Study on Ann-Based Multi-Step Prediction Model of Short-Term Climatic Variation

In the context of 1905–1995 series from Nanjing and Hangzhou, study is undertaken of estab-lishing a predictive model of annual mean temperature in 1996–2005 to come over the Changjiang (Yangtze River) delta region through mean generating function and artificial neural network in combination. Results show that the established model yields mean error of 0.45°C for their abso-lute values of annual mean temperature from 10 yearly independent samples (1986–1995) and the difference between the mean predictions and related measurements is 0.156°C. The developed model is found superior to a mean generating function regression model both in historical data fit-ting and independent sample prediction. Key words Climate trend prediction. Mean generating function (MGF) - Artificial neural network (ANN) - Annual mean temperature (AMT)

A modified stochastic model for LS+AR hybrid method and its application in polar motion short-term prediction

Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currently,least squares(LS)+auto-regressive(AR)hybrid method is one of the main techniques of PM prediction.Besides,the weighted LS+AR hybrid method performs well for PM short-term prediction.However,the corresponding covariance information of LS fitting residuals deserves further exploration in the AR model.In this study,we have derived a modified stochastic model for the LS+AR hybrid method,namely the weighted LS+weighted AR hybrid method.By using the PM data products of IERS EOP 14 C04,the numerical results indicate that for PM short-term forecasting,the proposed weighted LS+weighted AR hybrid method shows an advantage over both the LS+AR hybrid method and the weighted LS+AR hybrid method.Compared to the mean absolute errors(MAEs)of PMX/PMY sho rt-term prediction of the LS+AR hybrid method and the weighted LS+AR hybrid method,the weighted LS+weighted AR hybrid method shows average improvements of 6.61%/12.08%and 0.24%/11.65%,respectively.Besides,for the slopes of the linear regression lines fitted to the errors of each method,the growth of the prediction error of the proposed method is slower than that of the other two methods.

A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.

An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

Transformer-based correction scheme for short-term bus load prediction in holidays

To tackle the problem of inaccurate short-term bus load prediction,especially during holidays,a Transformer-based scheme with tailored architectural enhancements is proposed.First,the input data are clustered to reduce complexity and capture inherent characteristics more effectively.Gated residual connections are then employed to selectively propagate salient features across layers,while an attention mechanism focuses on identifying prominent patterns in multivariate time-series data.Ultimately,a pre-trained structure is incorporated to reduce computational complexity.Experimental results based on extensive data show that the proposed scheme achieves improved prediction accuracy over comparative algorithms by at least 32.00%consistently across all buses evaluated,and the fitting effect of holiday load curves is outstanding.Meanwhile,the pre-trained structure drastically reduces the training time of the proposed algorithm by more than 65.75%.The proposed scheme can efficiently predict bus load results while enhancing robustness for holiday predictions,making it better adapted to real-world prediction scenarios.

Research on the IL-Bagging-DHKELM Short-Term Wind Power Prediction Algorithm Based on Error AP Clustering Analysis

With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.

Development and validation of a circulating tumor DNA-based optimization-prediction model for short-term postoperative recurrence of endometrial cancer

BACKGROUND Endometrial cancer(EC)is a common gynecological malignancy that typically requires prompt surgical intervention;however,the advantage of surgical management is limited by the high postoperative recurrence rates and adverse outcomes.Previous studies have highlighted the prognostic potential of circulating tumor DNA(ctDNA)monitoring for minimal residual disease in patients with EC.AIM To develop and validate an optimized ctDNA-based model for predicting shortterm postoperative EC recurrence.METHODS We retrospectively analyzed 294 EC patients treated surgically from 2015-2019 to devise a short-term recurrence prediction model,which was validated on 143 EC patients operated between 2020 and 2021.Prognostic factors were identified using univariate Cox,Lasso,and multivariate Cox regressions.A nomogram was created to predict the 1,1.5,and 2-year recurrence-free survival(RFS).Model performance was assessed via receiver operating characteristic(ROC),calibration,and decision curve analyses(DCA),leading to a recurrence risk stratification system.RESULTS Based on the regression analysis and the nomogram created,patients with postoperative ctDNA-negativity,postoperative carcinoembryonic antigen 125(CA125)levels of<19 U/mL,and grade G1 tumors had improved RFS after surgery.The nomogram’s efficacy for recurrence prediction was confirmed through ROC analysis,calibration curves,and DCA methods,highlighting its high accuracy and clinical utility.Furthermore,using the nomogram,the patients were successfully classified into three risk subgroups.CONCLUSION The nomogram accurately predicted RFS after EC surgery at 1,1.5,and 2 years.This model will help clinicians personalize treatments,stratify risks,and enhance clinical outcomes for patients with EC.

