Time Series Extrapolation Research Articles

Depth extrapolation of field-scale soil moisture time series derived with cosmic-ray neutron sensing (CRNS) using the soil moisture analytical relationship (SMAR) model

Depth extrapolation of field-scale soil moisture time series derived with cosmic-ray neutron sensing (CRNS) using the soil moisture analytical relationship (SMAR) model

HARMONIC ANALYSISIN INVENTORY MANAGEMENT IN LOGISTICSAND SUPPLY CHAINS

The article examines the possibilities of using harmonic analysis apparatus while planning the need in stocks of various categories. The issues of improving material planning (forecasting) are currently quite relevant applied tasks in business, and are also of interest in terms of developing the theory of logistics and supply chain management. Among the approaches to planning the need for inventory, a wide range of statistical theory methods are used in practice, among which two large groups can be distinguished, such as one-parameter time series analysis models for goods of stable and relatively stable demand, as well as correlation and regression models for chaotic consumption stocks. Most of the goods sold to end consumers have a seasonal component, which may not always be explicitly expressed in statistics. However, due to change of seasons, regular fluctuations in the values of consumption from the warehouse, around the average chronological or trend, may necessitate regular recalculation of the main parameters of inventory management models, such as maximum, insurance, threshold inventory levels, etc. In addition, sales statistics may contain fluctuations of a higher order if the stocks sold have life cycles of interest in goods on the market, which can also be attributed to periodic or quasi-periodic processes. One of the methods to formalize such cyclic processes can be trigonometric approximation or harmonic analysis, when the values of a time series are represented as terms of a Fourier series (harmonics) having corresponding amplitudes and phases. The article compares the effectiveness (accuracy) of forecasts of inventory requirements made using harmonic analysis and traditional time series extrapolation methods.

Forecasting changes in the balance of the country's energy supply system under the introduction of a Carbon Border Adjustment Mechanism

Subject. The article investigates the Carbon Border Adjustment Mechanism (CBAM) and implications of its implementation for the energy systems of countries with high carbon footprint. Objectives. The aim is to create a forecast of changes in the balance of the country's energy supply system, considering the gradual introduction of the CBAM with a decrease in the number of free permits for non-payment of declared emissions, and an increase in the coverage of emissions. Methods. The study employs methods of statistical analysis. Results. The study established that the introduction of the CBAM creates economic threats for exporting countries with a high carbon footprint. A national emissions trading system is a means of combating it. The paper shows that with the forecast price of carbon permits obtained on the basis of time series extrapolation, the introduction of a system of emission quotas will reduce losses in GDP and the total energy capacity of the country's energy system. Conclusions. The establishment of the system of emission quotas is a complex and lengthy process that requires the development and testing of economic and financial mechanisms.

Beyond point forecasts: Uncertainty quantification in tensor extrapolation for relational time series data

Contemporary data sets are frequently relational in nature. In retail, for example, data sets are more granular than traditional data, often indexing individual products, outlets, or even customers, rather than aggregating them at the group level. Tensor extrapolation aims to forecast relational time series data; it combines tensor decompositions and time series extrapolation. However, previous approaches to tensor extrapolation are restricted to point forecasts and fail to quantify the uncertainty associated with the forecasts. This paper provides prediction intervals within which we expect the true future values to lie with a specified probability. Numerical experiments suggest the effectiveness of the proposed method in terms of forecast performance. Moreover, the approach proves to be up to 77 times faster than the univariate competitor. For this reason, it exerts positive influence on both inclusiveness and the environment.

NEURAL ORDINARY DIFFERENTIAL EQUATIONS FOR TIME SERIES RECONSTRUCTION

Context. Neural Ordinary Differential Equations is a deep neural networks family that leverage numerical methods approaches for solving the problem of time series reconstruction, given small amount of unevenly distributed samples.
 Objective. The goal of the following research is the synthesis of a deep neural network that is able to solve input signal reconstruction and time series extrapolation task.
 Method. The proposed method exhibits the benefits of solving time series extrapolation task over forecasting one. A model that implements encoder-decoder architecture with differential equation solving in latent space, is proposed. The latter approach was proven to demonstrate outstanding performance in solving time series reconstruction task given a small percentage of noisy and uneven distributed input signals. The proposed Latent Ordinary Differential Equations Variational Autoencoder (LODE-VAE) model was benchmarked on synthetic non-stationary data with added white noise and randomly sampled with random intervals between each signal.
 Results. The proposed method was implemented via deep neural network to solve time series extrapolation task.
 Conclusions. The conducted experiments have confirmed that proposed model solves the given task effectively and is recommended to apply it to solving real-world problems that require reconstructing dynamics of non-stationary processes. The prospects for further research may include the process of computational optimization of proposed models, as well as conducting additional experiments involving different baselines, e. g. Generative Adversarial Networks or attention Networks.

