Article
Environmental Sciences
Narjes Salmani-Dehaghi, Nozar Samani
Summary: This study highlights the importance of satellite data in filling gaps in precipitation time series and estimating precipitation at ungauged sites, while proposing effective bias correction models to improve the accuracy of the PERSIANN-CDR algorithm. These models have a wide range of applications in estimating precipitation and filling gaps in ground-based precipitation data.
ATMOSPHERIC ENVIRONMENT
(2021)
Review
Environmental Sciences
Thi Lan Anh Dinh, Filipe Aires
Summary: Climate models are widely used in studying climate change impacts, but their direct use is often limited due to inherent limitations. Bias correction methods have been proposed to improve the simulations. This study presents an up-to-date review of these methods, comparing six representative quantile-based approaches for temperature and precipitation data in Europe. New diagnostic tools are recommended to measure the impact of the adjustment on the model's ability to reproduce observations and capture climate change signals.
Article
Meteorology & Atmospheric Sciences
Xinyi Li, Zhong Li
Summary: This study evaluated the performance of two bias correction methods, QDM and SDM, for generating high-resolution daily Tmax and Tmin projections for Canada using the latest GCMs. The results showed that QDM performed better in relative to observations while SDM preserved the raw climate signals. Both methods effectively reduced the biases of Tmax and Tmin for all GCMs.
Article
Computer Science, Information Systems
Federico Gatta, Fabio Giampaolo, Edoardo Prezioso, Gang Mei, Salvatore Cuomo, Francesco Piccialli
Summary: Time series is a widely-used methodology to describe phenomena in various fields. Neural network generative approaches, which aim to generate new samples based on real data by learning the underlying probability distribution, are gaining more relevance in the data analysis community. This paper contributes to the debate by comparing four neural network-based generative approaches for time series, evaluating their performances under different experimental conditions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Astronomy & Astrophysics
Rohit Jaiswal, R. K. Mall, Nidhi Singh, T. V. Lakshmi Kumar, Dev Niyogi
Summary: Regional climate models (RCMs) are commonly used for regional climate assessments, but they often overpredict light rainfall events. This study employed three bias-correction methods to improve the accuracy of monsoon rainfall simulations in India. The corrected rainfall data were compared to observations, and the performance of the methods was evaluated using various metrics. The results showed that the SCL method was the most effective, followed by EQM, while LOCI was less effective. Spatial analysis revealed notable improvements in the Western Himalayan Region. The findings provide region-specific techniques for bias correction in impact assessment studies in the Indian monsoon region.
EARTH AND SPACE SCIENCE
(2022)
Article
Astronomy & Astrophysics
Hans van de Vyver, Bert Van Schaeybroeck, Lesley De Cruz, Rafiq Hamdi, Piet Termonia
Summary: This study proposes a bias-adjustment method for extreme precipitation intensity using intensity-duration-frequency (IDF) modeling to preserve the scaling equation for different accumulation levels. A validation is conducted using hourly precipitation data from 28 regional climate model projections of the EURO-CORDEX ensemble over Belgium. The scaling-based adjustment methods improve upon previous methods, identify an optimal method, and reveal problems with analytical quantile mapping methods. The ensemble mean of the adjusted extreme precipitation intensity follows the scale-invariance property and is consistent with observed extreme intensities, demonstrating the added value of IDF modeling in bias-adjustment.
EARTH AND SPACE SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Wonkeun Jo, Dongil Kim
Summary: Deep neural networks are important in machine learning for their excellent prediction performance and versatility. However, they lack explanatory power due to being black-box models. This study proposes a new neural network architecture that includes interpretability for multivariate time-series data. Experimental results show that the interpretable neural architecture performs well in predicting MTS data and provides reasonable importance for each input value.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Kexin Zhang, Yong Liu, Yong Gu, Jiadong Wang, Xiaojun Ruan
Summary: This paper proposes a feature learning approach for industrial time-series data based on self-supervised contrastive learning to address the challenge of the lack of labeled data in using neural networks to build a reliable fault detection model. The approach consists of two components: data transformation and representation learning. The data transformation converts the raw time-series into temporal distance matrices with temporal and spatial information. The representation learning component uses a convolution-based encoder to encode the temporal distance matrices into embedding representations.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Meteorology & Atmospheric Sciences
Fang Wang, Di Tian
Summary: This study comprehensively evaluates the Super Resolution Deep Residual Network (SRDRN) deep learning model for climate downscaling and bias correction. The SRDRN model effectively removes biases based on the relative relations among different GCMs and retains the intervariable dependences for multivariate bias correction. The results show that the SRDRN model outperforms other methods in reducing biases and reproducing the intervariable dependences of the observations.
