Forecast Criteria Research Articles

Landslide Deformation Prediction and Automatic Warning by Coupling Machine Learning and Physical Models

AbstractAutomatic deformation forecast and warning of a catastrophic landslide can effectively avoid significant casualties and economic losses. However, currently it has not come to a comprehensive forecast framework covering all the deformation stages of a landslide. Moreover, landslide deformation prediction possesses high error and false alarm rates. This work suggests a novel integrated framework of landslide deformation forecast and warning by coupling machine learning and physical models. The framework can relatively accurately predict all the deformation stages from creeping deformation to critical sliding and features 4 advantages. (a) The forecast indices are established by combining deformation and disaster‐triggering characteristics to improve the prediction accuracy. (b) It leverages the advantage of C5.0 decision tree algorithm in knowledge interpretability to automatically extract deformation forecast criteria. (c) It capitalizes on the precision superiority of a graph convolutional network in time‐series data learning to predict the four deformation stages from creeping deformation to rapidly accelerated deformation. (d) It utilizes the physical and mechanical bases of Morgenstern‐Price method to forecast the critical sliding stage. Zhujiatang Landslide is a large‐scale deep‐seated soil landslide with significant deformation. It is selected as a case study because it has endangered 1,131 persons and may cause a direct financial loss of 100 million RMB. The validating and predicting Accuracy values attain 97.39% and 95.72%, respectively, and the Kappa values reach 0.91 and 0.93, respectively. The landslide will run out when it suffers from a rainstorm with cumulative rainfall of 79.57 mm and an earthquake with a horizontal coefficient of 0.04.

AFRIMA Model Forecast Performance: An Empirical Study using Naira-Yuan Exchange Rate

In financial time series and econometrics, some macroeconomic variables exhibit long memory features that may not be best described using short memory models like ARIMA. This paper, however, is structured to compare different fractional integration in AFRIMA forecast performance for the Naira-Yuan exchange rate. The empirical monthly data set used covered the period from January 1981 to December 2022. Fractional integration test are based on the ADF unit root test and the auxiliary autoregressive order three (AAR(3)) order of integration test. Model estimation is support by the Marquart algorithm for calculating least squares estimates and performance comparison is based on the Amaefula forecast criterion (AFC). The result specified that AFRIMA (1, d, 1) where I(d = 0.07891) is more appropriate and has the best forecast performance compared to others. The result also reveals that AFRIMA model yield better and more precise forecasts when fractional integration is closer to zero that is, I(d→0) than when I(d→½). Therefore, AFRIMA models can be useful in studying exchange rate dynamics for risk-averse and risk incline in times of investment and profitability in the long-run.

Robust approach to earnings forecast: A comparison

AbstractThis paper applies three robust approaches, namely, the MM estimation, the Theil–Sen estimation, and the quantile regression, to generate earnings forecasts in Chinese financial market and evaluates the forecast accuracy of these three methods based on three forecasting criteria. We examine six forecasting models where the predicted variables include earnings per share, net income, and three profitability measures. We show that the three robust methods significantly outperform the OLS method. Moreover, the MM estimation and the quantile regression have better forecast accuracy than the Theil–Sen approach.

Ring-shape and linear gold mining districts of zimbabwe: estimation of residual gold resources