Short-term train arrival delay prediction:a data-driven approach

Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and accurate train delay predictions,facilitated by data-driven neural network models,can significantly reduce dispatcher stress and improve adjustment plans.Leveraging current train operation data,these models enable swift and precise predictions,addressing challenges posed by train delays in high-speed rail networks during unforeseen events.Design/methodology/approach-This paper proposes CBLA-net,a neural network architecture for predicting late arrival times.It combines CNN,Bi-LSTM,and attention mechanisms to extract features,handle time series data,and enhance information utilization.Trained on operational data from the Beijing-Tianjin line,it predicts the late arrival time of a target train at the next station using multidimensional input data from the target and preceding trains.Findings-This study evaluates our model’s predictive performance using two data approaches:one considering full data and another focusing only on late arrivals.Results show precise and rapid predictions.Training with full data achieves aMAEof approximately 0.54 minutes and a RMSEof 0.65 minutes,surpassing the model trained solely on delay data(MAE:is about 1.02 min,RMSE:is about 1.52 min).Despite superior overall performance with full data,the model excels at predicting delays exceeding 15 minutes when trained exclusively on late arrivals.For enhanced adaptability to real-world train operations,training with full data is recommended.Originality/value-This paper introduces a novel neural network model,CBLA-net,for predicting train delay times.It innovatively compares and analyzes the model’s performance using both full data and delay data formats.Additionally,the evaluation of the network’s predictive capabilities considers different scenarios,providing a comprehensive demonstration of the model’s predictive performance.

A Short-Term Climate Prediction Model Based on a Modular Fuzzy Neural Network

In terms of the modular fuzzy neural network (MFNN) combining fuzzy c-mean (FCM) cluster and single-layer neural network, a short-term climate prediction model is developed. It is found from modeling results that the MFNN model for short-term climate prediction has advantages of simple structure, no hidden layer and stable network parameters because of the assembling of sound functions of the self-adaptive learning, association and fuzzy information processing of fuzzy mathematics and neural network methods. The case computational results of Guangxi flood season (JJA) rainfall show that the mean absolute error (MAE) and mean relative error (MRE) of the prediction during 1998-2002 are 68.8 mm and 9.78%, and in comparison with the regression method, under the conditions of the same predictors and period they are 97.8 mm and 12.28% respectively. Furthermore, it is also found from the stability analysis of the modular model that the change of the prediction results of independent samples with training times in the stably convergent interval of the model is less than 1.3 mm. The obvious oscillation phenomenon of prediction results with training times, such as in the common back-propagation neural network (BPNN) model, does not occur, indicating a better practical application potential of the MFNN model.

Progress and Challenge of the Short-Term Climate Prediction

The experience of developing a short-term climate prediction system at the Institute of Atmospheric Science of the Chinese Academy of Sciences is summarized,and some problems to be solved in future are discussed in this paper.It is suggested that a good system for short-term climate prediction should at least consist of (1) well-tested model(s),(2) sufficient data and good methods for the initialization and assimilation,(3) a good system for quantitative corrections,(4) a good ensemble prediction method,and (5) appropriate prediction products,such as mathematical expectation,standard deviation,probability,among others.

Distribution Prediction of Suitable Growth Area for Eucommia ulmoides in China under Climatic Change Background

[ Objective] The research aimed to study distribution prediction of suitable growth area for Eucommia ulmoides in China under climatic change background. [ Method] By using the maximum entropy model and many kinds of climate change scenarios, we predicted current and future distribution pattems of suitable growth area for Eucommia ulmoides in China and its change process. [ Result ] At present, highly suitable growth area of E. ulmoides mainly distributed in Sichuan, Shaanxi and Chongqing, Under climate change background, total suitable growth areas in future three decades all drastically reduced when compared with that at present. It was noteworthy that moderately and highly suitable growth areas of wild E. ulmoides all disappeared, and junction between Shaanxi and Gansu and Taibai Mountain would be stable suitable growth area of wild E. ulmoides. [ Condusioa] The research could provide useful reference data for investigation, protection and sustainable development of the wild E. ulmoides resources.

