Wyniki wyszukiwania - BazTech

1

Forecasting particulate matter concentrations with deep neural networks using meteorological data

Bernacki Jarosław, Sówka Izabela

Zeszyty Naukowe SGSP / Szkoła Główna Służby Pożarniczej

|

2026

|

Nr 98 (tom 1)

85--102

EN

Particulate matter (PM), especially PM10 and PM2.5, poses a significant threat to human health and the environment. Accurate forecasting of particulate matter concentrations is essential for air quality management, public health protection, and the implementation of effective pollution reduction strategies. In this study, we investigate the problem of short-term forecasting of PM10 and PM2.5 concentrations using historical measurements. To address this challenge, we propose and evaluate two independent deep learning approaches: the Kolmogorov–Arnold Network (KAN) and the temporal fusion transformer (TFT). The KAN model is designed to capture complex nonlinear relationships within air quality time series, whereas the TFT architecture utilises attention mechanisms to model temporal dependencies and identify relevant patterns over time. The proposed models are trained and tested on real-world air quality datasets in two ways: using only historical concentrations and using both historical concentrations and meteorological data. The forecasting performance is assessed using standard metrics, including MAE, MSE, and R2 measures. Experimental results confirm the efficacy of the proposed methods, compared with the LSTM-based baseline model.

2

Management of logistics processes in road freight transport under conditions of sectoral digitalisation

Yelesheva Zhanna, Kanzhebayeva Gaukhar, Spanova Yerkezhan, Ustemirova Raigul, Shortanbayeva Aigul

Systemy Logistyczne Wojsk

|

2026

|

Vol. 64, no. 1

125--140

EN

Modern road freight transport faces increasing demands for speed and economic efficiency, rendering traditional planning methods insufficient. Concurrently, growing transit flows in Kazakhstan necessitate an urgent review of infrastructure and logistics strategies. The research niche of this article is the integration of digital platforms into existing logistics systems, specifically focusing on the interaction between different participants under various management models in road freight transport. The primary aim of the study was to justify the effectiveness of digital tools for optimising the management of logistics processes. The central research question evaluated the effectiveness of centralised, decentralised, and hybrid logistics flow management models under the implementation of digital solutions. The methodology relied on transport flow modelling, big data analysis, and the simulation of logistics processes. Data spanning 2020-2025 from official transport portals and meteorological resources in Kazakhstan were utilised to recreate authentic logistics structures. The quantitative simulation results demonstrated that adopting a hybrid management model integrated with geographic information systems and IoT reduced average vehicle downtime by 18% and improved peak-hour delivery reliability to 94%. Furthermore, pilot scenarios using a decentralised strategy reduced peak-hour delivery times by 12% and unplanned stops by 17%. Concurrently, based on the synthesis of secondary literature, the adoption of digital solutions within such models can potentially reduce transportation costs by 15-25% and improve demand forecasting accuracy by 45%. In conclusion, within the modelled Kazakhstan-specific road, climatic, and infrastructure conditions, the results suggest that hybrid digital logistics management may improve selected operational indicators compared with centralised and decentralised models, providing actionable directions for logistics policy specifically for the analysed routes.

3

Integration of artificial intelligence systems into the air defence of critical infrastructure

Volkov Andrii, Lezik Oleksandr, Halkin Yurii, Popadiuk Roman, Terletskyi Bohdan

Systemy Logistyczne Wojsk

|

2026

|

Vol. 64, no. 1

57--74

EN

This study examines the extent to which artificial intelligence (AI) enhances air-defence systems in countering modern air threats. Addressing the research niche at the intersection of algorithmic autonomy and time-critical defence decision-making, the study aims to assess whether mission-tailored AI pipelines, integrated across sensing, fusion, tracking, and command layers, improve detection latency, classification accuracy, trajectory prediction, and engagement success while reducing false alarms. The research is structured around testable sub-hypotheses (H1–H4). The study employs a modelling and simulation approach supported by a critical literature review. Scenario-based simulations were used to evaluate the impact of AI integration in selected air-defence systems protecting critical infrastructure. The results indicate substantial performance improvements. For example, integration of AI into the Patriot PAC-3 reduced mean target-detection time from 18 to 4 s and increased classification accuracy from 72% to 94%. Signal-processing throughput increased from 1200 to 8400 signals per minute, while reaction times (e.g., NASAMS) decreased from 35 to 8 s and interception success rose from 65% to 91%. For IRIS-T SLM, trajectory-prediction error decreased from 430 m to 55 m, and computation time from 7.0 to 1.5 s. The proportion of autonomous decisions increased from 25% to 80%, while false-alarm rates declined by 78.6%. These findings, derived from validated simulation scenarios, demonstrate that AI significantly improves adaptability, precision, and response speed in high-tempo environments. However, effective implementation requires strengthened cybersecurity, rigorous model validation, human-in-the-loop governance, and updates to regulatory frameworks to ensure safety, accountability, and interoperability.