Background. Despite the long history of exploitation and study of Zimbabwe’s geological potential, the ranks of gold ore formations at the level of regions and fields remain unclear. Assessment of the residual primary gold deposits in Zimbabwe appears an important research direction.Aim. Identification of ring-shaped and linear ore districts confined to greenstone belts corresponding in configuration within the gold province of the Zimbabwe craton.Materials and methods. The main method for analyzing gold ore deposits was ore formation analysis. To analyze the residual gold resources in the regions of Zimbabwe, the Zipf-Lotke-Bradford rule was applied according to the ratio of an outstanding rare event in the form of a large deposit, rather rare events in the form of medium-sized deposits, and fairly rare events in the form of small ore objects in a certain ore region.Results. A hypothesis is proposed for the formation of ring-shaped belts as ore-bearing volcano-tectonic structures of the central type. Within the gold province of the Zimbabwe craton, ore districts of ring-shaped and linear shape, confined to greenstone belts corresponding in configuration, are identified for the first time. It is shown that the localization of deposits in ore regions is due to a combination of the following criteria: ancient faults, arc fragments of greenstone belts, and the development of post-tectonic multiphase granitoid magmatism. A ranking of deposits was carried out in the ore districts of Darwin, Shamva, Midlands, Bulawayo, Gwanda, Busha Mwezi - Fort Victoria, Shashe - Ozi-Umatli, and Sinoia. Five gold mining areas corresponding to volcano-plutonic ring-shape structures and three linear areas were identified. Productivity is predicted to be highest in the Midlands, Bulawayo, and Shamva ring-shape regions. An assessment of the residual gold resources of each of the selected areas is given. The feasibility of detailing important forecast criteria — Late Archean linear and arc faults and post-tectonic granitoids — with the development of additional criteria for further metallogenic zoning and localization of promising areas is established.Conclusions. The presented data serve as the basis for assessing the prospects of industrially important primary gold deposits in Zimbabwe and carrying out their forecast in the identified gold mining areas.

Geophysical indicators of rare-metal ore content of Akmai-Katpar ore zone (Central Kazakhstan)

Purpose. Identification of geophysical criteria to determine ore content indicators within the territory relying upon systematization of both geological and geophysical materials. Methodology. The research involved innovative techniques used in the field of geology, i.e. GIS technology, and such theoretical scientific approaches as analysis and synthesis of petrophysical data, and data of geophysical anomalies in the context of the analyzed ore zone. Findings. Petrophysical characteristics of Akmai-Katpar ore zone rocks have been generalized and systematized. Petrophysical model of the ore zone has been developed; changes in petrophysical rock characteristics have been defined in terms of Silurian, Devonian, Carboniferous, and Permian systems. The obtained parameters of the petrophysical model are integrated with the identified geophysical anomalies. Geophysical indicators of ore content of the rare-metal ore zone have been determined. Cartographic documents have been specified which made it possible to perform layer-by-layer mapping of Akmai-Katpar ore zone. Originality. For the first time, the systematized geological and petrophysical materials have been applied to build the petrophysical model of Akmai-Katpar ore zone and improve geophysical forecasting criteria. Practical value. It consists in the use of geophysical forecasting criteria while identifying prospective areas where rare metals occur.

Distinguishing of areas for conducting the GDP (GMM)-200 for gold, based on the compilation and analysis of the distribution regularities and forecast maps for the black-shale and epithermal type large-volume gold deposits of the Russian Federation at scale 1:2 500 000

The article is devoted to problems of distinguishing the areas for conducting the GDP (GMM)-200 oriented for the black-shale and epithermal type large-volume gold deposits. The approach is based on compilation of the distribution regularity and forecast maps of the Russian Federation at a scale of 1:2 500 000, specialized for these gold deposits, and their analysis. Regional forecast criteria of the gold ore objects and the character of their manifestation over the territory of the Russian Federation are considered. Recommendations are given for setting up the GDP (GMM)-200 programs for map sheets favorable for localization of areas promising for revealing the large-volume black shale and epithermal gold deposits. The forecasted resources of gold and silver of the Far Eastern Federal District and the Arctic zone of the Russian Federation are presented.

Do extreme range estimators improve realized volatility forecasts? Evidence from G7 Stock Markets

This paper investigates whether range estimators contain important information in forecasting future realized volatility. We use widely applied range-based estimators: Parkinson, Garman-Klass, Roger-Satchell, and Yang-Zhang within a HAR-RV-X framework. Overnight volatility and close-to-close volatility estimators are also included, and the forecasting exercise is applied to G7 stock markets using a rolling window. Using QLIKE, HMSE and MCS forecast criteria, several noteworthy points are reported. The overall findings suggest that while no single model dominates, overnight return volatility achieves the most consistent performance. For example, HAR-RV model forecasts for CAC and DAX indices are improved only by overnight volatility, with some evidence also for SPX. For other indices, forecasts are improved by Parkinson and/or Garman-Klass volatility estimators. Of note, simpler range estimators outperform more complex range estimators. The findings could be important for investors in managing portfolio risk.

