Analysis of Characteristics of the Forecast Jump in the NCEP Ensemble Forecast Products

The limit of numerical prediction and ensemble prediction can be further understood by the study of the forecast jump. By using the ensemble average forecast and control forecast product output data for the United States National Environmental Prediction Center (NCEP) global ensemble forecast system (GEFS), and the concept of Jumpiness index from Zsoter et al., we analyzed the statistical characteristics of forecast jump. Results show that, on average, in the NCEP ensemble forecast product, the time average prediction jump index increases with the increase of the forecast aging, and the actual forecast experience can reflect this phenomenon. The consistency of ensemble average forecast is better than the corresponding control forecast. Also, in summer, the frequency of “forecast jump” phenomenon is fluctuating by 17.5%.

Better use of experience from other reservoirs for accurate production forecasting by learn-to-learn method

To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intuitively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.

Forecasting of China's natural gas production and its policy implications

With the vigorous promotion of energy conservation and implementation of clean energy strategies,China＇s natural gas industry has entered a rapid development phase,and natural gas is playing an increasingly important role in China＇s energy structure.This paper uses a Generalized Weng model to forecast Chinese regional natural gas production,where accuracy and reasonableness compared with other predictions are enhanced by taking remaining estimated recoverable resources as a criterion.The forecast shows that China＇s natural gas production will maintain a rapid growth with peak gas of 323 billion cubic meters a year coming in 2036;in 2020,natural gas production will surpass that of oil to become a more important source of energy.Natural gas will play an important role in optimizing China＇s energy consumption structure and will be a strategic replacement of oil.This will require that exploration and development of conventional natural gas is highly valued and its industrial development to be reasonably planned.As well,full use should be made of domestic and international markets.Initiative should also be taken in the exploration and development of unconventional and deepwater gas,which shall form a complement to the development of China＇s conventional natural gas industry.

Interpretation of EC Fine Grid Numerical Prediction Products in the Forecast of Frozen Fog in Urumqi Airport

In this paper, Urumqi Airport time-lapse ground man-made observation data from November 2015 to February 2017, European fine grid (0.25 × 0.25) initial field (20 o’clock) and the forecast field within 24 hours were utilized. From November 2015 to February 2016, the relevant materials were used as research samples (a total of 948 times), and from November 2016 to February 2017 as test samples (a total of 922 times), statistical methods were used to establish the scoring standards. And each relevant element was scored. After the score, the score level range was delineated, and the visibility forecast was performed according to the scope. The conclusions are as follows: 1) European fine grid forecast products are with good correspondence with the visibility of this field are 850 hPa and 2 m high temperature inversion, 850 hPa relative humidity and 850 hPa wind field over the field. 2) Through the statistical analysis of scores, it is defined that the score below 400 is level 4, the score above 1000 is level 1, the difference is significant, and the forecast indication is strong. Level 2 and level 3 are more evenly distributed, with no more concentrated fractions. 3) Applying the test sample to test the above indicators. The forecast accuracy of level 1 is 61.2%, and the forecast accuracy of level 4 is 97.2%, so level 1 and level 4 are expected to obtain better forecast results, which is of practical application value.

Analysis and Forecast of MSW Production Based on the ARIMA Model in Beijing

Based on the data of MSW generation in Beijing from 2004 to 2012,an ARIMA model of time series analysis was established. By contrast of the modeling results of different yearly data,the forecast period was identified to be 10 years. The yearly production of MSW from 2015 to 2025 was forecasted by using SPSS 16. 0 software. Result shows that the forecasting effect of ARIMA( 1,0,1) model is relatively good,and it can be applied to prediction of MSW production in Beijing. In the next 10 years,the amount of MSW produced in Beijing is increasing,but the growth rate is not large. Is expected to 2025,the production of MSW will reach more than 9 million tons. Taking into account the MSW return,it is inferred that the production of MSW in Beijing in 2025 will be close to 10 million tons. In order to reduce the pressure of subsequent waste disposal facilities in Beijing,the government can increase the intensity of the recycling of waste materials.

