Article
Meteorology & Atmospheric Sciences
R. Pahlavan, M. Moradi, S. Tajbakhsh, M. Azadi, M. Rahnama
Summary: This study successfully simulated fog events at six airports in Iran using a multi-physics ensemble prediction system. The advantages of probabilistic fog forecasting were shown by outperforming deterministic forecasts at 37.5% and 50% probability thresholds, with EPS correctly predicting more fog events compared to the reference forecast.
METEOROLOGICAL APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Rebecca Salles, Esther Pacitti, Eduardo Bezerra, Fabio Porto, Eduardo Ogasawara
Summary: TSPred is a framework for nonstationary time series prediction that seamlessly integrates nonstationary time series transformations with state-of-the-art statistical and machine learning methods. It provides rich functionality for defining and conducting time series prediction, and supports user-defined methods, significantly expanding its applicability.
Article
Computer Science, Artificial Intelligence
Felipe Tomazelli Lima, Vinicius M. A. Souza
Summary: Normalization is a crucial preprocessing step in time series problems to ensure similarity comparisons invariant to distortions. This study evaluates different normalization methods on classification tasks and suggests the use of maximum absolute scale as an alternative to z-normalization, showing promising results for similarity-based methods.
Article
Physics, Multidisciplinary
Faruk Serin, Yigit Alisan, Adnan Kece
Summary: Providing accurate travel time information is crucial in public transportation. A novel three-layer architecture method is proposed to predict bus travel time between two stops, outperforming traditional approaches with an approximate MAPE of 6 in experiments using Istanbul's public transportation data.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Haoyi Zhou, Jianxin Li, Shanghang Zhang, Shuai Zhang, Mengyi Yan, Hui Xiong
Summary: This study proposes an efficient model for long sequence time-series forecasting called Informer, which addresses the limitations of the traditional Transformer in terms of complexity, memory usage, and inference speed. Informer improves the prediction capacity by introducing the ProbSparse self-attention mechanism, attention distilling with convolutional operators, and a generative style decoder. Extensive experiments on large-scale datasets demonstrate that Informer outperforms existing methods and provides a new solution to the long sequence time-series forecasting problem.
ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jiabao Wen, Jiachen Yang, Bin Jiang, Houbing Song, Huihui Wang
Summary: This article proposes a new method using a semi-supervised prediction model and neural network model to solve the time analysis problem of massive industry data, and experimentally verifies its satisfactory predictive effect.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Seyed Ehsan Fatemi, Hosna Parvini
Summary: This study focuses on the critical issues of time series modeling and control of hydrological parameters in water resources management. By analyzing the correlogram of the time series, the significant relationship between natural properties and the best combination set of inputs for the fuzzy-neural adaptive network model is identified.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Raquel Espinosa, Jose Palma, Fernando Jimenez, Joanna Kaminska, Guido Sciavicco, Estrella Lucena-Sanchez
Summary: This study explores the design and testing of environmental pollution models, focusing on forecasting performance. By analyzing data from three years, deep learning and regression models are used to reliably predict pollutant concentrations in the air 24 hours in advance, allowing for interventions to mitigate effects on the population.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Jie Zhou, Ding Ding, Ziteng Wu, Yuting Xiu
Summary: A spatial context-aware time series forecasting (SCATSF) framework is proposed in this paper for QoS prediction by considering both the temporal and spatial context of users and services. Experimental results show that the SCATSF approach can effectively utilize spatio-temporal contextual information and achieve higher accuracy than many existing methods.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2023)
Article
Geochemistry & Geophysics
P. Hill, J. Biggs, V. Ponce-Lopez, D. Bull
Summary: The study compared different time series forecasting methods for seasonal signal prediction and found that SARIMA and sinusoid extrapolation performed better in different time windows, while machine learning methods (LSTM) showed less satisfactory results. Additionally, simple extrapolation of a constant function outperformed more sophisticated time series prediction methods in most cases.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2021)
Article
Energy & Fuels
Ibtissam Amalou, Naoual Mouhni, Abdelmounaim Abdali
Summary: Smart grids are a new technology that improves the efficiency and reliability of traditional electric networks for energy management based on demand optimization. The study compares different deep learning models and finds that the GRU model outperforms others in predicting energy demand.
Article
Energy & Fuels
Pawel Pelka
Summary: This article presents a statistical solution (ARIMA, ETS, and Prophet) for predicting monthly power demand, which estimates the relationship between historical and future demand patterns. The time series of energy demand exhibits seasonal fluctuations, long-term trends, instability, and random noise. To simplify the prediction issue, the monthly load time series is represented by an annual cycle pattern, which standardizes the data and filters out the trends. A simulation study conducted on the monthly electricity load time series for 35 European countries confirmed the high accuracy of the proposed models.
Article
Computer Science, Artificial Intelligence
Mehrnaz Ahmadi, Mehdi Khashei
Summary: Support vector machines (SVMs) are widely used in modeling, but traditional SVMs and fuzzy SVMs may not be sufficient for modeling both certain and uncertain patterns simultaneously. This paper proposes a generalized SVM that can effectively model both kinds of patterns to achieve more accurate wind speed forecasting results.
Article
Computer Science, Artificial Intelligence
Jinseong Park, Hoki Kim, Yujin Choi, Woojin Lee, Jaewook Lee
Summary: In this study, a new fast sharpness-aware training method called Periodic Sharpness-Aware Time series Training (PSATT) is proposed, which leverages the periodic characteristics of time series data and reuses gradient information from past iterations. This method improves both the generalization performance and time efficiency in time series classification and forecasting.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yuerong Tong, Jingyi Liu, Lina Yu, Liping Zhang, Linjun Sun, Weijun Li, Xin Ning, Jian Xu, Hong Qin, Qiang Cai
Summary: Time series analysis is an essential means of discovering knowledge hidden in time series data. This study focuses on analyzing the technical development routes of time series classification and prediction algorithms. The findings provide a comprehensive reference base for researchers interested in this field.
PEERJ COMPUTER SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Javier Barbero-Gomez, Pedro Antonio Gutierrez, Cesar Hervas-Martinez
Summary: This study presents a new CNN architecture based on OBD and ECOC for ordinal classification tasks. Experimental results show that this method significantly improves performance on ordinal and class-balancing metrics.
NEURAL PROCESSING LETTERS
(2023)
Article
Green & Sustainable Science & Technology
Ravinesh C. Deo, A. A. Masrur Ahmed, David Casillas-Perez, S. Ali Pourmousavi, Gary Segal, Yanshan Yu, Sancho Salcedo-Sanz
Summary: Prediction of Total Cloud Cover (TCDC) from numerical weather simulation models can aid renewable energy engineers in monitoring and forecasting solar photovoltaic power generation. A major challenge is the systematic bias in TCDC simulations induced by errors in the numerical model parameterization stages. Correction of GFS-derived cloud forecasts at multiple time steps can improve energy forecasts in electricity grids to bring better grid stability or certainty in the supply of solar energy.
Article
Computer Science, Artificial Intelligence
Sujan Ghimire, Thong Nguyen-Huy, Ramendra Prasad, Ravinesh C. Deo, David Casillas-Perez, Sancho Salcedo-Sanz, Binayak Bhandari
Summary: This study proposes a hybrid method that combines convolutional neural network (CNN) with multi-layer perceptron (MLP) to generate solar radiation forecasts. The proposed CMLP model shows excellent performance in predicting solar radiation at various study sites. It should be explored as a viable modelling tool for real-time energy management systems.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Information Systems
Sagthitharan Karalasingham, Ravinesh C. Deo, David Casillas-Perez, Nawin Raj, Sancho Salcedo-Sanz
Summary: This paper proposes a new image super-resolution deep learning model based on convolutional neural network to generate high resolution spatial representations of surface albedo from coarse resolution remote sensing-based data. The proposed model outperforms alternative deep learning, super-resolution approaches in terms of mean square error, signal-to-noise ratio, and structural similarity index.
