Article
Meteorology & Atmospheric Sciences
Jonathan A. Weyn, Dale R. Durran, Rich Caruana, Nathaniel Cresswell-Clay
Summary: The study presents an ensemble prediction system using a computationally efficient Deep Learning Weather Prediction (DLWP) model to recursively predict key atmospheric variables with good skill globally. The model performs well in simulating mid-latitude weather systems and generating tropical cyclones, showing decent predictive capabilities.
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2021)
Article
Engineering, Multidisciplinary
Merhan A. Abd-Elrazek, Ahmed A. Eltahawi, Mohamed H. Abd Elaziz, Mohamed N. Abd-Elwhab
Summary: According to the World Health Organization (WHO), patient Length of Stay (LOS) in hospitals is an important performance measurement and monitoring indicator. Prolonged LOS in the Intensive Care Unit (ICU) may lead to consuming hospital resources, manpower, and equipment. The proposed framework for predicting patient LOS in the ICU using different machine learning (ML) techniques demonstrates high prediction accuracy and applicability across all patients.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Article
Multidisciplinary Sciences
David Peter Kovacs, William McCorkindale, Alpha A. Lee
Summary: This study investigates automated reaction prediction using the Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a more realistic assessment of the model's performance.
NATURE COMMUNICATIONS
(2021)
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
Water Resources
Yongen Lin, Dagang Wang, Yue Meng, Wei Sun, Jianxiu Qiu, Wei Shangguan, Jingheng Cai, Yeonjoo Kim, Yongjiu Dai
Summary: This study investigates the incorporation of bias learning components into data driven models for streamflow prediction. Experiments are conducted in the Andun river basin of China and 273 watersheds in the United States to validate the effectiveness of the mapping-bias-learning models. The results show that these models outperform mapping-learning-alone models and machine learning methods are superior to traditional statistical methods in terms of bias learning ability.
JOURNAL OF HYDROLOGY-REGIONAL STUDIES
(2023)
Article
Meteorology & Atmospheric Sciences
Guangpeng Liu, Annalisa Bracco, Julien Brajard
Summary: This paper proposes a machine learning approach to improve the output of an ocean circulation model by learning and predicting its systematic biases. The method utilizes a sequence-to-sequence model to improve the representation of sea surface anomalies in model outputs using satellite altimeter data. The proposed method outperforms persistence in forecasting the systematic bias in the ocean circulation model and offers potential for further development of hybrid modeling tools.
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2023)
Article
Environmental Sciences
Fenghua Ling, Yue Li, Jing-Jia Luo, Xiaohui Zhong, Zhibin Wang
Summary: As most global climate models have large biases in simulating summer precipitation over China, it is crucial to develop suitable bias-correction methods. This study proposes two pathways of bias-correction with deep learning models incorporated, namely the deterministic pathway (DP) and the probability pathway (PP). The applications of deep learning models in both pathways improve the resolution of corrected predictions compared to the uncorrected ones and enhance summer precipitation predictions at a 4-month lead. The DP correction performs better in predicting extreme precipitation, while the PP is proficient in correcting the spatial pattern of precipitation anomalies over China.
ENVIRONMENTAL RESEARCH LETTERS
(2022)
Article
Environmental Sciences
Rangan Gupta, Christian Pierdzioch
Summary: This study contributes to the empirical literature by comparing the predictive role of aggregate and disaggregated metrics of policy-related and equity-market uncertainties, as well as geopolitical risks, for forecasting oil price volatility. Using machine-learning techniques, the study finds that adding disaggregated metrics improves the accuracy of forecasts, particularly at intermediate and long forecast horizons.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Civil
Ammara Talib, Ankur R. Desai, Jingyi Huang, Tim J. Griffis, David E. Reed, Jiquan Chen
Summary: Evapotranspiration prediction and forecasting are crucial for improving water use efficiency in agriculture, and the use of random forest models has shown better performance in estimating daily ET compared to LSTM models. Vapor pressure and crop coefficients are important predictors for irrigated crops, while short wave radiation and enhanced vegetation index are key predictors for non-irrigated crops.
JOURNAL OF HYDROLOGY
(2021)
Article
Economics
Oguzhan Cepni, Rangan Gupta, Daniel Pienaar, Christian Pierdzioch
Summary: This study investigates the impact of U.S. state-level economic-policy uncertainty measures on the prediction of oil-price return variance, and finds that incorporating these measures improves forecast accuracy, especially in the intermediate and long forecast horizon.