Risk-opportunity analyses and production peak forecasting on world conventional oil and gas perspectives

To investigate the situation of conventional oil and gas, this paper examines the global oil and gas discoveries, proved reserves, production, consumption and price. All the influencing factors can be subjected to risk and opportunity analyses, so in the paper, we build upon a risk-opportunity analysis framework, which is a new train of thought. To forecast the peak time of oil and gas production, we used the methods of multi-Hubbert model forecasting and data forecasting. Our results showed that the world oil production will reach a peak between 2010 and 2015 and the gas production will reach a peak around 2030 Oil peak is coming and gas peak is on the way. The main purpose of forecasting oil and gas production peak is give people enough time for preparing mitigation and adaptation plans. This means taking decisive action well before the problem is obvious.

A Dynamic Forecasting System with Applications in Production Logistics

Production logistics involve the co-ordination of ac tivities such as production and materials control (PMC), inventory management, p roduct life cycle management, etc. Those activities demand for an accurate forec asting model. However, the conventional methods of making sell and buy decision based on human forecast or conventional moving average and exponential smoothing methods is no longer be sufficient to meet the future need. Furthermore, the un derlying statistics of the market information change from time to time due to a number of reasons such as change of global economic environment, government poli cies and business risks. This demands for highly adaptive forecasting model which is robust enough to response and adapt well to the fast changes in the dat a characteristics, in other words, the trajectory of the "dynamic characteristic s" of the data. In this paper, an adaptive time-series modelling method was proposed for short -term dynamic forecasting. The method employs an autoregressive (AR) time-seri es model to carry out the forecasting process. A modified least mean square (MLM S) adaptive filter algorithm was established for adjusting the AR model coeffici ents so as to minimise the sum of squared of forecasting errors. A prototype dyn amic forecasting system was built based on the adaptive time-series modelling m ethod. Basically, the dynamic forecasting system can be divided into two phases, i.e. the Learning Phase and the Application Phase. The learning procedures star t with the determination of upper limit of the adaptation gain based on the conv ergence in the mean square criterion. Hence, the optimum ELMS filter parameters are determined using an iteration algorithm which changes each filter parameter i.e. the order, the adaptation gain andthe values initial coefficient vector on e by one inside a predetermined iteration range. The set of parameters which giv es the minimum value for sum of squared errors within the iteration range is sel ected as the optimum set of filter parameters. In the Application Phase, the sys tem is operated under a real-time environment. The sampled data is processed by the optimised ELMS filter and the forecasted data are calculated based on the a daptive time-series model. The error of forecasting is continuously monitored w ithin the predefined tolerance. When the system detects excessive forecasting er ror, a feedback alarm signal was issued for system re-calibration. Experimental results indicated that the convergence rate and sum of squared erro rs during initial adaptation could be significantly improved using the MLMS algorithm. The performance of the system was verified through a series of experi ments conducted on the forecast of materials demand and costing in productio n logistics. Satisfactory results were achieved with the forecast errors confini ng within in most instances. Further applications of the system can be found i n sales demand forecast, inventory management as well as collaborative planning, forecast and replenishment (CPFR) in logistics engineering.

Production Forecast of Citrus in China and Production and Marketing Situation of Citrus in Chongqing in 2016 Production Season

According to the statistics of the Ministry of Agriculture,the planting area of citrus would increase steadily,and the yield would decline slightly,2. 556 7 million ha and 36. 168 million t,respectively. Compared with 2015,the planting area would increase by 1. 97% and the yield would increase by 1. 17%. According to the production scheduling of Chongqing Agricultural Commission,the citrus production in Chongqing in 2016 would continue to maintain a steady and rapid growth,the estimated area and yield were 0. 206 7 million ha and 2. 8 million t,increasing by 4. 27% and 4. 48% compared with 2015 respectively. By the end of November 2016,most of mature citrus products in Chongqing would show different degree of rise in purchasing price,while the purchasing price of red orange and some processed raw material fruits would show different amplitude of decline. On the whole,the production and marketing situation of Chongqing citrus would become better.

How much Numerical Products Affect Weather Forecasting

The paper shows how much improvement can be achieved in weather forecasting by using NWP products. And for weather element forecasts, the types and number of NWP products highly impact on the quality of MOS forecasts and other utilities.

Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection

As the conventional prediction methods for production of waterflooding reservoirs have some drawbacks, a production forecasting model based on artificial neural network was proposed, the simulation process by this method was presented, and some examples were illustrated. A workflow that involves a physics-based extraction of features was proposed for fluid production forecasting to improve the prediction effect. The Bayesian regularization algorithm was selected as the training algorithm of the model. This algorithm, although taking longer time, can better generalize oil, gas and water production data sets. The model was evaluated by calculating mean square error and determination coefficient, drawing error distribution histogram and the cross-plot between simulation data and verification data etc. The model structure was trained, validated and tested with 90% of the historical data, and blindly evaluated using the remaining. The predictive model consumes minimal information and computational cost and is capable of predicting fluid production rate with a coefficient of determination of more than 0.9, which has the simulation results consistent with the practical data.

Forecasting on Indonesian Coal Production and Future Extraction Cost: A Tool for Formulating Policy on Coal Marketing

Since 2011 Indonesia has become the world’s largest exporter of steam coal. Two supporting factors of Indonesia to be the largest exporter are its enormous production and low operating cost. This paper foresees the production and extraction cost of Indonesian coal in the coming period to evaluate marketing policies and estimate the cost of Indonesian coal supply in domestic market as well as in export market. The production forecasting is carried out by Gompertz curve. Peak production of Indonesian coal is expected to take place in 2026. Moreover, the extraction cost in coal basins which produce high calorific value of coal, in accordance to the operating cost forecasting, is higher than the one with low calorific value of coal due to its higher stripping ratio. Three main basins of Central Sumatra, Tarakan, and Barito basins play major rule in supplying coal for domestic use in short term. And other coal basins such as South Sumatra, Kutai, Bengkulu, and Ombilin basins provide long term supply in the domestic and export markets.

Forecasting solar still performance from conventional weather data variation by machine learning method

Solar stills are considered an effective method to solve the scarcity of drinkable water.However,it is still missing a way to forecast its production.Herein,it is proposed that a convenient forecasting model which just needs to input the conventional weather forecasting data.The model is established by using machine learning methods of random forest and optimized by Bayesian algorithm.The required data to train the model are obtained from daily measurements lasting9 months.To validate the accuracy model,the determination coefficients of two types of solar stills are calculated as 0.935and 0.929,respectively,which are much higher than the value of both multiple linear regression(0.767)and the traditional models(0.829 and 0.847).Moreover,by applying the model,we predicted the freshwater production of four cities in China.The predicted production is approved to be reliable by a high value of correlation(0.868)between the predicted production and the solar insolation.With the help of the forecasting model,it would greatly promote the global application of solar stills.

Research on the Forecast of Grain Production in Henan Province from 2010 to 2015

According to the latest amended agricultural economic statistical data from 1996 to 2009 in Henan Statistical Yearbook-2010,by selecting and establishing the optimized grey model of logarithmic new developed coefficient, we conduct the empirical analysis and forecast research on the grain output and the relevant main economic indices in Henan Province from 2010 to 2015. The results show that the grain output of Henan Province in 2010 will reach 54.896 9 million tons, and it will break through 60 million tons at 60.17 million tons in 2015. In years ahead, the grain output of Henan Province will develop to a new stage steadily, which guarantees the national grain supply and socio-economic sustainable development forcibly.

Forecast of Grain Production of China during the Twelfth Five-Year Plan Period

According to the latest revised agricultural economic statistical data in China Statistical Yearbook-2010,by selecting and establishing the square root-treated grey model,the empirical analysis and forecast research on the grain output of China from 2011 to 2015 are conducted.The results show that the grain output of China in 2011 will reach 557.739 million tons,and it will break through 600 million tons at 605.617 million tons in 2015.The persistent and stable grain output will ensure that the national economy develops in normal during the twelfth five-year plan period and remit the world grain crisis efficiently;meanwhile,the problem of exorbitant grain prices should be remitted in some level.