Article
Computer Science, Artificial Intelligence
Victor Manuel Vargas, Pedro Antonio Gutierrez, Riccardo Rosati, Luca Romeo, Emanuele Frontoni, Cesar Hervas-Martinez
Summary: Ordinal problems involve predicting labels from a group of naturally ordered categories. They are common in various fields such as medical diagnosis and quality control. This study presents a new exponential regularized loss function to improve the classification performance for ordinal problems using deep neural networks.
APPLIED SOFT COMPUTING
(2023)
Review
Geochemistry & Geophysics
D. Barriopedro, R. Garcia-Herrera, C. Ordonez, D. G. Miralles, S. Salcedo-Sanz
Summary: Heat waves have significant socioeconomic and environmental impacts, and their frequency, intensity, and duration are projected to increase with global warming. While some thermodynamic processes have been identified, there is still a lack of understanding regarding dynamical aspects, regional forcings, and feedbacks, as well as their future changes.
REVIEWS OF GEOPHYSICS
(2023)
Article
Computer Science, Artificial Intelligence
C. G. Marcelino, J. Perez-Aracil, E. F. Wanner, S. Jimenez-Fernandez, G. M. C. Leite, S. Salcedo-Sanz
Summary: In this paper, a new hybrid optimization algorithm CE+CRO-SL is proposed to solve the optimal power flow problem. It outperforms traditional methods in terms of efficiency and accuracy, and achieves millions of dollars in profit in the tested scenarios.
Article
Computer Science, Artificial Intelligence
Victor Manuel Vargas, Pedro Antonio Gutierrez, Javier Barbero-Gomez, Cesar Hervas-Martinez
Summary: Activation functions play a critical role in neural network models, affecting the output range and capabilities of each layer. This study proposes two new activation functions and compares them with 17 different function proposals, finding that the proposed functions outperform commonly used ones.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Mathematics
Jorge Perez-Aracil, Carlos Camacho-Gomez, Eugenio Lorente-Ramos, Cosmin M. Marina, Laura M. Cornejo-Bueno, Sancho Salcedo-Sanz
Summary: This paper proposes new probabilistic and dynamic strategies for creating multi-method ensembles based on the CRO-SL algorithm. Two different probabilistic strategies are analyzed to improve the algorithm. The performances of the proposed ensembles are tested for different optimization problems, comparing the results with existing algorithms in the literature.
Article
Computer Science, Artificial Intelligence
Miguel Diaz-Lozano, David Guijo-Rubio, Pedro Antonio Gutierrez, Cesar Hervas-Martinez
Summary: The COVID-19 pandemic has caused a global health and economic crisis, leading to the development of various research lines to support countries' responses. This work contributes to the existing literature by developing a two-step methodology to analyze the transmission rate and design models applicable to territories with similar pandemic behavior characteristics.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
L. Cornejo-Bueno, J. Perez-Aracil, C. Casanova-Mateo, J. Sanz-Justo, S. Salcedo-Sanz
Summary: This study proposes a methodology based on classification and regression techniques to predict the occurrence and quantity of desert locusts. Different machine learning algorithms, such as linear regression, Support Vector Machines, decision trees, random forests, and neural networks, were applied and evaluated in Western Africa, primarily Mauritania. The results show that the random forest algorithm performs exceptionally well in both classification and regression tasks, making it the most effective machine learning algorithm among those used.