Article
Energy & Fuels
Adriaan P. Hilbers, David J. Brayshaw, Axel Gandy
Summary: The growth of variable renewables like solar and wind increases the impact of climate uncertainty in energy system planning. However, solving capacity expansion planning models with high-resolution time series is computationally expensive. To reduce costs, time series aggregation is often used, but it has limitations and may not accurately model outputs. In this paper, the authors introduce a posteriori time series aggregation schemes that preserve chronology and allow modelling of storage technologies. They find that these methods can perform better than a priori ones by identifying and preserving extreme events.
Article
Computer Science, Artificial Intelligence
Rakshitha Godahewa, Kasun Bandara, Geoffrey Webb, Slawek Smyl, Christoph Bergmeir
Summary: Ensembling techniques are used to improve the performance of Global Forecasting Models (GFM) and univariate models in heterogeneous datasets. A new clustered ensembles methodology is proposed to train multiple GFMs on different clusters of series, achieving higher accuracy than baseline models.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Statistics & Probability
Sumanta Basu, Suhasini Subba Rao
Summary: We propose NonStGM, a framework for studying dynamic associations among the components of a nonstationary multivariate time series. It captures conditional noncorrelations and nonstationarity/stationarity using graphical models and recovers sparsity patterns from finite-length time series using discrete Fourier transforms.
ANNALS OF STATISTICS
(2023)
Article
Engineering, Civil
Kue Bum Kim, Hyun-Han Kwon, Dawei Han
Summary: The study proposed an integrated framework combining bias correction of regional climate model precipitation and simulated flow from rainfall-runoff model, considering the uncertainty in distribution function parameters. Four different bias correction approaches were explored to reduce systematic biases in flow simulated by hydrological models using RCM precipitation as input. The Case-4 model, which corrects RCM precipitation and flow by preserving their natural variabilities, showed the best performance in terms of bias correction and spread of flow ensemble from a hydrological perspective.
JOURNAL OF HYDROLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Deniz Kenan Kilic, Omur Ugur
Summary: Wavelet analysis is utilized to separate S & P500 and NASDAQ data into components and model each component using an appropriate neural network structure. Additionally, wavelets are used as an activation function in long short-term memory networks to create a hybrid model. The results demonstrate that employing multiresolution analysis and wavelets as an activation function can significantly reduce the error.
APPLIED SOFT COMPUTING
(2023)
Article
Plant Sciences
Oybek Eraliev, Chul-Hee Lee
Summary: Indoor hydroponic greenhouses are gaining popularity for sustainable food production, but precise control of climate conditions is crucial. This study evaluated three deep learning models for climate prediction in an indoor hydroponic greenhouse. Results showed all models performed well in predicting temperature, humidity, and CO2 concentration, with the LSTM model outperforming others at shorter time intervals. The study highlights the importance of choosing the appropriate time interval for accurate predictions and contributes to sustainable food production.
Article
Computer Science, Interdisciplinary Applications
Balazs Grosz, Rene Dechow, Soeren Gebbert, Holger Hoffmann, Gang Zhao, Julie Constantin, Helene Raynal, Daniel Wallach, Elsa Coucheney, Elisabet Lewan, Henrik Eckersten, Xenia Specka, Kurt-Christian Kersebaum, Claas Nendel, Matthias Kuhnert, Jagadeesh Yeluripati, Edwin Haas, Edmar Teixeira, Marco Bindi, Giacomo Trombi, Marco Moriondo, Luca Doro, Pier Paolo Roggero, Zhigan Zhao, Enli Wang, Fulu Tao, Reimund Roetter, Belay Kassie, Davide Cammarano, Senthold Asseng, Lutz Weihermueller, Stefan Siebert, Thomas Gaiser, Frank Ewert
ENVIRONMENTAL MODELLING & SOFTWARE
(2017)
Article
Agronomy
Xiaogang Yin, Kurt Christian Kersebaum, Chris Kollas, Sanmohan Baby, Nicolas Beaudoin, Kiril Manevski, Taru Palosuo, Claas Nendel, Lianhai Wu, Munir Hoffmann, Holger Hoffmann, Behzad Sharif, Cecilia M. Armas-Herrera, Marco Bindi, Monia Charfeddine, Tobias Conradt, Julie Constantin, Frank Ewert, Roberto Ferrise, Thomas Gaiser, Inaki Garcia de Cortazar-Atauri, Luisa Giglio, Petr Hlavinka, Marcos Lana, Marie Launay, Gaeetan Louarn, Remy Manderscheid, Bruno Mary, Wilfried Mirschel, Marco Moriondo, Isik Oeztuerk, Andreas Pacholski, Dominique Ripoche-Wachter, Reimund P. Roetter, Francoise Ruget, Mirek Trnka, Domenico Ventrella, Hans -Joachim Weigel, Jurgen E. Olesen
EUROPEAN JOURNAL OF AGRONOMY
(2017)
Article
Agronomy
Matthias Kuhnert, Jagadeesh Yeluripati, Pete Smith, Holger Hoffmann, Marcel van Oijen, Julie Constantin, Elsa Coucheney, