Machine Time Research Articles

Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal

Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for this type of analysis. The main aim of this article is to develop a methodology for mapping LW in northwestern Portugal using a machine learning algorithm and time series from Landsat images. For the burnt area classification, we initially used the Fourier harmonic model to define outliers in the time series that represented pixels of possible burnt areas and, then, we applied the random forest classifier for the LW classification. The results indicate that the harmonic analysis provided estimates with the actual observed values of the NBR index; thus, the pixels classified by random forest were only those that were masked, collaborated in the processing, and reduced possible spectral confusion between targets with similar behaviour. The burnt area maps revealed that ~23.5% of the territory was burnt at least once from 2001 to 2020. The temporal variability of the burnt area indicated that, on average, 6.504 hectares were affected by LW within the 20 years. The annual burnt area varied over the years, with the minimum annual area detected in 2014 (679.5 hectares) and the maximum mapped area detected in 2005 (73,025.1 hectares). We concluded that the process of defining the mask with the outliers considerably reduced the universe of pixels to be classified within each image, which leaves the training of the classifier focused on separating the set of pixels into two groups with very similar spectral characteristics, thus contributing so that the separation of groups with similar spectral behaviour was performed automatically and without great sampling effort. The method showed satisfactory accuracy results with little omission for burnt areas.

Fuzzy Evaluation and Improvement Decision-Making Model for Machining Operation Performance

Taiwan is a major exporter and producer of machinery and machine tools in the world. There are at least hundreds of components for various machining machines. According to the concept of Taguchi loss function, when the process quality of the spare parts of machining machines is not good, the failure rate will increase after the product is sold, resulting in an increase in maintenance costs and carbon emissions. As the environment of the Internet of Things (IoT) becomes more common and mature, it is beneficial for manufacturers of machining machines to collect relevant information about process data from outsourcers, suppliers, and machining machine factories. Effective data analysis and application can help the machining machine industry move towards smart manufacturing and management, which can greatly reduce the average number of failures per unit time for all sold machines. Therefore, this paper developed a practical evaluation and improvement decision-making model for the machining operation performance to help machining machine manufacturers find out the components that often fail and improve them, so as to reduce the total loss caused by machine failures. This paper first defined the machining operation performance index for the machining machines and discussed the characteristics of this operation performance index. Subsequently, the confidence interval of the index was deduced, a fuzzy evaluation model based on this confidence interval was proposed, and decision-making rules regarding whether to make any improvement was established. The fuzzy evaluation and improvement decision-making model for the operation performance of machining machines proposed in this paper will contribute to various tool industries to boost their process quality, reduce costs, and lower carbon emissions, in order to achieve sustainable management of enterprises and the environment.

Demand Forecasting of Spare Parts Using Artificial Intelligence: A Case Study of K-X Tanks

The proportion of the inventory range associated with spare parts is often considered in the industrial context. Therefore, even minor improvements in forecasting the demand for spare parts can lead to substantial cost savings. Despite notable research efforts, demand forecasting remains challenging, especially in areas with irregular demand patterns, such as military logistics. Thus, an advanced model for accurately forecasting this demand was developed in this study. The K-X tank is one of the Republic of Korea Army’s third generation main battle tanks. Data about the spare part consumption of 1,053,422 transactional data points stored in a military logistics management system were obtained. Demand forecasting classification models were developed to exploit machine learning, stacked generalization, and time series as baseline methods. Additionally, various stacked generalizations were established in spare part demand forecasting. The results demonstrated that a suitable selection of methods could help enhance the performance of the forecasting models in this domain.

Intelligent Monitoring and Compensation between EDM and ECM

Electric discharge machining (EDM) is a type of high-precision machining usually applied to hard-material machining for mold manufacturing and in the aerospace industry. Longer process times typically reduce facility efficiency. The use of electrochemistry machining (ECM) can overcome this challenge to efficiently machine large workpieces. Some industries have adopted and combined these two processes for Inconel 718 material machining. However, the use of coordinate-measuring machine times to determine the machining accuracy of these two processes is difficult. This study matched process features by analyzing the electric driving pulses of ECM and EDM. Fitting intelligent sensing signals that respond to dimensional measurements can be used to analyze electrical pulse signals. For analyzing a cross-process model using extracted key features of the process, our feedback-based system determines lower machining measurement errors and improves geometric size. Finally, the processing time of experiments can be reduced by 80%, and our proposed model has a prediction accuracy of approximately 0.01 mm2.