EXPERIMENTS WITH SHORT-TERM CLIMATE PREDICTION MODELS ON SSTA OVER THE NINO OCEANIC REGION

Predictions of averaged SST monthly anomalous series for Nino 1-4 regions in the context of auto-adaptive filter are made using a model combining the singular spectrum analysis (SSA) and auto-regression (AR). The results have shown that the scheme is efticient in forward forecaning of the strong ENSO event in 1997- 1998, it is of high reliability in retrospective forecasting of three corresponding historical strong ENSO events. It is seen that the scheme has stable skill and large accuracy for experiments of both independent samples and real cases.With modifications, the SSA-AR scheme is expected to become an efficient model in routine predictions of ENSO.

Recent Researches on the Short-Term Climate Prediction at IAP-A Brief Review

Studies on the seasonal to extraseasonal climate prediction at the Institute of Atmospheric Physics (IAP) in recent years were reviewed. The first short-term climate prediction experiment was carried out based on the atmospheric general circulation model (AGCM) coupled to a tropical Pacific oceanic general circulation model (OGCM) In 1997, an ENSO prediction system including an oceanic initialization scheme was set up. At the same time, researches on the SST-induced climate predictability over East Asia were made. Based on the blennial signal in the interannual climate variability, an effective method was proposed for correcting the model predicted results recently In order to consider the impacts of the initial soil mois- ture anomalies, an empirical scheme was designed to compute the soil moisture by use of the atmospheric quantities like temperature, precipitation, and so on. Sets of prediction experiments were carried out to study the impacts of SST and the initial atmospheric conditinns on the flood occurring over China in 1998.

SHORT-TERM CLIMATE CHANGE AND ITS CAUSE AND CLIMATE PREDICTION IN CHINA

ＳＨＯＲＴ－ＴＥＲＭＣＬＩＭＡＴＥＣＨＡＮＧＥＡＮＤＩＴＳＣＡＵＳＥＡＮＤＣＬＩＭＡＴＥＰＲＥＤＩＣＴＩＯＮＩＮＣＨＩＮＡ￥ＷｅｉＦｅｎｇｙｉｎｇ（魏凤英）（ＩｎｓｔｉｔｕｔｅｏｆＳｙｎｏｐｔｉｃａｎｄＤｙｎａｍｉｃＭｅｔｅｏｒｏｌｏｇｙ．）Ｂｅｉｊ...

Prediction of Climate Change in Yangtze-Huaihe Region under the Background of Global Warming

Based on the prediction results of over twenty new climate models provided by Intergovernmental Panel on Climate Change(IPCC) ,the climate change trends in Yangtze-Huaihe region during 2011-2100 were analyzed under the SRES A1B scenario. The results showed that annual mean temperature in Yangtze-Huaihe region would go up gradually under the background of global warming,and temperature increase rose from southeast to northwest,while annual average temperature would increase by 3.3 ℃ in the late 20th century. Meanwhile,annual average precipitation would rise persistently,and precipitation increase would go up with the increase of latitude and the lapse of time,being obviously strengthened after 2041.

Multi-Year Simulations and Experimental Seasonal Predictions for Rainy Seasons in China by Using a Nested Regional Climate Model (RegCM_NCC) Part Ⅱ:The Experimental Seasonal Prediction

A nested regional climate model has been experimentally used in the seasonal prediction at the China National Climate Center （NCC） since 2001. The NCC/IAP （Institute of Atmospheric Physics） T63 coupled GCM （CGCM） provides the boundary and initial conditions for driving the regional climate model （RegCM_NCC）. The latter has a 60-km horizontal resolution and improved physical parameterization schemes including the mass flux cumulus parameterization scheme, the turbulent kinetic energy closure scheme （TKE） and an improved land process model （LPM）. The large-scale terrain features such as the Tibetan Plateau are included in the larger domain to produce the topographic forcing on the rain-producing systems. A sensitivity study of the East Asian climate with regard to the above physical processes has been presented in the first part of the present paper. This is the second part, as a continuation of Part Ⅰ. In order to verify the performance of the nested regional climate model, a ten-year simulation driven by NCEP reanalysis datasets has been made to explore the performance of the East Asian climate simulation and to identify the model＇s systematic errors. At the same time, comparative simulation experiments for 5 years between the RegCM2 and RegCM_NCC have been done to further understand their differences in simulation performance. Also, a ten-year hindcast （1991-2000） for summer （June-August）, the rainy season in China, has been undertaken. The preliminary results have shown that the RegCM_NCC is capable of predicting the major seasonal rain belts. The best predicted regions with high anomaly correlation coefficient （ACC） are located in the eastern part of West China, in Northeast China and in North China, where the CGCM has maximum prediction skill as well. This fact may reflect the importance of the largescale forcing. One significant improvement of the prediction derived from RegCM_NCC is the increase of ACC in the Yangtze River valley where the CGCM has a very low, even a negative, ACC. The reason behind this improvement is likely to be related to the more realistic representation of the large-scale terrain features of the Tibetan Plateau. Presumably, many rain-producing systems may be generated over or near the Tibetan Plateau and may then move eastward along the Yangtze River basin steered by upper-level westerly airflow, thus leading to enhancement of rainfalls in the mid and lower basins of the Yangtze River. The real-time experimental predictions for summer in 2001, 2002, 2003 and 2004 by using this nested RegCM-NCC were made. The results are basically reasonable compared with the observations.