Article
Agronomy
Dilip Kumar Roy, Tapash Kumar Sarkar, Sheikh Shamshul Alam Kamar, Torsha Goswami, Md Abdul Muktadir, Hussein M. Al-Ghobari, Abed Alataway, Ahmed Z. Dewidar, Ahmed A. El-Shafei, Mohamed A. Mattar
Summary: This study utilized deep learning models (LSTM and Bi-LSTM) for daily and multi-step forward forecasting of ET0, with results showing that the Bi-LSTM model outperformed other models.
Article
Computer Science, Artificial Intelligence
Sun Chuanxia, Zhang Han, Yin Peixuan
Summary: This paper proposes a study on predicting traffic accidents based on IoTs and deep learning to address the problem of current inaccurate traffic accident predictions. Traditional traffic accident prediction methods often apply classical prediction algorithms to a small portion of data, resulting in models that can only predict a limited range of traffic accidents. Most accident prediction models lack data features, do not consider practical application scenarios, and do not incorporate regional heterogeneity, leading to poor prediction accuracy. This paper analyzes and summarizes the relationship between traffic accidents and influencing factors from five aspects, and proves the influence of regional heterogeneity on accidents, paving the way for traffic accident prediction. The data and heterogeneous spatial data are preprocessed and feature selected, respectively. Logistic regression and random forest algorithm are used to train the corresponding prediction models. The results show that the prediction model combined with regional heterogeneity has better comprehensive performance than the original data.
Article
Green & Sustainable Science & Technology
Mihaela T. Udristioiu, Youness EL Mghouchi, Hasan Yildizhan
Summary: This paper proposes a combination of hybrid models to predict and forecast the daily concentrations of particulate matter (PM) and Air Quality Index (AQI) using Input Variable Selection (IVS), Machine Learning (ML), and regression method. The performance of the proposed models is evaluated and validated using objective measures, and high precision and successful performance are observed. Furthermore, multivariable-based PM models are developed and adjusted, and a handled application for multistep-ahead time series forecasting is elaborated, achieving a high level of accuracy in predicting PM concentrations and AQI for future periods.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Automation & Control Systems
Carlos Fernandez-Loria, Foster Provost
Summary: The goal of causal classification is to identify individuals whose outcome would be positively changed by a treatment. This study explores the feasibility of using outcome prediction instead of treatment effect estimation for causal classification, and finds that in certain situations, outcome prediction may actually perform better. The theoretical analysis and simulations demonstrate when outcome prediction is preferable, such as when data on counterfactuals are limited or when there is correlation between outcomes and treatment effects.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Computer Science, Information Systems
Thomas Weripuo Gyeera, Anthony J. H. Simons, Mike Stannett
Summary: Cloud computing relies on the dynamic allocation and release of resources to meet computing needs. This article presents a proactive method for predicting resource exhaustion and cloud service failures using historical data. The framework achieved a prediction accuracy of 95.59% and can be used for optimizing resource provisioning and cloud SLA management.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Energy & Fuels
Mathieu David, John Boland, Luigi Cirocco, Philippe Lauret, Cyril Voyant
Summary: This study compares the economic value of different operational solar forecasts for a specific application, finding a linear relationship between error metrics and economic gains. An improvement of 1% point in mean absolute error (MAE) results in approximately a 2% increase in economic gain for a large-scale PV farm with Li-ion batteries in the Australian energy market context.
Article
Green & Sustainable Science & Technology
Kacem Gairaa, Cyril Voyant, Gilles Notton, Said Benkaciali, Mawloud Guermoui
Summary: This paper investigates the prediction of solar energy by using multiple linear regression and artificial neural network models. It compares the performance of different combinations of inputs on two sites in Algeria. The study shows that adding ordinal variables to endogenous data can improve the accuracy of the prediction and simplify the implementation.
Article
Green & Sustainable Science & Technology
Cyril Voyant, Gilles Notton, Jean-Laurent Duchaud, Luis Antonio Garcia Gutierrez, Jamie M. Bright, Dazhi Yang
Summary: With the increasing share of intermittent renewable energy, advanced solar power forecasting models are needed to optimize the operation of solar power plants. This study compares the performance of advanced models with naive reference methods and considers the benefits of ensemble forecasting. The combination method and ARTU method statistically offer the best results for the proposed study conditions.
Article
Energy & Fuels
Dazhi Yang, Wenting Wang, Jamie M. Bright, Cyril Voyant, Gilles Notton, Gang Zhang, Chao Lyu
Summary: Forecasting global horizontal irradiance up to 12 hours ahead is crucial for solar photovoltaics grid integration. In this study, the ECMWF's HRES model and two NOAA models, namely RAP and HRRR, are validated and compared. Results show that HRES forecasts outperform HRRR and RAP forecasts in terms of accuracy.