Ultra-short-term load prediction of integrated energy system based on load similar fluctuation set classification

Due to the strong coupling characteristics and daily correlation characteristics of multiple load sequences, the prediction method based on time series extrapolation and combined with multiple load meteorological data has limited accuracy improvement, which is tested by the fluctuation of load sequences and the accuracy of Numerical Weather Prediction (NWP). This paper proposes a multiple load prediction method considering the coupling characteristics of multiple loads and the division of load similar fluctuation sets. Firstly, the coupling characteristics of multivariate loads are studied to explore the interaction relationship between multivariate loads and find out the priority of multivariate load prediction. Secondly, the similar fluctuating sets of loads are divided considering the similarity and fluctuation of load sequences. Thirdly, the load scenarios are divided by k-means clustering for the inter-set sequences of similar fluctuating sets, and the Bi-directional Long Short-Term Memory (BI-LSTM) models are trained separately for the sub-set of scenarios and prioritized by prediction. Finally, the effectiveness of the proposed method was verified by combining the multivariate load data provided by the Campus Metabolism system of Arizona State University.

Risk forecasting for the Russian economic sectors in the context of sanctions ramp-up

Subject. This article discusses the problems of the Russian economy stabilization and the international sanctions' peculiarities. Objectives. The article aims to define the forecast net foreign assets measure value impact on the level of financial risk for the Russian economy. Methods. For the study, I used a statistical analysis including the time series extrapolation method. Results. The article reveals that industries with a low percentage of import substitution are at the greatest risk if the sanctions ramp up. The article also confirms a steady downward trend in the net foreign assets value, which causes instability of the national currency exchange rate. Conclusions. Almost all sectors of the Russian economy are at risk of destabilization. The functioning of the economy in difficult conditions depends on the cohesion of the Government and business.

Tensor extrapolation: an adaptation to data sets with missing entries

BackgroundContemporary data sets are frequently relational in nature. In retail, for example, data sets are more granular than traditional data, often indexing individual products, outlets, or even users, rather than aggregating them at the group level. Tensor extrapolation is used to forecast relational time series data; it combines tensor decompositions and time series extrapolation. However, previous approaches to tensor extrapolation are restricted to complete data sets. This paper adapts tensor extrapolation to situations with missing entries and examines the method’s performance in terms of forecast accuracy.FindingsTo base the evaluation on time series with both diverse and controllable characteristics, the paper develops a synthetic data set closely related to the context of retailing. Calculations performed on these data demonstrate that tensor extrapolation outperforms the univariate baseline. Furthermore, a preparatory completion of the data set is not necessary. The higher the fraction of missing data, the greater the superiority of tensor extrapolation in terms of prediction error.ConclusionsForecasting plays a key role in the optimization of business processes and enables data-driven decision making. As such, tensor extrapolation should be part of the forecaster’s toolkit: Even if large parts of the data are missing, the proposed method is able to extract meaningful, latent structure, and to use this information in prediction.

Using Machine Learning Algorithms to Detect Anomalies in the Solar Heating System

This article explores the use of machine learning algorithms to identify anomalies in the solar heating system. A solar heating system that has been developed consists of several parts to simplify the description and modeling process. The authors propose a new architecture for neural networks based on ordinary differential equations. The idea is to apply the new architecture for practical problems of accident prediction (the problem of extrapolation of time series) and classification (classification of accidents based on historical data). The developed machine learning algorithms, artificial intelligence techniques, the theory of differential equations - these directions allow us to build a model for predicting the system's accident rate. The theory of database management (non-relational databases) - these systems allow you to establish the optimal storage of large time series.