Smart Platform for Data Blood Bank Management: Forecasting Demand in Blood Supply Chain Using Machine Learning

Despite the efforts of the World Health Organization, blood transfusions and delivery are still the crucial challenges in blood supply chain management, especially when there is a high demand and not enough blood inventory. Consequently, reducing uncertainty in blood demand, waste, and shortages has become a primary goal. In this paper, we propose a smart platform-oriented approach that will create a robust blood demand and supply chain able to achieve the goals of reducing uncertainty in blood demand by forecasting blood collection/demand, and reducing blood wastage and shortage by balancing blood collection and distribution based on an effective blood inventory management. We use machine learning and time series forecasting models to develop an AI/ML decision support system. It is an effective tool with three main modules that directly and indirectly impact all phases of the blood supply chain: (i) the blood demand forecasting module is designed to forecast blood demand; (ii) blood donor classification helps predict daily unbooked donors thereby enhancing the ability to control the volume of blood collected based on the results of blood demand forecasting; and (iii) scheduling blood donation appointments according to the expected number and type of blood donations, thus improving the quantity of blood by reducing the number of canceled appointments, and indirectly improving the quality and quantity of blood supply by decreasing the number of unqualified donors, thereby reducing the amount of invalid blood after and before preparation. As a result of the system’s improvements, blood shortages and waste can be reduced. The proposed solution provides robust and accurate predictions and identifies important clinical predictors for blood demand forecasting. Compared with the past year’s historical data, our integrated proposed system increased collected blood volume by 11%, decreased inventory wastage by 20%, and had a low incidence of shortages.

Different Forecasting Model Comparison for Near Future Crash Prediction

A traffic crash is becoming one of the major factors that leads to unexpected death in the world. Short window traffic crash prediction in the near future is becoming more pragmatic with the advancements in the fields of artificial intelligence and traffic sensor technology. Short window traffic prediction can monitor traffic in real time, identify unsafe traffic dynamics, and implement suitable interventions for traffic conflicts. Crash prediction being an important component of intelligent traffic systems, it plays a crucial role in the development of proactive road safety management systems. Some near future crash prediction models were put forward in recent years; further improvements need to be implemented for actual applications. This paper utilizes traffic accident data from the study Freeway in China to build a time series-based count data model for daily crash prediction. Lane traffic flow, weather information, vehicle speed, and truck to car ratio were extracted from the deployment of non-intrusive detection systems with support of the Bridge Management Administration study and were input into the model as independent variables. Different types of prediction models in machine learning and time series forecasting methods such as boosting, ARIMA, time-series count data model, etc. are compared within the paper. Results show that integrating time series with a count data model can capture traffic accident features and account for the temporal structure for variable serial correlation. A prediction error of 0.7 was achieved according to Root Mean Squared Deviation.

On employing pythagorean fuzzy processing time to minimize machine rental cost

<abstract> <p>The aim of this paper is to obtain the minimal rental cost of the three-phases flow shop scheduling problems. A novel strategy to tackle this issue using Pythagorean fuzzy processing time is introduced. It depends on converting the three stages machine into two stages when the minimum value of processing time of the first machine is greater than the maximum value of processing time of the second machine. The vague processing time does not convert to its crisp form. The jobs sequencing in machines is obtained using Johnson procedure. The zero element of the Pythagorean set is defined as, $ {\widetilde{\mathrm{O}}}^{\mathrm{p}} = \left(\mathrm{0, 1}\right) $ i.e., it has zero membership and one nonmembership values. A numerical example include Pythagorean rental cost is delivered to demonstrate the reliability of the suggested strategy. The idle time, utilization time, and the overall cost are calculated. The idle time of all machines is zero, which minimize the required time and hence, minimize the total rental cost.</p> </abstract>

A Safe Bayesian Optimization Algorithm for Tuning the Optical Synchronization System at European XFEL

The European XFEL is one of the largest linear particle accelerator in the world used to generate extremely intense and ultra short X-Ray flashes to study ultra fast, time resolved chemical processes. In order to improve the quality of the observations, the laser-based optical synchronization system is optimized by tuning PI controllers using a safe Bayesian optimization approach. Since machine time on the European XFEL is very expensive, the algorithm needs to find the optimal parameters as fast as possible. In this contribution, we present a safe Bayesian optimization algorithm which, while guaranteeing safety, shows significantly improved convergence speed and noise robustness. Application and comparison results are presented in simulation for the optical synchronization system of the European XFEL and an experimental demonstration is performed for a laboratory synchronization system.