Article
Green & Sustainable Science & Technology
S. Ouedraogo, G. A. Faggianelli, G. Notton, J. L. Duchaud, C. Voyant
Summary: This study investigates the influence of electricity price profiles on energy exchange planning in microgrids and explores energy management strategies and their impact on microgrid operation improvement. The study finds that electricity price profiles affect energy flow distribution and financial gains, while also observing that the battery size and limitation of power exchange with the main grid have different effects depending on the implemented energy management strategy.
Article
Chemistry, Multidisciplinary
Luis Garcia-Gutierrez, Cyril Voyant, Gilles Notton, Javier Almorox
Summary: This study introduces an innovative clustering method for solar radiation stations, utilizing both static and dynamic parameters for easier solar resource forecasting. The research found that only using mean and two dynamic parameters is sufficient to characterize solar irradiation behavior at each site, and recommends using k-means or hierarchical clustering for solar radiation clustering.
APPLIED SCIENCES-BASEL
(2022)
Article
Energy & Fuels
Caio Felippe Abe, Ghjuvan-Antone Faggianelli, Joao Batista Dias, Gilles Notton
Summary: This study investigates different modeling approaches for photovoltaic modules and evaluates their performance in various scenarios. The results show that using field-measured data to adjust the model parameters improves the prediction of the maximum power point, leading to lower average error levels compared to using data sheet information.
JOURNAL OF ENERGY ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Cyril Voyant, Philippe Lauret, Gilles Notton, Jean-Laurent Duchaud, Luis Garcia-Gutierrez, Ghjuvan Antone Faggianelli
Summary: A new method for short-term probabilistic forecasting of global solar irradiance using complex-valued time series is explored. By using a complex autoregressive model, this approach generates deterministic and probabilistic forecasts that are in agreement with experimental data, sometimes exhibiting better accuracy than classical models.
JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY
(2022)
Article
Green & Sustainable Science & Technology
Jean-Laurent Duchaud, Ghjuvan-Antone Faggianelli, Cyril Voyant, Gilles Notton
Summary: Renewable energy micro-grids coupled with energy storage systems can be controlled using the Model Predictive Control (MPC) strategy. This paper focuses on how the time-step, horizon, and refresh period affect the optimal solution. Results show that using a time-step of 30 minutes and a 12-hour horizon yields good performances.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Energy & Fuels
Caio Felippe Abe, Joao Batista Dias, Gilles Notton, Ghjuvan-Antone Faggianelli, Guillaume Pigelet, David Ouvrard
Summary: Bifacial photovoltaic modules are able to convert solar radiation from both front and rear sides, increasing power output. This study presents a new method to calculate effective irradiance and bifacial gain, which was experimentally tested and proven to be accurate and reliable.
IEEE JOURNAL OF PHOTOVOLTAICS
(2023)
Article
Green & Sustainable Science & Technology
M. Genovese, F. Piraino, P. Fragiacomo
Summary: This research proposes the concept of a hydrogen valley in southern Italy, where hydrogen is produced centrally and delivered via fuel cell hybrid trains to refueling stations, providing transportation services. The analysis from both technical and economic perspectives shows that the cost of hydrogen and energy efficiency reached competitive levels, and hydrogen rail transport offers significant benefits in terms of emissions reduction and economic gains compared to conventional diesel trains and fully electric trains.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Miaomiao Liu, Payam Nejat, Pinlu Cao, Carlos Jimenez-Bescos, John Kaiser Calautit
Summary: This article provides a critical review of the performance of windcatchers, pointing out the current research gaps and issues, and proposing directions for further investigation and market prospects.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Solomon Boadu, Ebenezer Otoo
Summary: Despite Africa's vast energy resources, including wind energy, the continent faces challenges in developing its wind energy industry. Northern African countries and South Africa currently dominate the wind energy sector in Africa. To uplift Africa's socio-economic status, strong political will, supportive policies, and institutional frameworks are needed to drive the development of wind energy and overcome existing challenges.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
E. K. Grubbs, S. M. Gruss, V. Z. Schull, M. J. Gosney, M. V. Mickelbart, S. Brouder, M. W. Gitau, P. Bermel, M. R. Tuinstra, R. Agrawal
Summary: As the global population grows, the demand for food, energy, and water will increase significantly. However, limited land availability and competition for solar resources pose challenges to resource generation technologies. In the United States, both agriculture and solar energy production have adopted densification schemes to improve yields and energy output per unit of land. This research proposes an Agrivoltaic food and energy coproduction architecture that optimizes power generation while maintaining crop productivity by implementing ideal anti-tracking during critical growth periods. This technology offers a viable pathway for widespread solar implementation throughout the contiguous United States.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Han Shao, Rui Henriques, Hugo Morais, Elisabetta Tedeschi