Evolving Gaussian process kernels from elementary mathematical expressions for time series extrapolation

Choosing the best kernel is crucial in many Machine Learning applications. Gaussian Processes are a state-of-the-art technique for regression and classification that heavily relies on a kernel function. However, in the Gaussian Processes literature, kernels have usually been either ad hoc designed, selected from a predefined set, or searched for in a space of compositions of kernels which have been defined a priori. In this paper, we propose a Genetic Programming algorithm that represents a kernel function as a tree of elementary mathematical expressions. By means of this representation, a wider set of kernels can be modeled, where potentially better solutions can be found, although new challenges also arise. The proposed algorithm is able to overcome these difficulties and find kernels that accurately model the characteristics of the data. This method has been tested in several real-world time series extrapolation problems, improving the state-of-the-art results while reducing the complexity of the kernels.

Identifying and responding to outlier demand in revenue management

Revenue management strongly relies on accurate forecasts. Thus, when extraordinary events cause outlier demand, revenue management systems need to recognise this and adapt both forecast and controls. Many passenger transport service providers, such as railways and airlines, control the sale of tickets through revenue management. State-of-the-art systems in these industries rely on analyst expertise to identify outlier demand both online (within the booking horizon) and offline (in hindsight). So far, little research focuses on automating and evaluating the detection of outlier demand in this context. To remedy this, we propose a novel approach, which detects outliers using functional data analysis in combination with time series extrapolation. We evaluate the approach in a simulation framework, which generates outliers by varying the demand model. The results show that functional outlier detection yields better detection rates than alternative approaches for both online and offline analyses. Depending on the category of outliers, extrapolation further increases online detection performance. We also apply the procedure to a set of empirical data to demonstrate its practical implications. By evaluating the full feedback-driven system of forecast and optimisation, we generate insight on the asymmetric effects of positive and negative demand outliers. We show that identifying instances of outlier demand and adjusting the forecast in a timely fashion substantially increases revenue compared to what is earned when ignoring outliers.

A New Medium and Long-Term Power Load Forecasting Method Considering Policy Factors

At present, China’s power load development is facing a new situation in which policies such as the new economic norm, industrial structure adjustment, energy conservation and emission reduction, etc. are being deeply promoted, load growth in some areas begin to ease, and volatility of load gradually become prominent, which increases the difficulty of medium and long-term load forecasting. In this context, in view of multi-correlation, uncertainty of influence of policy factors on power load, in order to improve the accuracy of load forecasting under the influence of policy factors, and solve the problem that policy factors are ambiguous, difficult to be quantified, and difficult to be integrated into load forecasting model, a medium and long-term load forecasting model considering policy factors is proposed. First, by analyzing the influence of various policies on power load, a hierarchical policy influencing factor index system that combines macro and micro levels is constructed to systematically reflect the influence of economy and policies on load under the new situation. Then, in view of the traditional grey relational analysis model’s insufficient consideration of the difference of historical data and future power development situation, by respectively weighting historical periods and factor indexes, a quantification analysis model of power load influencing factors based on two-way weighted grey relational analysis is proposed to quantify the influence of various policy factors on power load, achieve the combination of subjective weighting and objective weighting,and obtain quantification weights. Finally, the weighted fuzzy cluster analysis method combined with weights is used to predict load under the influence of policy factors. The proposed model can better solve the difficulty of medium and long-term load forecasting caused by the volatility of load under the influence of policy factors, and is suitable for medium and long-term load forecasting under the background of policy changes. The analysis of calculation examples shows that compared with traditional grey relational analysis model, the quantification results of proposed methods are more realistic, compared with traditional prediction methods such as time series extrapolation and elasticity coefficient, proposed method has better prediction accuracy and engineering application value.

