Article
Energy & Fuels
T. Gonzalez Grandon, J. Schwenzer, T. Steens, J. Breuing
Summary: This article presents a novel hybrid approach using classic statistics and machine learning to forecast the national demand of electricity. The proposed methodology combines multiple regression models and a LSTM hybrid model to accurately predict long-term electricity consumption.
Article
Physics, Fluids & Plasmas
Johanna Vielhaben, Nils Strodthoft
Summary: This paper explores the ability of generative neural samplers to estimate observables for real-world low-dimensional spin systems, and the results show good agreement with Monte Carlo results in certain cases.
Article
Computer Science, Artificial Intelligence
Hao Wang, Tao Liu, Zhongyang Yu
Summary: This study aims to enhance the application efficiency of modern science and technology in farm operation, predict farm supply and demand using machine learning and blockchain technology, and contribute to the integrated management and sustainable development of enterprises.
Article
Chemistry, Multidisciplinary
Santanu Kumar Dash, Michele Roccotelli, Rasmi Ranjan Khansama, Maria Pia Fanti, Agostino Marcello Mangini
Summary: This paper examines the forecasting of consumer electricity demand through the RNN-GBRT technique, which helps reduce electricity demand and ensure accurate evaluation. The efficiency of the proposed model is compared with various conventional models, while monitoring power consumption data on the distribution line to prevent financial losses and detecting abnormal changes.
APPLIED SCIENCES-BASEL
(2021)
Article
Green & Sustainable Science & Technology
Celina Dittmer, Johannes Kruempel, Andreas Lemmer
Summary: In the future energy system, it is increasingly important for biogas plants to produce electricity to compensate for fluctuating sources of wind power and photovoltaics. Flexibility concepts provide coordinated feeding management and suitable forecast models for power demand to adjust biogas production and generate future schedules.
Article
Physics, Multidisciplinary
Aaram J. Kim, Katharina Lenk, Jiajun Li, Philipp Werner, Martin Eckstein
Summary: We propose a diagrammatic Monte Carlo approach for quantum impurity models, which is a generalization of the strong-coupling expansion for fermionic impurity models. The algorithm is based on a self-consistently computed three-point vertex and a stochastically sampled four-point vertex and provides numerically exact results in a wide parameter regime. The performance of the algorithm is demonstrated with applications to a spin-boson model representing an emitter in a waveguide. The spatial distribution of the photon density around the emitter is also discussed.
PHYSICAL REVIEW LETTERS
(2023)
Article
Environmental Sciences
Shahab Safaei, Peiman Ghasemi, Fariba Goodarzian, Mohsen Momenitabar
Summary: This study proposes a new multi-echelon multi-period model for designing closed-loop supply chain networks, aiming to optimize the networks by minimizing total costs. The model considers multiple levels, including suppliers, manufacturers, distribution centers, customers, and recycling units. The study also applies an ARIMA model to estimate product demand and improve service levels in the supply chain network.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Nuzhat Fatema, Hasmat Malik, Mutia Sobihah Abd Halim
Summary: This study proposed a hybrid intelligent approach based on empirical mode decomposition, autoregressive integrated moving average, and Monte Carlo simulation methods for multi-step ahead medical tourism forecasting. The results show that the proposed approach can accurately predict the arrival of medical tourism.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Mona A. Alduailij, Ioan Petri, Omer Rana, Mai A. Alduailij, Abdulrahman S. Aldawood
Summary: Predicting energy consumption in buildings is crucial for digital transformation and energy savings, utilizing IoT devices for monitoring and control. Statistical, time series, and machine learning techniques are proposed to achieve energy efficiency in predicting electricity consumption for different building types.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Energy & Fuels
Mohanad S. AL-Musaylh, Kadhem Al-Daffaie, Ramendra Prasad
Summary: The study developed a novel technique to predict gas consumption demand patterns in Melbourne, Australia, by effectively decomposing and forecasting historical data. Evaluation comparison showed significant improvements in EWT models compared to traditional methods. This modeling approach has the potential utility in assisting energy usage monitoring and decision-making in national energy markets.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Andreas Kanavos, Fotios Kounelis, Lazaros Iliadis, Christos Makris
Summary: This paper focuses on the analysis and modeling of passenger demand dynamics in the aviation industry, proposing a method using time series and deep learning techniques to forecast aviation demand, and developing related models. The results of the study show that the proposed methods exhibit satisfactory accuracy and robustness in predicting air travel demand.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Astronomy & Astrophysics
Francesca Cuteri, Owe Philipsen, Alena Schoen, Alessandro Sciarra
Summary: The addition of heavy dynamical quarks weakens the first-order thermal deconfinement transition in SU(3) pure gauge theory until it disappears. The critical hopping parameter and associated pion mass for lattice QCD have been calculated, with significant cutoff effects observed. The results allow for an assessment of the accuracy of the fermion determinant used in literature.
Article
Environmental Sciences
Anwar Hussain, Junaid Alam Memon, Muntasir Murshed, Md Shabbir Alam, Usman Mehmood, Mohammad Noor Alam, Muhammad Rahman, Umar Hayat
Summary: This study forecasts the natural gas demand in Pakistan for the period of 2016-2030 using time series econometric methods. It finds that compressed natural gas consumption in the household sector will see the highest growth, and recommends increasing gas availability and strategizing the development of the compressed natural gas sector.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Ecology
Carlos Antonio Zarzar, Tales Jesus Fernandes, Izabela Regina Cardoso de Oliveira
Summary: This study focused on modeling the growth of Pacific white shrimp in an industrial-scale shrimp farm in northeastern Brazil. Six nonlinear hierarchical growth models were evaluated and fitted to real data, with the Weibull growth equation showing the best performance in predicting shrimp growth. The proposed method detected subtle differences between production cycles and provided a new approach for improving products, processes, and decision-making in aquaculture management.
ECOLOGICAL INFORMATICS
(2023)
Article
Multidisciplinary Sciences
Anh Duy Nguyen, Phi Le Nguyen, Viet Hung Vu, Quoc Viet Pham, Viet Huy Nguyen, Minh Hieu Nguyen, Thanh Hung Nguyen, Kien Nguyen
Summary: This paper proposes a novel deep learning-based Q-H prediction model that overcomes the issues of data scarcity, noise, and hyperparameter adjustment. Through the use of ensemble learning, singular-spectrum analysis, and genetic algorithm, significant improvements in prediction accuracy are achieved, with the ability to improve the NSE metric by at least 2%.
SCIENTIFIC REPORTS
(2022)
Article
Green & Sustainable Science & Technology
Qingmei Wen, Gang Liu, Wei Wu, Shengming Liao
Summary: The study aims to propose a multi-criteria comprehensive evaluation framework for distributed energy system planning, by establishing evaluation criteria system and determining subjective weights, objective weights, and comprehensive weights using fuzzy analytic hierarchy process method, Shannon entropy method, and a comprehensive method. The study combines various methods to improve decision making in evaluating distributed energy systems.
JOURNAL OF CLEANER PRODUCTION
(2021)