Summary: The integration of offshore wind energy into the electric grid provides opportunities in terms of environmental sustainability and cost efficiency, but poses challenges to power quality. This survey offers a deeper understanding of disturbance detection and classification tools, exploring root causes, disturbance locations, and algorithmic solutions. It highlights synchronized waveform measurement and discusses evaluation metrics for detection and classification algorithms. Additionally, a novel system-wide monitoring framework is proposed.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Eleni Davidson, Yair Schwartz, Joe Williams, Dejan Mumovic
Summary: A continued upward trend in global greenhouse gas emissions poses risks to global infrastructure and built assets. Maintaining high indoor environmental quality standards is a challenge for higher education institutions under future climates. Passive cooling mechanisms may be insufficient to tolerate predicted temperature increases. Different building typologies have varying energy demand projections.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
Kexin Pang, Jian Zhou, Stamatis Tsianikas, David W. Coit, Yizhong Ma
Summary: This study proposes a new framework for long-term microgrid expansion planning, using deep reinforcement learning method to consider various uncertainties and constraints. The framework aims to enhance the effectiveness of microgrid expansion planning from the perspectives of economy, resilience, and greenhouse gas emission reduction.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
Jun Zhao, Kangyin Dong, Xiucheng Dong
Summary: The continuous growth of global electricity penetration has provided modern energy for alleviating energy poverty, but its impact on carbon neutrality has been overlooked. The research reveals that clean electricity from traditional fossil energy and renewable energy has a positive influence on the greenhouse effect. Eradicating energy poverty can effectively alleviate the greenhouse effect, especially in non-Belt and Road Initiative (B&RI) nations.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Hossein Shahbeik, Hamed Kazemi Shariat Panahi, Mona Dehhaghi, Gilles J. Guillemin, Alireza Fallahi, Homa Hosseinzadeh-Bandbafha, Hamid Amiri, Mohammad Rehan, Deepak Raikwar, Hannes Latine, Bruno Pandalone, Benyamin Khoshnevisan, Christian Sonne, Luigi Vaccaro, Abdul-Sattar Nizami, Vijai Kumar Gupta, Su Shiung Lam, Junting Pan, Rafael Luque, Bert Sels, Wanxi Peng, Meisam Tabatabaei, Mortaza Aghbashlo
Summary: This review explores the production of biocrude oil from biomass feedstocks through the process of hydrothermal liquefaction (HTL). It discusses the impact of process parameters on the quality, quantity, cost, and environmental impacts of biofuels. The review also highlights the challenges and prospects for the future development of biocrude oil.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
Meysam Majidi Nezhad, Mehdi Neshat, Georgios Sylaios, Davide Astiaso Garcia
Summary: Digital twins promise innovation for the marine renewable energy sector by using modern technological advances and the existing maritime knowledge frameworks. This research presents critical aspects of digital twin implementation challenges in marine energy digitalization approaches that use and combine data systems.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
Yeganeh Sharifian, Hamdi Abdi
Summary: This paper discusses the background and objectives of the multi-area economic dispatch problem, as well as various techniques and methods applied in this field. It also covers comprehensive formulations of the problem and important issues in the field of probabilistic MAED, along with some related concepts and suggestions.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
J. G. B. Churchill, V. B. Borugadda, A. K. Dalai
Summary: The increasing global energy demand and the need to reduce fossil fuel reliance have created a demand for renewable and sustainable fuel sources. This review explores the potential of tall oil, a by-product of the pulping industry, as a feedstock for biofuels. The review provides an overview of tall oil production, purification, and treatment, and investigates recent trends and barriers towards tall oil-derived biofuels.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
David C. Broadstock, Xiangnan Wang
Summary: This study provides a general review of research on district cooling, identifying key topics and themes and highlighting potential research priorities for future studies.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Article
Green & Sustainable Science & Technology
L. Scharnhorst, D. Sloot, N. Lehmann, A. Ardone, W. Fichtner
Summary: This study investigates and analyzes the barriers to demand response in industrial and commercial sectors, highlighting their significance. Concerns about diminished product quality, disruptions to production processes, human resource management, and revenue uncertainty are identified as the most frequently cited barriers. Overcoming these barriers requires bridging knowledge gaps, allocating sufficient resources, and adapting external incentives and policies.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)
Review
Green & Sustainable Science & Technology
Tong Feng, Yuechi Sun, Yating Shi, Jie Ma, Chunmei Feng, Zhenni Chen
Summary: Air pollution is a significant global challenge, and policymakers have implemented policies to reduce it. Evaluating the effectiveness of these policies is critical, and our study reveals trends and gaps in air pollution policy research. We found that research has shifted from focusing solely on air pollutants to including methodologies, policies, and health implications. China has emerged as a major contributor in this field of research.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2024)