accelerator of induced investment. A scheme is proposed for obtaining approximate solutions of nonlinear differential equation by splitting solution into the rapidly oscillating business cycles and slowly varying trend using Krylov-Bogoliubov-Mitropolsky averaging. Simplest modes of the economic system are described. Characteristics of the bifurcation point are found and bifurcation phenomenon is interpreted as loss of stability making the economic system available to structural change and accepting innovations. System being in a nonequilibrium state has a dynamics with self-sustained undamped oscillations. The model is verified with economic development of the US during the fifth Kondratieff cycle (1982-2010). Model adequately describes real process of economic growth in both quantitative and qualitative aspects. It is one of major results that the model gives a rough estimation of critical points of system stability loss and falling into a crisis recession. The model is used to forecast the macroeconomic dynamics of the US during the sixth Kondratieff cycle (2018-2050). For this forecast we use fixed production capital functional dependence on a long-term Kondratieff cycle and medium-term Juglar and Kuznets cycles. More accurate estimations of the time of crisis and recession are based on the model of accelerating log-periodic oscillations. The explosive growth of the prices of highly liquid commodities such as gold and oil is taken as real predictors of the global financial crisis. The second wave of crisis is expected to come in June 2011.

Non-crossing Quantile Regression Neural Network as a Calibration Tool for Ensemble Weather Forecasts

Despite the maturity of ensemble numerical weather prediction(NWP),the resulting forecasts are still,more often than not,under-dispersed.As such,forecast calibration tools have become popular.Among those tools,quantile regression(QR)is highly competitive in terms of both flexibility and predictive performance.Nevertheless,a long-standing problem of QR is quantile crossing,which greatly limits the interpretability of QR-calibrated forecasts.On this point,this study proposes a non-crossing quantile regression neural network(NCQRNN),for calibrating ensemble NWP forecasts into a set of reliable quantile forecasts without crossing.The overarching design principle of NCQRNN is to add on top of the conventional QRNN structure another hidden layer,which imposes a non-decreasing mapping between the combined output from nodes of the last hidden layer to the nodes of the output layer,through a triangular weight matrix with positive entries.The empirical part of the work considers a solar irradiance case study,in which four years of ensemble irradiance forecasts at seven locations,issued by the European Centre for Medium-Range Weather Forecasts,are calibrated via NCQRNN,as well as via an eclectic mix of benchmarking models,ranging from the naïve climatology to the state-of-the-art deep-learning and other non-crossing models.Formal and stringent forecast verification suggests that the forecasts post-processed via NCQRNN attain the maximum sharpness subject to calibration,amongst all competitors.Furthermore,the proposed conception to resolve quantile crossing is remarkably simple yet general,and thus has broad applicability as it can be integrated with many shallow-and deep-learning-based neural networks.

Short-Term and Long-Term Price Forecasting Models for the Future Exchange of Mongolian Natural Sea Buckthorn Market

Sea buckthorn market floated uncertainly within a narrow range. The market situation provided upward pressure on prices, and producer and consumer interest were poor, coupled with weak prices in the regional markets. The objectives of the study are: 1) to estimate the relationship between wild Sea buckthorn (SB) price and Supply, Demand, while some other factors of crude oil price and exchange rate by using simultaneous Supply-Demand and Price system equation and Vector Error Correction Method (VECM);2) to forecast the short-term and long-term SB price;3) to compare and evaluate the price forecasting models. Firstly, the data was analyzed by Ferris and Engle-Granger’s procedure;secondly, both price forecasting methodologies were tested by Pindyck-Rubinfeld and Makridakis’s procedure. The result shows that the VECM model is more efficient using yearly data;a short-term price forecast decreases, and a long-term price forecast is predicted to increase the Mongolian Sea buckthorn market.

Short and Long-Term Time Series Forecasting Stochastic Analysis for Slow Dynamic Processes

This paper intends to develop suitable methods to provide likely scenarios in order to support decision making for slow dynamic processes such as the underlying of agribusiness. A new method to analyze the short- and long-term time series forecast and to model the behavior of the underlying process using nonlinear artificial neural networks (ANN) is presented. The algorithm can effectively forecast the time-series data by stochastic analysis (Monte Carlo) of its future behavior using fractional Gaussian noise (fGn). The algorithm was used to forecast country risk time series for several countries, both for short term that is 30 days ahead and long term 350 days ahead scenarios.