4

Econometric modeling of unemployment rate in the United Kingdom : from classical ARIMA to exogenous and machine learning approaches

Tran Van Hai Trieu, Tran Tinh Minh Tu

Operations Research and Decisions

|

2026

|

Vol. 36, No. 2

85--107

EN

Unemployment is a key macroeconomic indicator for the labour market’s health. Economic shocks, political changes, and structural shifts in the UK have shaped its dynamics. Using 326 monthly observations from 1997–2024 (UK Office for National Statistics), this study forecasts unemployment via ARIMA(1,1,1), ARIMAX, Random Forest, and XGBoost. Especially, ARIMA works for short-term predictions but misses structural breaks and non-linearities. ARIMAX, with gross value added as an exogenous variable, offers slight gains yet suffers from heteroskedasticity. XGBoost delivers the best performance by capturing nonlinear relationships, but direct interpretability is limited. The structural stability test was inconclusive, constraining regime-switching or rolling forecasts. Future research should address these limitations and integrate SHAP-based interpretability with feature significance analysis to better understand model behaviour and the drivers of unemployment.

5

Proposal of Support Planning System for Magnesite Mining Operations Based on an Assortment Volume Sale Forecasting

Kačmáry Peter, Kleinová Kristína

Management Systems in Production Engineering

|

2026

|

nr 1 (34)

68--75

EN

In the long term, the mining industry can be regarded as market volatile in terms of commodity price movements and sales. Although the general demand for raw materials is increasing, volatility in the different segments of the industry is visible. This paper presents a model for production planning system based on forecast for streamlining Magnesite assortment production in a prominent mining company in Slovakia. The forecast is based on several approaches i.e. quantitative approach – ARIMA method and regression and qualitative-probabilistic approach will be formed by the relevance tree method and discrete Markov chain under the final corrections of an expert (planner). The aim is to provide a medium-term production outlook over a 2-year time horizon for total magnesite production at active mining operation in Slovakia. The planning of magnesite production or extraction is thus based on the forecasted demand for particular processed product ranges in which magnesite is significantly or fully represented. Compared to the previous on-demand planning method, this innovative and implemented system has resulted in a more even production and a reduction of extracted magnesite stock by approximately 20%.

6

Simulation studies on the impact of using demand forecasts based on deep neural networks for inventory replenishment efficiency

Krzyżaniak Stanisław, Cyplik Piotr, Bartkowiak Marcin, Górecki Tomasz, Koralewski Adam

LogForum

|

2026

|

Vol. 22, no 1

111--124

EN

Background: Recent advancements in supply chain management, supported by information technology, have enabled reductions in inventory levels, among other operational improvements. Nevertheless, inventory-related challenges persist. Economic factors, particularly various forms of uncertainty, often necessitate holding inventory to ensure product availability. Demand variability, which is frequently unpredictable, remains a major challenge in numerous industries and requires the creation of safety buffers. Addressing this issue calls for increasingly sophisticated forecasting methods within replenishment models. Forecasts based solely on traditional time series methods offer limited improvements, whereas advanced approaches using machine learning and deep neural networks provide significantly greater potential. These models are capable of identifying factors that influence customer purchasing decisions, leading to more accurate demand forecasts and, consequently, a stronger foundation for improving replenishment processes. Objective: The primary aim of the research was to illustrate the extent to which advanced demand forecasting models can improve replenishment efficiency, particularly by reducing inventory levels. Methods: Simulation techniques were employed to replicate the replenishment process under various forecasting scenarios based on historical data. This dataset consisted of demand patterns for 1,000 Walmart stock-keeping units (SKUs), publicly released by the retailer for research purposes. The forecast methods examined included a benchmark arithmetic mean model, seven traditional time series-based models, and five advanced models employing machine learning and deep learning techniques. All simulations were conducted using the Reorder Cycle replenishment model with a uniform inventory review cycle across products. The second control parameter, the maximum inventory level (S), was fixed for the benchmark model and dynamically adjusted for the remaining twelve models according to their respective forecasts. A total of 13,000 replenishment simulation cycles were performed. Key performance indicators included average inventory and the service level (SLα), defined as the probability of fully satisfying demand within a replenishment cycle. The parameter S was calibrated to ensure a consistent service level across models. Consequently, the inventory level index was the primary measure of replenishment efficiency, enabling comparisons between the twelve forecasting models and the benchmark. Additionally, the relationship between this index and forecast quality improvement was analyzed using forecast error measurements, specifically the root mean square error (RMSE). Results: The findings confirm that inventory levels can be reduced by an average of 10% through the application of machine learning and deep neural network-based forecasting methods, without compromising service quality. The magnitude of the reduction varied depending on specific temporal demand patterns. Conclusions: The observed improvements can be attributed to two main factors: increased forecast accuracy and the dynamic adjustment of the maximum inventory level (S), based on current forecasts and their associated error estimates. Furthermore, replenishment efficiency may be enhanced further by selecting the most appropriate forecasting method for individual products during specific time periods.