Status of China's Refined Oil Products Consumption and Forecast on Demand During the“11th Five-Year Plan”Period

作者在这工业使用了二个普通方法，我。e。“消费系数方法”和“弹性系数趋势方法”，在 2010 预报精制的油产品需求。通过分析并且比较二预报结果，对在 2010 的完成的产品油的要求一年将在 220 ～ 240 百万吨的范围，这被投射。另外，从关于总数的担心给产品消费上油在 2020 超过 6 亿吨 / 年，作者提出针对油产品的保存和其他的燃料的申请的建议和措施。

Interrupted Time Series Analysis of Military and Civilian Regimes in Nigeria: A Statistical Evidence from Gross Domestic Product (GDP)

Governments influence the economy by changing the level and types of taxes, the extent and composition of spending, and the degree and form of borrowing. Governments directly and indirectly influence the way resources are used in the economy. Higher taxes, fees, and greater regulations can stymie businesses or entire industries and the resulting impact is reflected on the country’s economy status (strong or weak). The growth rate of GDP is often used as an indicator of the general health of the economy. In broad terms, an increase in real GDP is interpreted as a sign that the economy is doing well. So it is important to study and pay more attention to country’s GDP growth rate. In this paper, an intervention analysis approach was applied to Nigeria GDP data in order to evaluate the performances of military and civilian rules in the country. Data on Nigeria GDP were collected and subjected to interrupted (intervention) time series model. Based on the Alkaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and sigma2 values, the interrupted time series model ARIMA (1, 1, 0) with exogenous variables (per capita per capita GDP, intervention, year and yearAfter) was identified as the best model amongst other competing models. It was observed that the intervention (civilian rule) was significant at the 10% level of significance in increasing the Nigeria GDP by 10B US$ on the average since 2005 till 2021 while controlling for the effects of other determinants. Also, the ARIMA (1, 1, 0) forecasts indicate that the Nigeria GDP will continue increasing during the civilian rule. As a result, changing from military rule to civilian rule in Nigeria significantly increased the GDP of the country.

Interrupted Time Series Analysis of Military and Civilian Regimes in Nigeria: A Statistical Evidence from Gross Domestic Product (GDP)

Governments influence the economy by changing the level and types of taxes, the extent and composition of spending, and the degree and form of borrowing. Governments directly and indirectly influence the way resources are used in the economy. Higher taxes, fees, and greater regulations can stymie businesses or entire industries and the resulting impact is reflected on the country’s economy status (strong or weak). The growth rate of GDP is often used as an indicator of the general health of the economy. In broad terms, an increase in real GDP is interpreted as a sign that the economy is doing well. So it is important to study and pay more attention to country’s GDP growth rate. In this paper, an intervention analysis approach was applied to Nigeria GDP data in order to evaluate the performances of military and civilian rules in the country. Data on Nigeria GDP were collected and subjected to interrupted (intervention) time series model. Based on the Alkaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and sigma2 values, the interrupted time series model ARIMA (1, 1, 0) with exogenous variables (per capita per capita GDP, intervention, year and yearAfter) was identified as the best model amongst other competing models. It was observed that the intervention (civilian rule) was significant at the 10% level of significance in increasing the Nigeria GDP by 10B US$ on the average since 2005 till 2021 while controlling for the effects of other determinants. Also, the ARIMA (1, 1, 0) forecasts indicate that the Nigeria GDP will continue increasing during the civilian rule. As a result, changing from military rule to civilian rule in Nigeria significantly increased the GDP of the country.

A New Method for Forecasting the Life Test Data of Mechanical Products

The model for forecasting the test data on mechanical products is established in the application of the grey system theories. A new formula of the background value is introduced into the model. The result of an example shows the method can reduce test expense and enhance the precision of forecasting.

Boruta-Optuna-XGBoost融合模型的聚驱油田产量智能预测方法研究

在聚驱油田开采时,存在向油层中加注水溶性高分子聚合物的过程,此过程包含大量参数,对油田产量具有较大影响。针对传统油田产量预测方法存在的人工计算量大、准确率低的问题。提出一种Boruta-Optuna-XGBoost融合模型对聚驱油田产量进行预测,解决传统方法存在的问题。通过Boruta特征筛选方法进行聚驱油田特征筛选,降低特征冗余,提高特征相关性,避免模型过拟合;使用Optuna超参数优化算法对XGBoost进行自适应超参数评价,提高模型精度;使用最优超参的XGBoost算法对聚驱油田产量进行回归预测,通过算法建立油田注入参数和油田月产量之间的逻辑关系模型,对聚驱油田的月产量进行预测。所提方法应用在大庆油田的实际有效数据的准确率达95%,证明了方法的有效性,能够对油田的生产效益、资源配置和可持续发展产生影响,也为数字化聚驱油田智能产量预测发展提供了新思路。