Pricing strategies for online hotel searching: a fuzzy inference system procedure

PurposeHotels are considered one of the keys to tourism industry, without which it is impossible to visualize this industry. Setting the proper price for hotels has always been a nuisance for the decision makers because of its direct relationship with the demand for hotels. Thus, in the current study a Stackelberg game between the government (leader) and the hotels (follower) has been presented to determine the optimal price under competitive conditions. The selected hotels are different with respect to energy consumption and the environmental impact. Thus, the government makes efforts to control their prices with incentives and tariffs.Design/methodology/approachThe fuzzy inference system (FIS) has also been applied to forecast the hotel demand. Therefore, first off, the demand forecast criteria have been chosen by the experts and in the continuation, it has been screened by fuzzy Delphi approach. Finally, the quantity of hotel demand is computed by the Mamdani inference system. A mathematical model has been presented for determining the optimal sequencing of hotels and minimizing the searches to find a hotel.FindingsA case study based on the data extracted from online travel agencies (OTAs) has been presented to validate the proposed model. The results demonstrate that by the ranking position increase, the number of the tourists decreases and the higher the star number of a hotel, the lower its ranking position.Originality/valueConsidering the energy saving and environmental impacts in hotel pricing and considering the government's intervention in hotel revenues regarding the incentives and tariffs are the innovations of the present study.

A closed-form solution for the stochastic volatility model with applications on international stock markets

This paper proposes a closed-form estimator for the stochastic volatility (SV) model. Compared to the usual maximum likelihood estimation (MLE), which is difficult to perform without appropriate approximations, the proposed method can be easily implemented and does not require the use of any numerical optimizer or starting values for iterations. Moreover, closed-form estimates can be supplied as initial values to MLE, for instance, conducted with a novel Laplace approximation. Denoted by MLE-C, this method consistently outperforms other estimators including the Markov chain Monte Carlo (MCMC). This is confirmed with simulation studies consisting of various combinations of true parameters and sample sizes. Our empirical data include daily returns of S&P 500, Nikkei 225 and DAX 100 over 2011–2020. The SV model estimated by MLE-C almost uniformly beats the popular GARCH counterparty, based on both the in-sample fit and out-of-sample forecasting criteria. Value-at-Risk analyses further demonstrate the capability of the SV model to accurately describe the tail behaviors of negative returns.

Variable targeting and reduction in large vector autoregressions with applications to workforce indicators

We develop statistical tools for time series analysis of large multivariate datasets, when a few core series are of principal interest and there are many potential auxiliary predictive variables. The methodology, based on Vector Autoregressions (VAR), handles the case where unrestricted fitting is precluded by a large number of series and a huge parameter space. In particular, we adopt a forecast error criterion and use Granger-causality tests in a sequential manner to build a VAR model that targets the main variables. This approach affects variable reduction (or equivalently, sparsity restrictions) in a computationally fast way that remains feasible for large dimensions. The search for the best model results in a VAR, fitted with a selection of supporting series, that has the best possible forecast performance with respect to the core variables. We apply the statistical methodology to model real Gross Domestic Product and the national Unemployment Rate, two time series widely monitored by economists and policy-makers, based on a large set of Quarterly Workforce Indicators comprising various major sectors of the economy and different measures of labor market conditions.

Forecasting of Atopic Dermatitis in Newborns.