7

A deep ensemble learning framework for forecasting root zone soil moisture in semi-arid regions of South Bihar

Patel Ravi, Kumar Aditya, Koch Niharika, Singh Gurpreet, Yadav Jainath

Acta Geophysica

|

2026

|

vol. 74, no. 3

art. no. 168, s. 1--23

EN

Accurate forecasting of root zone soil moisture (RZSM) is crucial for effective groundwater management, irrigation planning, and drought mitigation in semi-arid agrarian regions such as South Bihar. Traditional hydrological models mostly struggle to figure out the nonlinear temporal dynamics inherent in soil moisture data. This study proposes a hybrid deep ensemble learning framework that leverages the strengths of six deep neural networks (LSTM, Bi-LSTM, GRU, Bi-GRU, RNN, and CNN) as base models, with eXtreme Gradient Boosting (XGBoost) employed as a meta-learner in a stacked ensemble architecture. Each model is independently trained on Groundwater Root Zone Soil Wetness (GWETROOT) time series data (Jan 1985 to June 2025), and their predictions are aggregated using XGBoost to generate a robust final forecast. The study utilizes daily RZSM data (GWETROOT, surface to 100 cm depth) obtained from the NASA POWER project, which provides satellite-and model-based gridded estimates. The performance of all models was evaluated across five districts in Bihar (Arwal, Aurangabad, Gaya, Jehanabad, and Nawada) using standard statistical metrics including MAE, MAPE, RMSE, MSE, and R2. Results demonstrate that the proposed ensemble approach consistently outperformed individual models, offering improved accuracy (R2 = 0.99) and generalizability. The findings highlight the effectiveness of integrating deep learning with ensemble techniques for soil moisture forecasting and offer a scalable solution for climate-resilient water resource management.

8

Passenger traffic in Polish seaports in the face of the COVID-19 pandemic

Sobczuk Sebastian, Borucka Anna

Zeszyty Naukowe Politechniki Morskiej w Szczecinie

|

2025

|

nr 81 (153)

57--66

EN

The outbreak of the COVID-19 pandemic had a profound impact on the global economy and disrupted daily life across many regions of the world. Restrictions imposed at the time, such as the closure of national borders and restrictions on mobility, led to unprecedented challenges for the transportation sector and related tourism services compared with any prior crisis. This disruption also affected maritime passenger transport in Poland. This article aims to assess the impact of the COVID-19 pandemic on passenger traffic in Polish seaports and to develop mathematical models that could support management in the event of future epidemic threats. Three different models are proposed, which showed that the epidemic crisis resulted in a significant decline in passenger traffic at Polish seaports. The most accurate proved to be the SARIMA model. The Holt-Winters model also demonstrated high fitting and predictive performance. In turn, the STL model offered intriguing insights with its time series decomposition, enabling a detailed analysis of individual components. A comparative analysis of the proposed models confirms their usefulness in forecasting passenger traffic in seaports in the face of disruptions such as the COVID-19 pandemic. These models can be an effective decision-support tool, helping to reduce the negative effects of future epidemic threats.

9

Management and forecasting of road accidents in Poland and Montenegro using neural networks

Gorzelańczyk Piotr, Backovic Tamara, Melović Boban

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2025

|

Vol. 28

153--172

EN

Despite a general decline in recent years, road traffic accidents remain a significant public safety concern in both Poland and Montenegro. Although accident rates were affected by the COVID-19 pandemic, the persistent frequency of such incidents underscores the urgent need for further preventive measures to enhance road safety. The aim of this study is to forecast the number of road traffic accidents in Poland and Montenegro for the period 2024-2030. To achieve this, historical data on annual accident counts were obtained from Monstat (Montenegro) and the Polish Police. These datasets were then analyzed using selected neural network models to generate projections for the specified timeframe. The results suggest a potential stabilization in the number of traffic accidents in the near future. This forecast is influenced by several factors, including the steady increase in car ownership and ongoing investments in road infrastructure, such as the construction of new motorways and local roads. It should be noted, however, that the inherent uncertainty in data sampling – used for training, testing, and validating the models – places natural limitations on the precision of the forecasts.