The Nature of Lean Manufacturing of Information Economic Products

In this article a research of the nature of modern enterprises development is presented, characterized by moving from material-based to information-based economic products. It was discovered that economically developed enterprises have almost exhausted their potential for further growth due to organizational improvements, previously affecting mainly the material part of the economic product. Therefore, studies on improving the efficiency of the production organization of information economic products are becoming more and more relevant.Purpose: the main purpose of this research is to develop extended principles of lean manufacturing of information economic products. To achieve this goal following tasks were resolved: material intensity analysis was implemented, the structure of information economic product (IEP) was examined, traditional principles of lean manufacturing were reviewed and expanded for information economic product creation.The object of the research are modern industrial enterprises that apply the concept of lean manufacturing or similar. The subject of the research are the principles of lean manufacturing for creating an information economic product.Methods: the time series extrapolation method and the empirical analysis method were used to calculate the material intensity index of products. Abstract and comparative analysis methods were applied to develop the extended principles of IEP lean manufacturing. In addition, methods of analysis and synthesis, the historical method, as well as elements of factor analysis were used for the study.Results: the material and information structure of the economic product is considered and proposed. The nature of the dynamics of its changes in the process of changing the stages of technological and economic development of scientific and technological progress is justified, which allowed us to argue the vector of changes in the structure of costs for creating a modern material product in terms of increasing information and reducing material components. The constantly rising costs of creating information increasingly characterize it as a market product that has its own cost structure, which gave reason to classify it as an information economic product (IEP). In this regard, the structure of the information economic product was studied and developed, based on the analysis of the term of "information" both from the perspective of the organization and operational management and from the perspective of related branches of knowledge. As a result of the comparative analysis, extended principles of IEP lean manufacturing were developed.Conclusions and Relevance: the analysis of the material intensity index revealed a tendency to a continuous decrease in the material intensity of the economic product and an increase in the information component. As a result of the study of the structure of the information economic product, it was revealed that the potential for increasing the economic efficiency of modern industrial enterprises is primarily laid in improving logical data processing. It is proposed to achieve this by using the developed extended principles of IEP lean manufacturing, among which the main one is the principle of intellectual and creative reciprocity.

On the equivalence of the forecast value construction in the “pyramidal” extrapolation method and cubic forecast

The paper is devoted to the new method of short time series extrapolation, which was developed in recent years and was called “pyramidal”. This method can be used for predicting the deterministic component of an arbitrary economic, environmental and geophysical parameters. Numerical results show significant advantages of the proposed method in comparison with approaches to extrapolate, based on the use of polynomials, including Newton’s extrapolation . In this paper we study the procedure for constructing the forecast value in accordance with the pyramidal method and show that it is equivalent to the cubic forecast.

Integration of Digital Image Correlation of Sentinel-2 Data and Continuous GNSS for Long-Term Slope Movements Monitoring in Moderately Rapid Landslides

This work explores the advantages and drawbacks of the application of Digital Image Correlation (DIC) to Sentinel-2 Multi Spectral Instrument (MSI) data in conjunction with continuous Global Navigation Satellite System (GNSS) monitoring. The goal is to retrieve a spatially distributed and long-term time-series of slope movements in large-scale moderately rapid landslides. The short revisit time of Sentinel-2 satellites (5 days since March 2017 and 10 days before) increases the availability of cloud and snow free satellite acquisitions of the area of interest, which is a prerequisite for the extrapolation of slope movement time-series using DIC techniques. Despite the Sentinel-2 limited spatial resolution, the derived long time-series can be integrated with—and validated by—continuous GNSS monitoring data. This allows to effectively monitor landslide movements that are too fast for the application of interferometric approaches. In this study, we used the Normalized Cross Correlation (NCC) digital image correlation technique by 51 Sentinel-2 MSI scenes (band 4 with 10 m spatial resolution), acquired between 19 February 2016 and 16 July 2019, to derive the slope movement time-series of the Ca’ Lita earthslide-earthflow in the northern Apennines (Italy). During the period considered, the landslide experienced two to three months-long phases of moderately rapid velocity (around 10 m/month) and, in between, prolonged periods of slow movements (approx. 10 cm/month). NCC results have been integrated with, and are compared to, time series from three continuous GNSS devices located in different geomorphic zones of the landslide. On this basis, the errors and limitations associated to NCC time series are analysed and discussed together with their advantages and potentialities for assessing the spatial distribution and monitoring slope movements during moderately rapid reactivation events.

Production of Various Types of Poultry in Bulgaria for the Period 2010-2018

Poultry farming has always been a major part of animal husbandry in every country. Bulgaria is no exception and has a long-standing tradition in the breeding and production of various types of poultry. In reality, our country was mainly producing chickens, laying hens and eggs in the beginning, but was also successful in the breeding of ducks, turkeys, geese, yurts and other feathered more extravagant species, such as quails, ostriches, pheasants, etc. The main purpose of this article is to analyze the production of different types of poultry in Bulgaria for a sufficiently long period of 9 years, to be able to predict trends and changes that may occur in different types of poultry in the country and to determine not only which ones shall have a leading role for specific regions in Bulgaria, but also the ways to increase their effective production in the direction of closing the production and sales cycle with poultry products processing and reaching the end customer. The article uses methods of situation analysis, time series analysis, induction, deduction, extrapolation, trend derivation and logical dependencies, method of adding value and creating a final product.