ПІДВИЩЕННЯ ЕФЕКТИВНОСТІ ФРЕЗЕРУВАННЯ ПОВЕРХОНЬ ЕНДОПРОТЕЗІВ

Purpose to work: is to increase the efficiency of milling endoprosthesis components, taking into account their kinematic characteristics. Methodology: theoretical research was carried out on the basis of mathematical analysis, computer modeling using modern software and computing equipment. The PowerMILL CAM system was used for statistical processing of milling trajectories. Results: when manufacturing endoprosthesis components, the best processing strategies were "Selection of 3D model by model shift" and "Selection of 3D model by shift". These two strategies give the lowest idle time for the lowest core processing time. Machine processing time when using the strategies "3D model selection" by model shift and "3D model selection" by shift is reduced by 2 times compared to the "3D model selection" raster strategy, and by 3 times compared to the "3D model selection" strategy Vortex. However, it should be noted that all 4 studies were conducted at the same cutting modes, which are not typical for high-speed milling. Vortex's "3D Model Selection" is ineffective in these cutting modes due to the fact that it is designed exclusively for high-speed milling. "Sampling a 3D model" with a raster also turned out to be ineffective due to the fact that it is intended for work on open planes. Scientific novelty: the most effective milling strategy for the manufacture of endoprosthesis components is proposed. Practical significance: recommendations for the use of milling strategies are given. Key words: milling, strategy, endoprosthesis, idle movements, model, technological process, operation, machine time.

DIAGNOSING THE TECHNICAL CONDITION OF MOBILE POWER EQUIPMENT USING DIGITAL TECHNOLOGIES

Research aimed at creating and implementing modern methods of diagnosing agricultural machinery, allowing to improve diagnostics and increase the reliability of assessing the technical condition of machines in real time using modern digital technologies, is relevant at the present time. (Research purpose) The research purpose is evaluating the possibilities of diagnosing high-power agricultural machinery using digital technologies. (Materials and methods) Materials and methods based on the use of intelligent information technologies, automated control systems and management of the technical condition of agricultural machinery were used. An electronic control unit with a CAN bus was used to identify the technical condition of the object. The article shows that reducing maintenance and repair costs and increasing the level of efficiency of agricultural machinery significantly contribute to an integrated approach to the development of methods, tools and technologies for diagnostics and automated control systems based on digital technologies with minimal requirements for the controllability of the machine. The expansion of the nomenclature of methods and equipment for obtaining information about the operational reliability of high-energy equipment makes it possible to conduct systematic research on technical diagnostics. (Results and discussion) The results and analysis of this work consists in a comprehensive approach to conducting diagnostic studies using digital technologies through an electronic control unit, assessing the level of technical condition using this diagnostic method, which allows fixing malfunctions based on the received output signals from energy-saturated equipment. (Conclusions) The introduction of diagnostic elements of mobile power facilities via the CAN bus allows you to receive current information about the technical condition of the machine in real time, which does not allow its parameters to exceed permissible limits during the operation of energy-saturated equipment, thereby reducing its downtime.

Digital Twins for Smart Home Gadget Threat Prediction using Deep Convolution Neural Network

Digital twin is one of the most important innovations in the Internet of Things (IoT) era and business disruption. Digital twins are a growing technology that bridges the gap between the real and the digital. Home automation in the IoT refers to the practice of automatically managing and monitoring smart home electronics by use of a variety of control system methods. The geysers, refrigerators, fans, lighting, fire alarms, kitchen timers, and other electrical and electronic items in the home can all be managed and monitored with the help of a variety of control methods. Digital twins replicate the physical machine in real time and produce data, such as asset degradation, product performance level that may be used by the predictive maintenance algorithm to identify the product functionality levels. The purpose of this research is to design the framework of Digital Twin using machine learning and state estimation algorithms model to assess and predict home appliances based on the probability rate of smart home system gadgets functionality. The main goal of this research is to create a digital twin for smart home gadgets that are used to monitor the health status of these devices for increasing the life time and to reduce maintenance costs. This research presents a Deep Convolution Neural Network based Logistic Regression Model with Digital Twins (DCNN-LR-DT) for accurate prediction of smart home gadget functionality levels and to predict the threats in advance. The proposed model is compared with the traditional models and the results represent that the proposed model performance is better than traditional models.