10

Forecasting the number of road accidents in Poland using trend models

Gorzelanczyk Piotr, Jurkovic Martin

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2025

|

Vol. 28

187--197

EN

Every year a very large number of people die on the roads. From year to year the value decreases, but it is still a very large number. The purpose of this article is to forecast the number of road accidents in Poland. The study was divided into two parts. The first was the analysis of annual data from police statistics on the number of road accidents in Poland in 2000-2021, and on this basis the forecast of the number of road accidents for 2022-2031 was determined. The second part of the study, dealt with monthly data from 2000-2021. Again, the analyzed forecast for the period January 2022 – December 2023 was determined.

11

Modelling Military Equipment Losses with Open-Source Visual Intelligence: Evidence from the War in Ukraine

Sobczyk Olimpia Wiktoria

Systemy Logistyczne Wojsk

|

2025

|

Vol. 63, no. 2

151--163

EN

The research niche of this article is the use of open-source visual intelligence and automated computer vision, combined with classical time-series modelling, to analyse and forecast military equipment losses in the Russo-Ukrainian war. The purpose of the research was to test whether visually confirmed data (the Oryx repository) can be algorithmically transformed into a reliable weekly series and used for short-term forecasting. Two hypotheses were examined: (H1) open visual data yield a series with stable trend and seasonality; (H2) ARIMAX with Fourier terms outperforms seasonal ARIMA at short horizons. The methodology comprised a Python pipeline in which YOLOv8 localized date stamps and EasyOCR read them; STL decomposition characterized the trend and seasonal structure. Forecasting employed SARIMA and ARIMAX with sine/cosine pairs for the annual period. Results confirm pronounced annual seasonality (peaking in March–April) and a trend cresting in early spring 2023; relative to SARIMA, ARIMAX reduced errors by 14.6–23.7% (MAE) and 23.8–25.5% (RMSE) in both in-sample fit and rolling validation. The conclusions indicate that, despite limitations (a lower bound on true losses), public visual data provide a robust, verifiable analytical basis with strong predictive potential; future work should incorporate machine learning, exogenous covariates, and probabilistic forecasting.

12

Identyfikacja i prognozowanie zagrożeń elementem odstraszania i wzmacniania odporności państwa

Keplin Jarosław, Ligęza Krzysztof, Kupiński Jerzy

Rocznik Bezpieczeństwa Morskiego

|

2025

|

R. XIX

1105--1131

PL

Artykuł omawia problem identyfikacji i prognozowania zagrożeń jako kluczowego elementu wzmacniania odporności państwa, w kontekście dynamicznych zmian zachodzących we współczesnym środowisku bezpieczeństwa. Autorzy zwracają uwagę na nieprzewidywalność i nagłość występowania zagrożeń określanych jako „czarne łabędzie”, które mogą powodować istotne zmiany w światowym ładzie. Zaproponowany model analityczny opiera się na systemowym i procesowym podejściu, uwzględniającym obszary funkcjonowania państwa takie jak polityczny, ekonomiczny, militarny, społeczny, informacyjny i infrastruktury (PEMSII). W modelu tym kluczową rolę odgrywa identyfikacja zagrożeń krytycznych, głównych i newralgicznych, dokonywana przez zespoły eksperckie na podstawie danych historycznych oraz obserwacji otoczenia. Proces analizy obejmuje metody heurystyczne, analizy SWOT, a także analizę synchroniczną i diachroniczną, co umożliwia uchwycenie związków przyczynowo-skutkowych i przewidywanie przyszłych zagrożeń. Istotnym elementem proponowanego podejścia jest ocena ryzyka, bazująca na szacowaniu prawdopodobieństwa wystąpienia oraz skutków zagrożeń według precyzyjnych skal oceny. Artykuł podkreśla znaczenie właściwego doboru wskaźników i mierników, które pomagają obiektywnie ocenić realny stan bezpieczeństwa i potencjalne skutki zagrożeń. Na podstawie otrzymanych wyników tworzone są scenariusze rozwojowe, uwzględniające zarówno bezpośrednie, jak i pośrednie konsekwencje zagrożeń. Autorzy sugerują konieczność dalszego doskonalenia narzędzi analitycznych oraz podkreślają potrzebę rozwijania strategii zarządzania bezpieczeństwem państwa, dostosowanych do zmieniającego się środowiska globalnego. Całość przedstawionego podejścia ma na celu zwiększenie odporności państwa na nieprzewidywalne kryzysy, zarówno w skali lokalnej, jak i międzynarodowej.

EN

The article addresses the issue of identifying and forecasting threats as a crucial element in strengthening state resilience within a dynamically changing security environment. It highlights the unpredictability and sudden emergence of threats known as "black swans," which can significantly alter global order. The proposed analytical model is based on a systematic and process-oriented approach, considering areas of state functioning including political, economic, military, social, informational, and infrastructure dimensions (PEMSII). Within this model, the identification of critical, main, and pivotal threats is conducted by expert teams using historical data and environmental observations. The analytical process involves heuristic methods, SWOT analysis, and synchronic and diachronic analyses, enabling an understanding of causeand-effect relationships and forecasting of future threats. A critical aspect of the proposed approach is risk assessment based on estimating the probability and impact of threats using precise evaluation scales. The article emphasizes the importance of selecting appropriate indicators and metrics to objectively assess the actual security situation and potential impacts of threats. Based on obtained results, developmental scenarios are created, accounting for both direct and indirect consequences of threats. Authors suggest the necessity of further improving analytical tools and underline the need for developing state security management strategies adapted to a rapidly evolving global environment. The overall approach aims to enhance the state’s resilience to unpredictable crises at both local and international levels.

13

Forecasting electricity prices in the Polish Day-Ahead Market using machine learning models

Sowiński Rafał, Komorowska Aleksandra

Polityka Energetyczna

|

2025

|

T. 28, z. 2

211--230

EN

Given the constantly changing market situation for electricity prices, driven by shifts in the energy mix, regulatory reforms, and broader socio-economic factors, it is necessary to reassess the understanding of price forecasting periodically. Traditional statistical methods may struggle when faced with heightened volatility, nonlinear dependencies, and rapidly changing input features. In contrast, machine learning models, particularly Artificial Neural Networks (ANNs), can adapt more effectively to complex, non-stationary patterns in price time series. In this study, six distinct artificial neural network (ANN) architectures were developed and trained using eight years of historical Polish Day-Ahead Market electricity price data (2016–2024). Four of these were plain deep learning models: a Multilayer Perceptron (MLP), a Convolutional Neural Network (CNN), a Long Short-Term Memory (LSTM) model, and a Gated Recurrent Unit (GRU) model. Two others were hybrid models combining convolutional layers with recurrent layers. The hybrid architectures, namely CNN+LSTM and CNN+GRU, were designed to leverage the capacity of CNN to automatically extract features from narrower sliding windows of past prices and the LSTM/GRU layers’ ability to capture long-term temporal dependencies. The models’ performances were evaluated using three metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination (R2). The top-performing CNN+LSTM achieved an MAE of 75.21 PLN/MWh, an RMSE of 103.64 PLN/MWh, and an R2 of 0.59. Results were also compared against several models previously reported in the literature. These results may be used to improve price forecasting by indicating the optimal pathways for building forecasting models and, in extension, lead to more efficient power system planning.

PL

Ze względu na stale zmieniające się ceny energii elektrycznej, spowodowane zmianami w miksie energetycznym, regulacyjnymi i innymi czynnikami społeczno-ekonomicznymi, konieczne staje się okre sowe weryfikowanie podejścia do prognozowania cen. Tradycyjne metody statystyczne mogą zawodzić w warunkach nasilonej zmienności, nieliniowych zależności i często zmieniających się cech wejściowych. Modele uczenia maszynowego, a zwłaszcza Sztuczne Sieci Neuronowe (SSN), potrafią skutecznie dostosowywać się do złożonych, niestacjonarnych wzorców w szeregach czasowych. W niniejszym badaniu opra cowano i wytrenowano sześć różnych modeli SSN, korzystając z danych historycznych z Polskiego Rynku Dnia Następnego z lat 2016–2024. Cztery z tych modeli to czyste modele głębokiego uczenia: wielowar stwowy perceptron (MLP), sień konwolucyjna (CNN), długa pamięć krótkotrwała (LSTM) oraz bramkowa jednostka rekurencyjna (GRU). Dwa pozostałe to architektury hybrydowe, oznaczone jako CNN+LSTM i CNN+GRU, łączą zdolność CNN do wychwytywania cech z węższych okien czasowych i umiejętność warstw rekurencyjnych do uczenia się zależności długoterminowych. Wydajność modeli oceniano na pod stawie trzech miar: średniego błędu bezwzględnego (MAE), pierwiastka ze średniego błędu kwadratowego (RMSE) i współczynnika determinacji (R2). Najlepsze wyniki osiągnęła architektura CNN+LSTM, uzy skując MAE na poziomie 75,21 zł/MWh, RSME równe 103,64 zł/MWh i R2 wynoszące 0,59. Wyniki te mogą zostać wykorzystane do usprawnienia procesów prognozowania cen energii elektrycznej poprzez wskazanie wytycznych dotyczących projektowania modeli prognostycznych opartych na uczeniu maszy nowym, co z kolei może wiązać się z wydajniejszym planowaniem działania systemu energetycznego.

14

Optimising the Operation of Ships with Artificial Intelligence Systems

Bolkvadze Nugzar, Verdzadze Ruslan, Bazaian Aram, Bolkvadze Levan, Gabedava George

Polish Maritime Research

|

2025

|

nr 4

119--131

EN

The objective of this study was to conduct an empirical evaluation of the effectiveness of artificial intelligence systems in optimising the operation of commercial maritime vessels. The methodology involved collecting and processing telemetry from 58 synchronised onboard measurement channels, including temperatures, vibration metrics, gyroscopic data, trim and heel angles, and data from automatic identification systems, differential global positioning systems, and radar signals. Data were sampled at intervals of 1 s, filtered using the Hampel method, and aggregated into frames of 3 min. A hybrid deep learning model was developed to forecast vessel speed, fuel usage, and stability. Experiments were conducted on 16 vessels: six container carriers (3,000 20-foot equivalent units class) and 10 Handymax bulk carriers (40,000–55,000 deadweight tons). These vessels completed 97 voyages between March 2023 and February 2024, 45% of which took place in the Black Sea and 55% in the North Sea. A validation campaign comprising 9,230 h of simulator trials and real-world deployment was carried out to test the artificial intelligence model under variable sea states and in scenarios involving disruptions to automatic identification and differential global positioning systems. The results showed a 12.4% reduction in average fuel consumption and an 8.2% decrease in voyage duration. Ship stability improved, with a 22% reduction in roll amplitude. Predictive maintenance algorithms achieved 95% accuracy, enabling early fault detection and reducing unscheduled downtime. Only three manual interventions were recorded during deployment, and course deviations remained below 1.3°. An environmental analysis revealed a 4.2% improvement in carbon intensity, demonstrating compliance with the International Maritime Organization Carbon Intensity Indicator standards.

15

Analytical analysis of the current situation and development prospects of the Southern Gas Corridor

Ismayilov Ramiz A., Guliyeva Turkan Sh., Mammadov Huseyn V.

Nafta-Gaz

|

2025

|

R. 81, nr 9

618--624

EN

Azerbaijan currently plays a key role in reducing Europe’s dependence on Russian gas and in diversification of gas pipeline routes. The predicted capacity of the Azerbaijani natural gas reserves, the volume of actual production, existing infrastructure, political stability, and participation in recent projects have demonstrated the country’s reliability as partner, which has been unequivocally acknowledged. This article presents an analysis of the current operations and prospective development directions of the Southern Gas Corridor, which plays a critical role in delivering natural gas to the European Union. The applied methodology is based on the dynamics of current and potential gas reserves which have the potential to support this energy corridor during its expansion phase with the increased natural gas volumes. Production trends, domestic demand, and export volumes have been analyzed accordingly, and forecasts have been generated based on current data and external sources for the coming years. Based on the conducted research, it was determined that the natural gas supply from existing Azerbaijan crude oil, gas, and gas condensate reserves, along with those located in the Caspian Sea area, as well as the potential transportation of natural gas from Turkmenistan and Kazakhstan, may lead to a significant increase in the volume of natural gas exported through the Southern Gas Corridor to Europe which is supported and proved by conducted calculations.

PL

Azerbejdżan odgrywa obecnie kluczową rolę w zmniejszaniu zależności Europy od rosyjskiego gazu oraz w dywersyfikacji tras gazociągów. Prognozowana wielkość zasobów gazu ziemnego w Azerbejdżanie, wielkość rzeczywistej produkcji, istniejąca infrastruktura, stabilność polityczna oraz udział w ostatnich projektach jednoznacznie potwierdziły niezawodność tego kraju jako partnera. W niniejszym artykule przedstawiono analizę bieżącej działalności i perspektyw rozwoju Południowego Korytarza Gazowego, który odgrywa kluczową rolę w dostawach gazu ziemnego do Unii Europejskiej. Zastosowana metodologia opiera się na analizie dynamiki obecnych i potencjalnych zasobów gazu, które mogą wesprzeć ten korytarz energetyczny w fazie rozbudowy wraz ze wzrostem wielkości dostaw gazu ziemnego. Przeanalizowano trendy w produkcji, popyt krajowy i wielkość eksportu, a na podstawie aktualnych danych i źródeł zewnętrznych opracowano prognozy na najbliższe lata. Na podstawie przeprowadzonych badań ustalono, że dostawy gazu ziemnego z istniejących zasobów ropy naftowej, gazu i kondensatu gazowego w Azerbejdżanie, wraz z zasobami znajdującymi się w regionie Morza Kaspijskiego, a także potencjalny transport gazu ziemnego z Turkmenistanu i Kazachstanu mogą doprowadzić do znacznego wzrostu ilości gazu ziemnego eksportowanego przez Południowy Korytarz Gazowy do Europy, co potwierdzają przeprowadzone obliczenia.

16

Shaping a Safe Working Environment in the Coal Production Process: Utilizing Model Studies to Assess Methane Hazard Formation

Tutak Magdalena, Brodny Jarosław, Romanyshyn Lyubomyr

Management Systems in Production Engineering

|

2025

|

nr 2 (33)

311--320

EN

The establishment of a safe working environment is one of the key challenges in the implementation of various production processes. This is particularly relevant to underground coal production, where the primary operations (exploitation) take place in an underground environment. In this context, the paper presents the results of a study on methane hazard formation during the coal production process. The analysis was conducted through model studies that included driven dog headings, longwall workings with and without auxiliary ventilation equipment, and collapsing goafs. The research methodology, mining region models, and validation of the obtained results were further supported by tests conducted under real conditions. The findings highlight the significant potential of model studies based on structural models for assessing ventilation hazards in the examined regions and the phenomena occurring within them. Based on these results, the identification and assessment of methane hazard levels in the studied regions were carried out. This, in turn, opens avenues for their practical application in enhancing both safety and efficiency in the mining production process. The developed methodology and models are universal in nature, offering a broad range of applications for studying various ventilation states, both in steady and unsteady conditions. Additionally, they allow for comprehensive predictions of methane concentration distributions, forming a critical basis for preventive measures and improvements in underground mining safety.

17

Application of neural networks for drought forecasting based on the standardised precipitation index

Fathiyana Rana Z., Haryadi Deny, Ananda Naufal, Hidayat Dinda J., Wicaksana Haryas Subyantara, Azahra Rahma Wafii, Saputra Hakim Giraldi

Journal of Water and Land Development

|

2025

|

no. 65

113--121

EN

Based on data from the National Disaster Management Agency, South Sumatra is one of the provinces with a reasonably large drought-affected area, totalling 8,853,691.009 ha. Drought is a hydrometeorological disaster, characterised by anomalous rainfall below normal levels. Reduced rainfall can lead to decreased soil moisture, reduced river flows, and a general scarcity of water, which limits availability of water both on the surface and in the soil. To anticipate and mitigate the impacts of drought, an accurate forecasting system is essential for effective disaster management and mitigation. This research focuses on forecasting drought using the standardised precipitation index (SPI) based on Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) algorithms. It compares LSTM and MLP algorithms by integrating rainfall data from the FY-4A satellite and observational rain gauges, which are processed to generate SPI values. These data are employed to train and test MLP and LSTM models in predicting future drought conditions. The results indicate that drought can be effectively predicted using both MLP and LSTM. However, the MLP outperforms the LSTM, as reflected by a higher Nash-Sutcliffe efficiency (NSE) value, a lower error rate, and a predicted date trend that more closely aligns with actual observations.

18

Heterogeneous ensemble neural network for forecasting the state of multi-zone heating facilities

Yukhymchuk Maria, Dubovoi Volodymyr, Harbar Zhanna, Yeraliyeva Bakhyt

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2025

|

T. 15, nr 2

94--99

EN

The research is aimed at increasing the accuracy of forecasting the state of multi-zone thermal facilities. Such facilities include multi-room premises, multi-zone greenhouses, tunnel kilns for brick production, and others. Thehigh inertia of such facilities reduces the effectivenessof "ad hoc control". Modern proactive control systems based on forecasting are mainly based on using neural network training. However, to forecastthe state of a specific multi-zone thermal facility, training the network requires a very large dataset, which is difficult to create and use. A combined neuro-structural method for forecasting the state of multi-zone thermal facilities is proposed, in which the structure of the neural model reflects the structureof the mutual influence of the facility zones. The research of the method has shown the possibility of ensuring sufficiently high forecast accuracywith a smaller size of the training dataset.

PL

Badania mają na celu zwiększenie dokładności prognozowania stanu wielostrefowych obiektów cieplnych. Obiekty takie obejmują obiekty wielopokojowe, wielostrefowe szklarnie, piece tunelowe do produkcji cegieł i inne. Duża bezwładność takich obiektów zmniejszaskuteczność "sterowania ad hoc". Nowoczesne proaktywne systemy sterowania oparte na prognozowaniu opierają się głównie na szkoleniu sieci neuronowych. Jednak w celu prognozowania stanu konkretnego wielostrefowego obiektu termicznego, szkolenie sieci wymaga bardzo dużego zbioru danych, który jest trudnydo utworzenia i wykorzystania. Zaproponowano połączoną neurostrukturalną metodę prognozowania stanu wielostrefowych obiektów cieplnych, w której struktura modelu neuronowego odzwierciedla strukturę wzajemnego wpływu stref obiektu. Badania metody wykazały możliwość zapewnienia wystarczająco wysokiej dokładności prognozy przymniejszym rozmiarze zbioru danych treningowych.

19

Development of a system for predicting failures of bagging machines

Huliieva Nataliia, Lishchyna Nataliia, Pasternak Viktoriya, Huliieva Zemfira

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2025

|

T. 15, nr 4

10--13

EN

The reliabilityand effective operation of machines is a pressing problem for every enterprise, which requires labour intensivesystematizationof production processes.The goal is to develop an algorithm and a system for predicting failures of packaging machines based on the analysisof operational indicators.The scientific novelty lies in the integration of statistical data to assess the efficiency of machine operation and predict possible failures, which allows significantly improving maintenance processes and reducing the risks of unforeseen breakdowns.The practical valueis the development of a forecasting system that collects the necessary statistical data and performs forecasting. Based on the collected data, an assessment of the efficiency of work and forecasting of possible failures is carried out. The forecasting system is demonstrated on the example of packaging machines LEMO INTERmat ST-SA 850 of "Tatrafan" LLC.Two research methods were used: calculation (mathematical) and forecasting system (least squares method). The forecasting system provides two ways of presenting data: tabular and graphical. Tabular presentation of data allows filtering information according to various criteria, while graphical display is implemented in the formof diagrams showing the operating time and downtime of machines.The main results are the determined rangeof probable failure of LEMO INTERmat ST-SA 850 packaging machines, which lies in the range from 9090.5to 12736.5 hours of operation and almost coincides with the manufacturer's warranty period. With timely maintenance, it is possible to increase the lower limit of this interval.

PL

Niezawodność i efektywna praca maszyn stanowi palący problem każdego przedsiębiorstwa, wymagający pracochłonnego usystematyzowania procesów produkcyjnych. Celem jest opracowanie algorytmu i systemu prognozowania awarii maszyn pakujących na podstawie analizy wskaźników eksploatacyjnych. Nowością naukową jest integracja danych statystycznych w celu oceny efektywności pracy maszyn i przewidywania ewentualnych awarii, co pozwala znacząco usprawnić procesy utrzymania ruchu i ograniczyć ryzyko nieprzewidzianych awarii. Znaczenie praktyczne ma opracowanie systemu prognostycznego, który będzie zbierał niezbędne dane statystyczne i wykonywał prognozowanie. Na podstawiezebranych danych przeprowadzana jest ocena efektywności pracy i prognozowanie ewentualnych awarii. System prognozowania zaprezentowano na przykładzie maszyn pakujących LEMO INTERmat ST-SA 850 firmy Tatrafan LLC.W badaniach zastosowano dwie metody: obliczeniową (matematyczną) i prognostyczną (metodę najmniejszych kwadratów). System prognozowania umożliwia prezentację danych na dwa sposoby: w formie tabelarycznej i graficznej. Prezentacja danych w formie tabelarycznej pozwala na filtrowanie informacji według różnych kryteriów, natomiast prezentacja graficzna realizowana jest w formie diagramów, obrazujących pracę i przestoje maszyn.Głównymi wynikami jest określony zakres prawdopodobnej awarii maszyn pakujących LEMO INTERmat ST-SA 850, który mieści się w przedziale od 9090,5 do 12736,5 godzin pracy i niemal pokrywa się z okresem gwarancji producenta. Dzięki terminowej konserwacji możliwe jest podwyższenie dolnej granicy tego przedziału.

20

Trends and challenges of forecasting in the airline industry research

Dewi Oki Anita Candra, Masruroh Nur Aini, Wibowo Budhi Sholeh

Engineering Management in Production and Services

|

2025

|

Vol. 17, no. 2

23--36

EN

This study aims to comprehensively review aviation forecasting research by identifying its bibliometric trends, evolving research areas, and thematic developments. It focuses on understanding the aviation industry’s research gaps, highlighting emerging trends, and offering insights into future forecasting innovations. A systematic literature review in the Scopus database used Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) and bibliometric analysis. It identified key patterns, influential publications, and emerging topics. A science mapping analysis was executed to pinpoint research trends in airline forecasting using Biblioshiny to visualise the network analysis and thematic evolution keywords mapping. The study categorised research trends and identified underexplored areas for future investigation. The findings reveal significant shifts in aviation forecasting research, with three distinct phases of publication growth and a surge in output from 2016 onwards. Passenger demand forecasting remains the most researched topic, though its growth has stabilised. Emerging issues such as customer behaviour, financial forecasting, and dynamic pricing have gained prominence, driven by advancements in machine learning and big data analytics. The study also highlights transitioning from traditional statistical methods to more advanced predictive techniques, emphasising real-time decision-making and operational efficiency. Established research areas, such as air cargo forecasting and f leet scheduling, have become more standardised, reducing the need for further innovation.