APPLIED SCIENCES-BASEL
(2023)
Article
Acoustics
Alberto Palomo-Alonso, David Casillas-Perez, Silvia Jimenez-Fernandez, Jose A. Portilla-Figueras, Sancho Salcedo-Sanz
Summary: This article proposes a flexible architecture with different algorithms for effective story segmentation of broadcast news from subtitle files. The proposed system uses spatial and temporal distance, as well as sentence similarity, to classify different stories in news broadcasts. The computational algorithms focus on each sentence's features and are combined to build an overall classifier. The proposed approach is evaluated using Video Text Track (VTT) subtitle files, and the algorithms are designed to handle noisy content.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2023)
Review
Computer Science, Artificial Intelligence
Iztok Fister Jr, Iztok Fister, Dusan Fister, Vili Podgorelec, Sancho Salcedo-Sanz
Summary: Association rule mining aims to search for relationships between attributes in transaction databases. The process involves pre-processing techniques, rule mining, and post-processing with visualization. This review paper provides a literature review and analysis of techniques, applications, and future research directions in association rule mining and visualization.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Antonio M. Duran-Rosal, David Guijo-Rubio, Victor M. Vargas, Antonio M. Gomez-Orellana, Pedro A. Gutierrez, Juan C. Fernandez
Summary: Machine learning is the science of enabling computers to learn from data without being explicitly programmed to do so, combining knowledge from artificial intelligence, statistics and mathematics. It falls under the umbrella of Data Science and is usually developed by Computer Engineers becoming what is known as Data Scientists.
INTERNATIONAL JOINT CONFERENCE 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS (CISIS 2022) 13TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATION (ICEUTE 2022)
(2023)
Article
Meteorology & Atmospheric Sciences
Vittal Hari, Oldrich Rakovec, Wei Zhang, Akash Koppa, Matthew Collins, Rohini Kumar
Summary: This study reveals a significant association between the Atlantic Meridional Mode (AMM) and temperature variability in the eastern European region. Positive AMM phase leads to a significant increase in temperature, while negative phase has the opposite effect. The AMM modulates the temperature through planetary-scale Rossby waves and anomalous anticyclone circulation.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Fang Cao, Yi-Xuan Zhang, Yan-Lin Zhang, Wen-Huai Song, Yu-Xian Zhang, Yu-Chi Lin, Chaman Gul, Md. Mozammel Haque
Summary: This study investigates the influences of continental emissions on marine aerosols in the Yellow Sea and Bohai Sea of China. The results show that biomass burning is the major contributor to organic aerosols in these marine atmospheres.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Chenxi Liao, Wenhua Gao, Lanzhi Tang, Chengyin Li
Summary: Based on ERA5 data, this study analyzed the characteristics of four hydrometeors and their relationship with precipitation intensity in central eastern China and the northwest Pacific Ocean. The results show that stratiform precipitation is dominated by ice processes, while convective precipitation has comparable contributions from water and ice processes.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Hsiang-Yu Huang, Sheng-Hsiang Wang, William K. M. Lau, Shih-Yu Simon Wang, Arlindo M. da Silva
Summary: This study presents a diagnostic analysis of the interannual variation of regional climate and its impact on biomass burning aerosol emissions in peninsular Southeast Asia (PSEA). It identifies four climatic factors governing the emission and transport of PSEA biomass burning aerosols and reveals a significant correlation with the El Nin similar to o-Southern Oscillation (ENSO). The results contribute to a better understanding and improved model simulations of aerosol-climate interactions in South and Southeast Asian monsoon regions.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Deniz H. Diren-Ustuen, Yurdanur S. Unal, Simge Irem Bilgen, Cemre Yuruk Sonuc, Sahar Sodoudi, Caner Guney, Ahmet Ozgur Dogru, Selahattin Incecik
Summary: This is the first comprehensive study to examine how urbanization affects the microclimate of Istanbul using the urban climate model MUKLIMO_3. The findings suggest that changing the albedo of roofs and implementing green-roofs can significantly reduce air temperatures in urban areas.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Yetong Li, Yan Xia, Fei Xie, Yingying Yan
Summary: Surface ozone, a major air pollutant, is influenced by stratosphere-troposphere exchange (STE) which contributes to both the decrease and increase of surface ozone in the Southern and Northern Hemispheres, respectively. Additionally, global warming is expected to worsen surface ozone pollution in the future.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Na Li, Ping Zhao, Changyan Zhou