Early forecasting of any pathological process is of great significance from both medical and economic point of view. An illness requires much more attention in the light of exhaustion of resources of the body, and a doctor should be maximally aware of the near and far future of a patient. In this regard, the preparation of forecasting programs on a mathematical basis would be a rational and, most probably, the only true approach to the solution of forecasting. The aim of the article is to study the forecasting of atopic dermatitis (AD) in newborns. The authors studied 109 clinical and laboratory indicators in children without and with AD. Discriminant analysis was used as an algorithm for the resolution of diagnostic issues. The main indicators acceptable as a forecasting criterion in the formation of AD in children were defined. The sensitivity, specificity, and general diagnostic value of statistically valid differing factors in the formation of AD were studied. Key rules of the forecast were formed after processing all indicators through the KU-Kruskal-Wallis discriminant criterion, a universal computer method. It was concluded that the power of influence of rhinitis, cluster of differentiation 31, mucin 2, and intestinal trefoil factor 3 are higher in the AD model.

Principal scheme of step-by-step study of non-anticlinal traps of oil and gas (types of work and research methods)

The article scientifically substantiates and systematizes the types of work and research methods to identify and search for hydrocarbon accumulations associated with non-anticlinal traps, consistently at all stages of geological exploration. The tasks and criteria for forecasting and identifying non-anticlinal traps at each stage of geological exploration are formulated. New research methods are proposed. Keywords: oil; gas; non-anticlinal traps; study scheme; types of work; research methods; forecast criteria; stages of geological exploration.

The role of plicative structures as forecast criteria in the Alakit-Мarkhinsky field (western Yakutia)

This paper describes the tectonic features of the Alakit-Markha kimberlite field, regional factors of kimberlite magmatism control in this area, structural and tectonic preconditions for kimberlite pipe prospecting. The paper highlights kimberlite pipe formation features and the role of tectonics in this process. The most promising areas are those related to low-amplitude negative structures (e.g. depressions), especially transverse low-amplitude complications of the opposite sign for the main plicative structure: for antiforms (elevations), these are saddle-shaped depressions, and antiform elevations are for synforms (depressions).

A data-driven deep sequence-to-sequence long-short memory method along with a gated recurrent neural network for wind power forecasting

Large amounts of wind power generation have an impact not only on energy markets but also on wholesale and retail market designs. Simultaneously, technological issues arise as a result of the need to ensure the smooth operation of the power grid. In the long run, high-quality wind data series are required to generate model results that lead to robust policy advice. Several techniques are commonly used to forecast short-term, nonstationary, and nonlinear wind speeds. These techniques are lacking in model optimization and data processing abilities. This lack of expertise is posing a significant challenge for reliable and stable wind power forecasting. Furthermore, the medium and long-term forecasting criteria for models (e.g., robustness, accuracy, speed) are higher, making it difficult to obtain reliable results. This study used the extended deep sequence-to-sequence long short-term memory regression (STSR-LSTM) model for time-series wind power forecasting to overcome these challenges for accurate forecasting decisions. The statistical-learning technique is used to improve the dependability of the derived features as well as the expected performance. Three different locations/sites were used and analyzed (e.g., Belgian, DSO-Connected, Elia), three different forecasting classes (e.g., week-ahead forecast, day-ahead forecast, and most recent forecast), three different seasons (e.g., monthly, seasonal, and annual), and three experimental setups. The performance of Deep STSR-LSTM is validated using two existing models and four performance evaluation indexes. Despite the fact that the input wind power load curve had a lot of variation, we were able to achieve higher forecast accuracy. Using different sites and classes, similar forecast accuracy was achieved for each season (e.g., monthly, seasonal, and annual).

Prospect for expansion and replenishment of rare metal resources and reserves in Eastern Kazakhstan

