LSTM With Bayesian Optimization for Forecasting of Local Scour Depth Around Bridges and Piers DOI
Ahmed Ali, Saman Ebrahimi, Muhammad Masood Ashiq

и другие.

Advances in computational intelligence and robotics book series, Год журнала: 2023, Номер unknown, С. 207 - 221

Опубликована: Дек. 29, 2023

Scour is a critical issue that impacts the safety and strength of bridges. Precise scour forecasts around bridge piers can provide useful data for engineers to bring preventive actions. This study uses long short-term memory (LSTM) neural network with Bayesian optimization forecast bridges piers. The LSTM was trained tested using only depth from calibrated numerical model. outcomes indicate proposed model provides precise forecasts. presents performance predicting piers, which help enhance stability has shown acceptable outcomes, rank correlation equal 0.9866 in training stage 0.9655 testing stage. Moreover, used 11 minutes.

Язык: Английский

Directions of Price Transmission on the Diesel Oil Market in Poland DOI Creative Commons
Grzegorz Przekota, Anna Szczepańska-Przekota

Energies, Год журнала: 2025, Номер 18(1), С. 139 - 139

Опубликована: Янв. 1, 2025

The formation of crude oil prices and their impact on diesel represent a significant economic challenge. economy’s dependence energy resources means that the development competitiveness economy, as well standard living society, are contingent upon prices, including those liquid fuels. It is therefore important to recognise process by which changes in price affect other commodities. recognition these dependencies will have implications for political fiscal decision-making at governmental level, investment strategies enterprises, patterns consumption. research presented this paper concerns transmission wholesale retail Poland between 2010 2024. A correlation analysis, Granger causality test, an impulse response function calculation were conducted. demonstrated cause oil. However, bilateral, with stronger flow impulses from than vice versa. These findings evolution market. While current situation may lead monopolisation market, it also provides decision-makers ability regulate potentially reducing volatility relative raw material quotations. Furthermore, offers safeguard market against speculative activities mitigate sudden increases prices.

Язык: Английский

Процитировано

0

Assessment of the Potential of European Union Member States to Achieve Climate Neutrality DOI Open Access
Anna Bluszcz, Anna Manowska, Nur Suhaili Mansor

и другие.

Sustainability, Год журнала: 2024, Номер 16(3), С. 1311 - 1311

Опубликована: Фев. 4, 2024

Climate neutrality is the main environmental goal set for European Union Member States until 2050. EU economies can achieve this ambitious climate by reducing emission intensity of economies, which has been achieved many years pollution emitted industry. The aim study focused primarily on demonstrating degree relationship between variables describing economic growth, GDP, and level CO2 emissions. In first stage research, potential countries to was assessed, estimating correlation GDP indices in relation 2013 Research shown that despite countries’ differences structure their energy balances, they independence growth from economies. research also concerns Poland’s special situation compared other according balance based coal. A model differential equations used simulate impact intensity, share biofuels temperature concentration 2030, using data Poland as an example. analysis answer question whether transformation country will assumed reduction goals 2030.

Язык: Английский

Процитировано

4

Spatiotemporal heterogeneity of carbon emission intensity distribution in the tourism industry and its calculation methods DOI Creative Commons
Xiaodong Mao, Yan Zhuang

Sustainable Energy Research, Год журнала: 2025, Номер 12(1)

Опубликована: Апрель 4, 2025

Язык: Английский

Процитировано

0

Research on the decision-making method of coal order price and coal purchase quantity based on prediction DOI
Yunrui Wang, Yao Wang, Jinghui Zhang

и другие.

Computers & Industrial Engineering, Год журнала: 2024, Номер 188, С. 109885 - 109885

Опубликована: Янв. 4, 2024

Язык: Английский

Процитировано

3

The Transmission Mechanisms and Impacts of Oil Price Fluctuations: Evidence from DSGE Model DOI Creative Commons
Bei Zhang,

Xiaoqing Ai,

Xingming Fang

и другие.

Energies, Год журнала: 2022, Номер 15(16), С. 6038 - 6038

Опубликована: Авг. 20, 2022

This paper constructs an open economy dynamic stochastic general equilibrium (DSGE) model with oil to investigate the transmission mechanism and impact effects of price fluctuations driven by different factors on China’s macroeconomy using quarterly data from 1996 2019. The results show that international crude supply-driven decline promotes positive output growth in short run through cost effect supply channel, production regulation will dampen incentive invest new energy sector long run. Domestic economic development demand-driven increases act demand driving prices fluctuate same direction, generating a negative real balance interest rate channel. oil-specific foreign nominal shocks is transmitted exchange triggering imported inflation, lower aggregate demand, output. Different sources have mechanisms thus differential effects. For this reason, based root causes fluctuations, policy recommendations deal situation are proposed at level, level.

Язык: Английский

Процитировано

12

Forecasting Liquefied Natural Gas Bunker Prices Using Artificial Neural Network for Procurement Management DOI Creative Commons
Kyunghwan Kim, Sangseop Lim, Changhee Lee

и другие.

Journal of Marine Science and Engineering, Год журнала: 2022, Номер 10(12), С. 1814 - 1814

Опубликована: Ноя. 24, 2022

The LNG price is basically determined based on the oil price, but other than that, it also by influence of method transportation; storage; processes; and political, economic, geographical instability. Liquefied natural gas (LNG) may not reflect its market value if destination purchase restricted or contract includes a take-or-pay clause. Furthermore, difficult for buyer to flexibly manage procurement, resulting in decoupling prices. Therefore, as bunker expected be more volatile marine future, shipping companies need prepare countermeasures scientific forecasting techniques. This study aims first analyze short-term prices using recurrent neural network (RNN) models suitable highly data such time series. Predictive analysis was performed simple RNN, long memory (LSTM), gated unit (GRU) models, which effectively forecast time-series data, prediction performance LSTM among three excellent. had relatively excellent outliers beyond. In addition, possible ship operating costs with improved practice. this contributes establishing systematic strategy supervisors global companies, port authorities, bunkering companies.

Язык: Английский

Процитировано

8

A Hybrid Forecast Model of EEMD-CNN-ILSTM for Crude Oil Futures Price DOI Open Access
Jingyang Wang, Tianhu Zhang, Tong Lü

и другие.

Electronics, Год журнала: 2023, Номер 12(11), С. 2521 - 2521

Опубликована: Июнь 2, 2023

Crude oil has dual attributes of finance and energy. Its price fluctuation significantly impacts global economic development financial market stability. Therefore, it is necessary to predict crude futures prices. In this paper, a hybrid forecast model EEMD-CNN-ILSTM for proposed, which based on Ensemble Empirical Mode Decomposition (EEMD), Convolutional Neural Network (CNN), Improved Long Short-Term Memory (ILSTM). ILSTM improves the output gate (LSTM) adds important hidden state information original output. addition, learning cell at previous time in forget input gate, makes learn more fully from historical data. EEMD decomposes series data into residual sequence multiple Intrinsic Functions (IMF). Then, IMF components are reconstructed three sub-sequences high-frequency, middle-frequency, low-frequency, convenient CNN extract data’s features effectively. The accuracy improved efficiently by This paper uses daily Shanghai Energy Exchange China as experimental set. compared with seven prediction models: Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), LSTM, ILSTM, CNN-LSTM, CNN-ILSTM, EEMD-CNN-LSTM. results experiment show effective accurate.

Язык: Английский

Процитировано

4

Modeling And Enhancing Crude Oil Price Forecasting Using Enhanced Set Algebra-Based Heuristic Algorithm-Based Extreme Learning Machine DOI Creative Commons
Sudersan Behera,

A.V. Senthil Kumar,

Sarat Chandra Nayak

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Фев. 2, 2024

Abstract This study has two main aspects. Firstly, we combined the Nelder-Mead Simplex Algorithm with Set Algebra-Based Heuristic (SAHA) in order to improve SAHA's capacity do local searches. integration resulted a hybrid learning approach known as ESAHA. After that, use Enhanced Simulated Annealing Hybrid (ESAHA) six benchmark functions so that can see how well ESAHA works. Furthermore, utilize enhance weights and biases of an Extreme Learning Machine (ELM), resulting creation model referred ESAHA-ELM. We ESAHA-ELM predict final price crude oil datasets. In addition, employ SAHA, BMO, PSO, GA algorithms train ELM generate four alternative models for purpose comparison forecasting job. examine predictive accuracy each model, MAPE MSE error metrics. Additionally, implement Prediction Change Direction (POCID) statistical test determine if there are any significant differences between models. The experimental investigation shows relevance accurately capturing inherent volatility financial time series. it surpasses other such SAHA-ELM, MBO-ELM, PSO-ELM, GA-ELM.

Язык: Английский

Процитировано

1

Investigating the Impact of Agricultural, Financial, Economic, and Political Factors on Oil Forward Prices and Volatility: A SHAP Analysis DOI Creative Commons

H.J. Kim,

Hui-Sang Kim,

Sun‐Yong Choi

и другие.

Energies, Год журнала: 2024, Номер 17(5), С. 1001 - 1001

Опубликована: Фев. 21, 2024

Accurately forecasting crude oil prices is crucial due to its vital role in the industrial economy. In this study, we explored multifaceted impact of various financial, economic, and political factors on forward volatility. We used machine learning models forecast volatility based their superior predictive power. Furthermore, employed SHAP framework analyze individual features identify contributions terms prediction. According our findings, contributing can be summarized into four key focal outcomes. First, it was confirmed that soybean pricing overwhelmingly contributes predictions. Second, SSEC second-largest contributor predictions, surpassing S&P 500 or Third, contribution highest predicting Lastly, DXY significantly influences both price with a particularly notable summary, through framework, identified prices, SSEC, volatility, are primary contributors while 500, main These research findings provide valuable insights most-influential for laying foundation informed investment decisions robust risk-management strategies.

Язык: Английский

Процитировано

1

Wykorzystanie narzędzi geomatycznych w zarządzaniu infrastrukturą krytyczną DOI Open Access
Anna Bluszcz, Katarzyna Tobór–Osadnik, K. Tomiczek

и другие.

Inżynieria Mineralna, Год журнала: 2023, Номер 1(1)

Опубликована: Июль 16, 2023

Celem artykułu jest scharakteryzowanie zarządzania kryzysowego, w tym głównych etapów działania sztabów antykryzysowych. W artykule przedstawiono obszerne przykłady infrastruktury krytycznej oraz opracowano przykładowe mapy oprogramowaniu QGIS, które mogą być ważnymi narzędziami prowadzeniu działań służb kryzysowego. Przedstawiono oprogramowanie QGIS Free i OpenSource Geographic Information System do identyfikacji wybranych obiektów na podstawie dostępnych danych GIS Open z regionu Malezji Polski. analizie wybrane narzędzia geoprzetwarzania służące generowania obszarów o ustalonej odległości od zidentyfikowanych zwanych buforami. Warstwy buforowe to obszary widoczne generowanych mapach, posłużyć jako narzędzie wizualizacji potencjalnych dla Zidentyfikowanie tych stref buforowych umożliwia budowanie strategii wdrażania adekwatnych zapobiegawczych lub ratowniczych sytuacji zagrożenia. klasyfikację ryzyka poszczególnych strefach buforowych, która może optymalizacji podejmowanych przez służby Zademonstrowano szeroki zakres funkcjonalności systemów informacji przestrzennej geograficznej, który zwiększa efektywność optymalizację podejmowania decyzji zarządzaniu kryzysowym. Publikacja stanowić cenny przykład wykorzystania informatycznych

Процитировано

3