Anomaly detection architecture for smart hospitals based on machine learning, time series, and image recognition analysis: survey

Anomaly detection architecture for smart hospitals based on machine learning, time series, and image recognition analysis: survey

Content Size-Dependent Alginate Microcapsule Formation Using Centrifugation to Eliminate Empty Microcapsules for On-Chip Imaging Cell Sorter Application.

Alginate microcapsules are one of the attractive non-invasive platforms for handling individual cells and clusters, maintaining their isolation for further applications such as imaging cell sorter and single capsule qPCR. However, the conventional cell encapsulation techniques provide huge numbers of unnecessary empty homogeneous alginate microcapsules, which spend an excessive majority of the machine time on observations and analysis. Here, we developed a simple alginate cell encapsulation method to form content size-dependent alginate microcapsules to eliminate empty microcapsules using microcapillary centrifugation and filtration. Using this method, the formed calcium alginate microcapsules containing the HeLa cells were larger than 20m, and the other empty microcapsules were less than 3m under 4000 rpm centrifugation condition. We collected cell-containing alginate microcapsules by eliminating empty microcapsules from the microcapsule mixture with simple one-step filtration of a 20 m cell strainer. The electrical surface charge density and optical permeability of those cell-encapsulated alginate microcapsules were also evaluated. We found that the surface charge density of cell-encapsulated alginate microbeads is more than double that of cells, indicating that less voltage is required for electrical cell handling with thin alginate gel encapsulation of samples. The permeability of the alginate microcapsule was not improved by changing the reflective index of the medium buffer, such as adding alginate ester. However, the minimized thickness of the alginate gel envelope surrounding cells in the microcapsules did not degrade the detailed shapes of encapsulated cells. Those results confirmed the advantage of alginate encapsulation of cells with the centrifugation method as one of the desirable tools for imaging cell sorting applications.

Self-attention based deep direct recurrent reinforcement learning with hybrid loss for trading signal generation

Algorithmic trading based on machine learning has the advantage of using intrinsic features and embedded causality in complex stock price time series. We propose a novel algorithmic trading model based on recurrent reinforcement learning, optimized for making consecutive trading signals. This paper elaborates on how temporal features from complex observation are optimally extracted to maximize the expected rewards of the reinforcement learning model. Our model incorporates the hybrid learning loss to allow sequences of hidden features for reinforcement learning to contain the original state’s characteristics fully. The self-attention mechanism is also introduced to our model for learning the temporal importance of the hidden representation series, which helps the reinforcement learning model to be aware of temporal dependence for its decision-making. In this paper, we verify the effectiveness of proposed model using some major market indices and the representative stocks in each sector of S&P500. The augmented structure that we propose has a significant dominance on trading performance. Our proposed model, self-attention based deep direct recurrent reinforcement learning with hybrid loss (SA-DDR-HL), shows superior performance over well-known baseline benchmark models, including machine learning and time series models.

Performance Evaluation of Novel Random Biased-Genetic Algorithm (NRB-GA): A Hybrid Load Balancing Algorithm in a Cloud Computing Environment

A novel random biased-genetic algorithm (NRB-GA) load-balancing algorithm that exhibits the characteristics of both genetic algorithms and biased random algorithms is designed and developed to improve the processing time and response time metrics of the cloud computing environment. The NRB-GA is designed to discover a virtual machine with fewer loads by applying a genetic algorithm with a fitness function that is inversely proportional to the average load over a period of time for each virtual machine and with biased parent selection to maximize the fitness values of offspring. The developed NRB-GA load-balancing algorithm is evaluated by analysing its performance for various simulated scenarios in a cloud computing environment with different user bases and data center configurations. The analysis of the experimental results of NRB-GA indicates that the average response time is reduced by 27.22%, 21.15%, and 22.34%, and the processing time is reduced by 25.73%, 16.14%, and 18.82% for one, two, and three data centers, respectively. It is evident that the proposed NRB-GA algorithm for load balancing outperforms other existing algorithms significantly.