A Review of Seasonal Climate Prediction Research in China

The ultimate goal of climate research is to produce climate predictions on various time scales. In China, efforts to predict the climate started in the 1930 s. Experimental operational climate forecasts have been performed since the late 1950 s,based on historical analog circulation patterns. However, due to the inherent complexity of climate variability, the forecasts produced at that time were fairly inaccurate. Only from the late 1980 s has seasonal climate prediction experienced substantial progress, when the Tropical Ocean and Global Atmosphere project of the World Climate Research program（WCRP） was launched. This paper, following a brief description of the history of seasonal climate prediction research, provides an overview of these studies in China. Processes and factors associated with the climate variability and predictability are discussed based on the literature published by Chinese scientists. These studies in China mirror aspects of the climate research effort made in other parts of the world over the past several decades, and are particularly associated with monsoon research in East Asia. As the climate warms, climate extremes, their frequency, and intensity are projected to change, with a large possibility that they will increase. Thus, seasonal climate prediction is even more important for China in order to effectively mitigate disasters produced by climate extremes, such as frequent floods, droughts, and the heavy frozen rain events of South China.

The Prediction of Non-stationary Climate Series Based on Empirical Mode Decomposition

This paper proposes a new approach which we refer to as ＂segregated prediction＂ to predict climate time series which are nonstationary. This approach is based on the empirical mode decomposition method （EMD）, which can decompose a time signal into a finite and usually small number of basic oscillatory components. To test the capabilities of this approach, some prediction experiments are carried out for several climate time series. The experimental results show that this approach can decompose the nonstationarity of the climate time series and segregate nonlinear interactions between the different mode components, which thereby is able to improve prediction accuracy of these original climate time series.

The Predictability Problems in Numerical Weather and Climate Prediction

The uncertainties caused by the errors of the initial states and the parameters in the numerical model are investigated. Three problems of predictability in numerical weather and climate prediction are proposed, which are related to the maximum predictable time, the maximum prediction error, and the maximum admissible errors of the initial values and the parameters in the model respectively. The three problems are then formulated into nonlinear optimization problems. Effective approaches to deal with these nonlinear optimization problems are provided. The Lorenz’ model is employed to demonstrate how to use these ideas in dealing with these three problems.

Probabilistic Multimodel Ensemble Prediction of Decadal Variability of East Asian Surface Air Temperature Based on IPCC-AR5 Near-term Climate Simulations

Based on near-term climate simulations for IPCC-AR5 （The Fifth Assessment Report）, probabilistic multimodel ensemble prediction （PMME） of decadal variability of surface air temperature in East Asia （20°-50°N, 100°- 145°E） was conducted using the multivariate Gaussian ensemble kernel dressing （GED） methodology. The ensemble system exhibited high performance in hindcasting the deeadal （1981-2010） mean and trend of temperature anomalies with respect to 1961-90, with a RPS of 0.94 and 0.88 respectively. The interpretation of PMME for future decades （2006-35） over East Asia was made on the basis of the bivariate probability density of the mean and trend. The results showed that, under the RCP4.5 （Representative Concentration Pathway 4.5 W m-2） scenario, the annual mean temperature increases on average by about 1.1-1.2 K and the temperature trend reaches 0.6-0.7 K （30 yr）-1. The pattern for both quantities was found to be that the temperature increase will be less intense in the south. While the temperature increase in terms of the 30-yr mean was found to be virtually certain, the results for the 30-yr trend showed an almost 25% chance of a negative value. This indicated that, using a multimodel ensemble system, even if a longer-term warming exists for 2006-35 over East Asia, the trend for temperature may produce a negative value. Temperature was found to be more affected by seasonal variability, with the increase in temperature over East Asia more intense in autumn （mainly）, faster in summer to the west of 115°E, and faster still in autumn to the east of 115°E.