The main rare metal-bearing structures in Eastern Kazakhstan are granitoid belts formed in the Hercynian cycle of tectogenesis in the post-collisional (orogenic) geodynamic environment of the Permian time and confined to the continental blocks of siallitic high-level. The geotectonic position of the Kalba–Narym rare metal granitoid belt in the geological structure of the Greater Altai is considered. The known rare-metal pegmatite deposits (Ta, Nb, Be, Li, etc.) are spatially and genetically related to Kalba granites (P1). The richest ore-bearing are granite massifs formed in the mobile tectonic environment and under unbalanced P–T conditions. The distribution of rare alkalis in granitoids of the Hercynian evolutionary series is given. The forecast estimate of prospects is associated with the study of hidden granite massifs on the northwestern flank of the belt, identified based on the geological and geophysical data. The forecasting criteria are the intensive alteration of the above-intrusive zone (granitization, greisenization, silicification), direct signs of tin–tungsten mineralization on ground surface, identification of ongonite-like dikes and rare metal minerals in metasomatites from the results of electron microscopy. The estimation of the prospects of nontraditional tin–lithium–tantalum mineralization associated with albitized and greisenized granites is given. It is recommended to undertake deep mineralogical mapping of the closed reserved areas. The further geological exploration should be aimed at expansion of mineral resources and reserves for rare metal production.The study was supported by the Committee of Science of the Ministry of Education and Science of the Republic of Kazakhstan, Contract No. 120 dated 1 June 2020, Registration No. 0120RK00135, and Grant IRN AR08856325.

Lithology and geochemical characterization of low-permeability shale strata: A-case-study of Khadum Formation in Ciscaucasia

According to classical concepts, the primary function of oil and gas source beds is generation of hydrocarbons. The oil and gas source beds in favorable conditions generate oil and gas, while oil-andgas-bearing reservoirs accumulate hydrocarbons and donate them in the course of mining. This research aimed to prove forecast criteria for the occurrence of hydrocarbons in oil and gas source beds with a view to enhancing efficiency of prospect and exploration of adsorbed oil in terrigenous deposits or matrix oil in carbonate deposits. In terms of Khadum Formation in Ciscaucasia, the authors examine productive strata which are both the source and reservoir of hydrocarbons. The research findings on the organic porosity, as well as the analyses of adsorbed oil and matrix oil in terrigenous and carbonate deposits can help essentially modify the oil and gas exploration strategies. The obtained results prove the scientific idea that oil and gas source beds can generate, accumulate and cluster hydrocarbons, which calls for the criteria for oil exploration in oil and gas source beds. The results of this research can be used for the analysis and assessment of the hydrocarbon stock potential, as well as for the exploration and recovery of adsorbed and matrix oil in terrigenous and carbonate deposits.

Substantiating topicality of injectable localizing and deactivation of coal seams prone to endogenous spontaneous combustion

The analysis for possible development of endogenous fires in coal seams prone to oxidation and spontaneous combustion is done. The coal free surface area is taken as a forecasting criterion for estimating the state of the zones of broken condition. The effectiveness of applying fracture plugging (cementing) technology for injectable localizing and deactivation of the massif is substantiated. The conception for further studying of the processes for controlling physical and chemical characteristics of a seam considering native properties of coal is formed.

Short-term Electricity Price Probabilistic Forecasting Based on Support Vector Quantile Regression Optimized by Simulated Annealing Algorithm

Background: Electricity price forecasting is still a challenging issue as it plays an essential role in balancing electricity generation and consumption. Probabilistic electricity price forecasting not only provides deterministic price forecasts but also effectively quantifies the uncertainty of electricity price. Methods: This paper introduces a new short-term electricity price forecasting approach called SASVQR, which is based on support vector quantile regression (SVQR) optimized by simulated annealing algorithm. In this study, SVQR is employed to obtain the conditional quantiles of the electricity under different quantile points, while the simulated annealing algorithm is applied to optimize each SVR model. Then the kernel density estimation takes these conditional quantiles as inputs and generates the probability density functions for future electricity prices. Result: The proposed algorithm is assessed in three datasets: the GEFCom 2014, two real electricity price datasets from the PJM market and the Singapore market. Three popular probabilistic forecasting criteria, namely prediction interval coverage probability (PICP), prediction interval normalized average width (PINAW), and coverage width-based criterion (CWC), are utilized to evaluate the numerical experiment results..It shows the promising forecasting performance, robustness, and effectiveness of SASVQR on different datasets. Conclusion: The SASVQR method can effectively forecast the short-term electricity price compared with other methods.