Μ-modification of the “pyramidal” method of data extrapolation

In this work certain generalizations of the classical derivative of a differentiable function are introduced. The method of time series extrapolation is proposed on the basis of corresponding generalizations. In the basis of this method is the analysis of separated differences. It is proposed procedure of the corresponding differences modification and finding of such order, for which it is possible to find in the certain sense the best forecast value. Then the value of the output function at a point that lies outside the interpolation interval is based on the found predictive value for the separated differences using a special computational procedure.

Scenario approach in forecasting tax revenues of the state budget of Ukraine

Introduction. State revenue management stands first in the areas of government regulation, which is provided by the regulation of fiscal policy. It is achieved by optimizing the amount of nationwide taxes and their tax rates, with the least amount of tax evasion. It is also important to ensure the implementation of the budget process, which is based on budget planning and forecasting, the effectiveness criterion of which is the reliability of the forecast. The compulsory component of extrapolation of time series – the most used forecasting method – is the scenario approach, so the research of possibilities of its implementation is relevant.
 Aim and tasks. The aim of the article is to introduce a scenario approach in forecasting tax revenues of the state budget of Ukraine. The main tasks set to achieve this aim are: modeling the dependence of tax revenues on macroeconomic indicators; trend analysis and extrapolation of time series of macroeconomic indicators; development of forecast scenarios of state budget revenues from state taxes.
 Results. It is proved that comprehensive stimulation of the production of gross value added, especially in the sphere of material production, as a basis for economic growth, will have a positive impact on the growth of output of goods and services, as well as will provide an increase in the revenues from value added tax (VAT) and excise tax to the state budget. Provision at the state level of further growth of the minimum wage and the deployment of social programs, as well as stimulating the legalization of shadow incomes of individuals in order to stimulate incomes of the population will lead to revenue increase from the personal income tax to the state budget. Creating favorable conditions for doing business by creating a business environment free from corruption, legalizing the shadow income of legal entities in order to maximize the profit of gross profit, mixed income will lead to an increase in corporate income tax revenues and subsoil use fee to the state budget of Ukraine.
 Conclusions. Over the next 5 years, aggregate tax revenues to the state budget will increase, regardless of the forecast scenario. The largest contribution to tax revenue growth can be provided by excise tax. The dynamics of the remaining taxes will also be increasing. Because the extrapolation of time series and scenario analysis are applied and universal methods of forecasting, they can be used in forecasting tax revenues of both consolidated and local budgets of Ukraine. Prospects for further research of the author will be relevant to these areas.

The Development of the Health and Social Care Sector in the Regions of the Czech Republic in Comparison with other EU Countries

In this paper, the quantitative status of employees in the Health and Social Care sector in the Czech Republic is assessed, and the future development of the sector is predicted both for the Czech Republic as a whole, and for individual regions according to the NUTS3 classification. At present, labor market prognoses are created using the ROA-CERGE model, which includes the main professions in the Health and Social Care sector. This article expands the predictions by adding the regional level and using extrapolation of time series, and it identifies the regions important for the given sector and the labor force. The position of the Czech Republic with regard to selected professions in comparison with other countries of the European Union, i.e., its qualitative status, is also assessed in the paper. The following professions are assessed: general nurses and midwives (both with and without a specialization), physicians, and professional assistants. Healthcare workers do not manifest geographical mobility between regions and work primarily in the region where they live. Since the Czech Republic’s accession to the EU, staff working in key professions have been able to work under comparable conditions in any of the member states. The workforce flow depends, among other things, on its qualitative representation in the given country. To find groups of European countries with similar characteristics of quantitative coverage in selected professions in the Health and Social Care sector, cluster analysis is used to identify homogeneous clusters of countries, as of 2016. Secondary data was obtained from the Czech Statistical Office (CZSO) and the Information System (ISA+) of the National Institute of Education (NIE).

Pyramidal method of extrapolation for short time series

The paper proposed a new method of short time series extrapolation, which can be used for predicting of economic, environmental and geophysical parameters. This method is based on the property of the rows of modified finite differences that the best cubic approximation is in the range of convexity. Numerical results show significant advantages of the proposed method in comparison with approaches to extrapolate, based on the use of polynomials, including Newton's extrapolation.