Predicting daily emergency department visits using machine learning could increase accuracy

ObjectiveAdministrators and clinicians alike have attempted to predict emergency department visits for many years. The ability to predict or “forecast” ED visit volume can allow for more efficient resource allocation, including up-staffing or down-staffing, changing OR schedules, and predicting the need for significant resources. The goal of this study is to examine combinations of variables via machine learning to increase prediction accuracy and determine the factors that are most predictive of overall ED visits. As compared to a simple univariate time series model, we hypothesize that machine learning models will predict St. Joseph Mercy Ann Arbor's patient visit load for the emergency department (ED) with higher accuracy than a simple univariate time series model. MethodsUnivariate time series models for daily ED visits, including ARIMA, Exponential Smoothing (ETS), and Facebook Inc.'s prophet algorithm were estimated as a baseline comparison. Machine learning models, including random forests and gradient boosted machines (GBM), were trained using data from 2017 to 2018. After final models were created, they were applied to the 2019 data to determine how well these models predicted actual ED patient volumes in data not utilized during the model fitting process. The accuracy of the machine learning and time series models were assessed based on out-of-sample predictive accuracy, compared using root mean squared error (RMSE). ResultsUsing root mean squared error (RMSE) to assess out-of-sample predictive accuracy of the models, the results showed that the random forest model was the most accurate at predicting daily ED visits in the 2019 test set, followed by the GBM model. These performed only slightly better than the simple exponential smoothing model predictions. The ARIMA model performed poorly in comparison. The day of the week (likely capturing differences between weekdays and weekends) was found to be the most important predictor of patient volumes. Weather-related features such as maximum temperature and SFC pressure appeared to capture some of the seasonality trends related to changes in patient volumes. ConclusionsMachine learning models perform better at predicting daily patient volumes as compared to simple univariate time series models, though not by a substantial amount. Further research can help confirm these limited initial results. Gathering more training data and additional feature engineering could also be beneficial to training the models and potentially improving predictive accuracy.

Использование синергетической концепции при определении программы ЧПУ при токарной обработке

Introduction. One of the dynamically developing areas of increasing the efficiency of CNC machines is associated with the use of the synergetic concept in determining the CNC program. The principle of compression-expansion of the dimensionality of the state space is used. Subject. On the example of the workpiece machining, the stiffness parameters of which are a function of the toolpath, all stages of control synthesis, which ensures the mutual consistency of dynamic subsystems, including the cutting process, are described in the paper. The aim of the work is to determine asymptotically stable machine actuator toolpath, given by CNC program parameters, from the set of paths, for which the condition of minimum wear intensity is fulfilled. Method and methodology. Mathematical modeling of the controlled cutting system, which is based on the principle of compression-expansion state space, is presented. When the dimension of the state space is expanded, the model of the dynamic cutting system includes all elements from the CNC system that programs the motion of the actuating elements to the elastic deformations of the tool, which interacts with the workpiece through the connection formed by the cutting process. The dynamic coupling integrates the subsystems into a single coupled control system. In this space, the desired shaping motion path of the tool tip relative to the workpiece is constructed, which should be the attractor of the entire state space. The transformation of the desired motion path into an attractor characterizes the procedure of compressing the dimensionality of the state space. It is supposed that it is possible to control the motion trajectories of the actuators within the bandwidths of the servomotors. Results and Discussion. The analysis of the stability of the cutting process is performed; the example of the efficiency of a NC program on the basis of the synergetic paradigm is presented. It is shown that by coordinating the external control with the internal dynamics of the system it is possible to increase the efficiency of a part production up to two times in machine time.

Machine Learning and Deep Learning Based Time Series Prediction and Forecasting of Ten Nations' COVID-19 Pandemic.