Металогенічне районування міденосних трапів нижнього венду Волині

Metallogenic zoning of the Lower Vendian trap distribution area in Volyn has been performed according to the complex metallogenic map of Ukraine at a scale of 1 : 500,000 (2003) and according to the division of the territory into structural-facial zones and subzones and taking into account deformation structures in the crystalline basement and sedimentary cover. Two metallogenic zones have been identified within the Prypiatsko-Dniesterska structuralmetallogenic zone: Lukivsko-Ratnivska cupreous with associated silver and gold and VolynoPodilska, which does not contain industrial concentrations of copper and mineralization of precious metals. Within the first metallogenic zone, Volynskyi, Kukhitsko-Volskyi and Manevytskyi metallogenic regions were identified according to a number of forecast criteria and search features. These regions territorially correspond to the areas of distribution on the pre-Mesozoic surface of certain trap sections of the Lower Vendian and the corresponding structural-facial subzones of the Brestsko-Volynska structural-facial zone. As part of the described metallogenic regions, 12 ore-bearing fields were identified, which are characterized by the degree of prospects for the detection of copper deposits with concomitant precious metal mineralization (high, medium), by the degree of reliability of prospects (reliable, medium reliability, low reliability) and by the average depth of study. It is concluded that the most productive for copper is the Volyn metallogenic region, which has six ore-bearing fields with numerous ore occurrences of native copper. The region corresponds to the area of distribution of the ore-generating Verkhnioprypiatskyi trap complex. It is characterized by the greatest completeness of the trap formation sections and a tense plicatedblock deformation structure. Key words: copper, traps, metallogenic region, ore-bearing field, Lower Vendian, Volyn.

COMPREHENSIVE INTERPRETATION OF FACTORS AND PARAMETERS OF PRODUCTIVE HYDROCARBON STRUCTURES

Problem Statement and Purpose. Geophysical (seismic) criteria are most often used as indirect indicators in the search for hydrocarbon-containing deposits, especially within anticlinal structures that are revealed by geophysical methods buried beneath the sedimentary cover of marine basins. However, geophysical methods have their limitations, such as the inability to detect non-anticline-type traps (riphogenic, litho­logical, tectonically and stratigraphically shielded). Therefore, additional predictive and sufficiently sensitive criteria are needed. The main focus of the present paper is a discussion of forecast criteria for locating hydrocarbon fields in the sedimentary cover of the Black Sea based on the principles of the fluidogenetic theory (which assumes constant replenishment of hydrocarbon reserves) and ranking them by their degree of sensitivity to the intended goal of hydrocarbon exploration.Data & Methods. Regional seismic profiles obtained by the Common Depth Point method have been studied for their capacity to provide geophysical (magnetic, gravi­tational, geothermal) data promising for investigating hydrocarbon reservoirs as well as other geochemical, mineralogical, and meiobenthic methods. Obtained results were visualized in GIS and ranked on their degree of sensitivity to the hydrocarbon deposits and their ability to identify deep geological structures promising for oil-gas explora­tion and production.Results & Discussion. The work focused on creating a guiding structural model of exploration for hydrocarbon deposits for the inland Eurasian seas using a comprehen­sive comparative analysis of various exploration approaches, including geological, geophysical, geochemical, mineralogical, geomorphological, and meiobenthic, then ranking these approaches according to their sensitivity to the goal of exploration on the basis of the theory of fluidogenesis.This subject-oriented model includes two independent blocks of information that can mutually exchange information: (1) knowledge in the subject area, and (2) research methodology. The first block generates predictive hypotheses and potential search indicators based on the theory of fluidogenesis and ranked by expert analysis. The sec­ond block includes examples and methods of obtaining specific information, which allows you to test hypotheses and in so doing supplement the model of hydrocarbon exploration to guide the process of locating reservoirs.Conclusions. Material has been prepared to demonstrate an application of the model for one location that shows promise for containing hydrocarbons: the Pradniprovska structure on the outer shelf of the Black Sea. Geophysical, geochemical, mineralogi­cal, and micropaleontological studies have been carried out and ranked according to the degree of sensitivity to the occurrence of hydrocarbons within the depths reached during drilling in the area of a deep parametric well.