Summary: In this study, the daily sensible and latent heat fluxes in the Tibetan Plateau are estimated using the maximum entropy production model. The results show good performance of the model and reveal the spatial distribution and trends of surface heat fluxes in the region.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Wenqing Lin, Huopo Chen, Weiqi Wang, Dawei Zhang, Fan Wang, Wuxia Bi
Summary: It is found in this study that anthropogenic activities may significantly contribute to the decrease in snowfall days, light snowfall, and light snowfall days across Eurasia, with greenhouse gas emissions being the main driver. However, detection of human influence is challenging for intense snowfall.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Chongxun Mo, Xingbi Lei, Xixi Mo, Ruli Ruan, Gang Tang, Lingguang Li, Guikai Sun, Changhao Jiang
Summary: Reliable precipitation information is crucial for scientific and operational applications. Open-access gridded precipitation products (OGPPs) are important sources due to their continuous spatiotemporal coverage. This study proposes a methodology to comprehensively compare the accuracies and stabilities of ten different OGPPs, particularly in mountainous basins. The results show high accuracy but unstable performance of all OGPPs, with multi-source fusion-type products offering better stability and accuracy. Multi-source weighted-ensemble precipitation and climate prediction center morphing method products exhibit the best comprehensive performance.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Jingzhuo Wang, Hanbin Zhang, Jing Chen, Guo Deng, Yu Xia
Summary: In this study, a new scale-blending technique was proposed to evaluate the impact of multiscale initial perturbations on the CMA-CPEPS. The results showed that the blended scheme improved the dispersion of dynamical variables and increased the ensemble spread of precipitation, leading to reduced forecast error.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Ziyi Song, Botao Zhou, Xinping Xu, Zhicong Yin
Summary: This study, based on reanalysis data from 1980 to 2019, reveals that the relationship between autumn sea ice concentration in the Barents-Kara Seas (BKSIC) and subsequent winter North Atlantic Oscillation (NAO) underwent an interdecadal weakening in the early 1990s. The weakening can be attributed to the decrease in the interannual variability of BKSIC, which leads to a discrepancy in the tropospheric warming. In the former period (1980-1993), the decrease in autumn BKSIC enhances tropospheric warming and weakens the circumpolar westerly, resulting in a negative NAO phase. However, in the latter period (1994-2019), the smaller interannual variability of BKSIC weakens its influence on the tropospheric temperature, diluting the relationship with the subsequent winter NAO.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Wogu Zhong, Zhiwei Wu
Summary: Significant phase shifts in winter surface air temperature (SAT) anomalies have occurred in East Asia in recent years, leading to detrimental effects on socio-economic activities. In this study, the fourth principal mode of month-to-month SAT variations over EA in winter was identified, representing subseasonal SAT reversals over the mid-high latitudes of EA during late winter. The formation of this mode is accompanied by stratospheric temperature anomalies over eastern Siberia-Alaska in January.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Weiqian Ji, Leiku Yang, Xinyao Tian, Muhammad Bilal, Xin Pei, Yu Zheng, Xiaofeng Lu, Xiaoqian Cheng
Summary: This study systematically evaluated the AOD products of the DB and MAIAC algorithms based on MODIS over bright surfaces, and investigated the underestimation of AOD affected by various factors. The results indicated that the MAIAC products performed better than DB, and the C6.1 MAIAC showed slight improvement compared to C6.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Tao Wang, Xiaohua Gou, Xuejia Wang, Hongwen Liu, Fei Xie
Summary: This study finds that the meridional position of subtropical jet anomalies has shifted equatorward in both the Northern Hemisphere and Southern Hemisphere since the 1960s due to the influence of ENSO. The changes in tropical SST anomalies associated with ENSO contribute to this equatorward shift.
ATMOSPHERIC RESEARCH
(2024)
Article
Meteorology & Atmospheric Sciences
Alireza Ghaderi Bafti, Arman Ahmadi, Ali Abbasi, Hamid Kamangir, Sadegh Jamali, Hossein Hashemi
Summary: Actual evapotranspiration (ETa) plays a crucial role in the water and energy cycles of the earth. This study develops an automated deep learning model for accurate estimation of ETa using image processing, architectural design, and hyper-parameter tuning. The proposed model shows promising results in different climatic regions, highlighting its potential for enhanced atmospheric research.
ATMOSPHERIC RESEARCH
(2024)