In the paper, the authors investigated and predicted the future environmental circumstances of a COVID-19 to minimize its effects using artificial intelligence techniques. The experimental investigation of COVID-19 instances has been performed in ten countries, including India, the United States, Russia, Argentina, Brazil, Colombia, Italy, Turkey, Germany, and France using machine learning, deep learning, and time series models. The confirmed, deceased, and recovered datasets from January 22, 2020, to May 29, 2021, of Novel COVID-19 cases were considered from the Kaggle COVID dataset repository. The country-wise Exploratory Data Analysis visually represents the active, recovered, closed, and death cases from March 2020 to May 2021. The data are pre-processed and scaled using a MinMax scaler to extract and normalize the features to obtain an accurate prediction rate. The proposed methodology employs Random Forest Regressor, Decision Tree Regressor, K Nearest Regressor, Lasso Regression, Linear Regression, Bayesian Regression, Theilsen Regression, Kernel Ridge Regressor, RANSAC Regressor, XG Boost, Elastic Net Regressor, Facebook Prophet Model, Holt Model, Stacked Long Short-Term Memory, and Stacked Gated Recurrent Units to predict active COVID-19 confirmed, death, and recovered cases. Out of different machine learning, deep learning, and time series models, Random Forest Regressor, Facebook Prophet, and Stacked LSTM outperformed to predict the best results for COVID-19 instances with the lowest root-mean-square and highest R 2 score values.

Novel photothermal pyrolysis on waste fan blade to generate bisphenol A

Waste fan blade would explosively grow with the life time of wind power machine is ended. Developing new low carbon-emission method to treat waste fan blade and achieving high resource recovery is promising. In this work, a novel photothermal pyrolysis method was developed and firstly applied to treat waste fan blade. A typical waste fan blade was cut, crushed and screened to separate base material and reinforcing fiber, whose mass ratio was 74.36:25.64. The base material was pyrolyzed at varied conditions of pyrolysis temperature, heating rate, gas flow rate respectively. The study showed that bisphenol A was significantly acquired in tars (relative contents were commonly over 40%), and its generation can be promoted by increasing pyrolysis temperature, heating rate and gas flow rare. The generation mechanism of bisphenol A was revealed during photothermal pyrolysis process: The main chain of 2,2-bis(4-glycidyloxyphenyl)propane resin in base material undergone random or chain cracking reaction to produce bisphenol A rigid skeleton, phenoxy, alkane, hydroxyl and other active groups. Bisphenol A rigid skeleton was the precursor of bisphenol A. Bisphenol A was formed after receiving hydrogen atoms, accompanied by the formation of tetrahydrofuran, 4,4-(propane-2,2-diyl)bis(methoxybenzene) and other substances. Bisphenol A undergone decomposition via secondary reactions, and it was mainly decomposed into phenol and 4-isopropylphenol, 4-isopropylphenol was then dehydrogenated to produce 4-isopropenylphenol.

Renewable energy strategy analysis in relation to environmental pollution for BRICS, G7, and EU countries by using a machine learning framework and panel data analysis

The present research uses machine learning, panel data and time series prediction and forecasting techniques to establish a framework between a series of renewable energy and environmental pollution parameters, considering data for BRICS, G7, and EU countries, which can serve as a tool for optimizing the policy strategy in the sustainable energy production sector. The results indicates that XGBoost model for predicting the renewable energy production capacity reveals the highest feature importance among independent variables is associated with the gas consumption parameter in the case of G7, oil consumption for EU block and GHG emissions for BRICS, respectively. Furthermore, the generalized additive model (GAM) predictions for the EU block reveal the scenario of relatively constant renewable energy capacity if gas consumption increases, while oil consumption increases determine an increase in renewable energy capacity until a kick point, followed by a decrease. The GAM models for G7 revealed the scenario of an upward trend of renewable energy production capacity, as gas consumption increases and renewable energy production capacity decreases while oil consumption increases. In the case of the BRICS geopolitical block, the prediction scenario reveals that, in time, an increase in gas consumption generates an increase in renewable energy production capacity. The PCA emphasizes that renewable energy production capacity and GHG, respectively CO2 emissions, are highly correlated and are integrated into the first component, which explains more than 60% of the variance. The resulting models represent a good prediction capacity and reveal specific peculiarities for each analyzed geopolitical block. The prediction models conclude that the EU economic growth scenario is based on fossil fuel energy sources during the first development stage, followed by a shift to renewable energy sources once it reaches a kick point, during the second development stage. The decrease in renewable energy production capacity when oil consumption increases indicates that fossil fuels are in trend within the G7 economy. In the case of BRICS, it is assumed that gas consumption appears because of increasing the industrial capacity, followed by the increase of economic sustainability, respectively. In addition, the generalized additive models emphasize evolution scenarios with different peculiarities, specific for each analyzed geopolitical block.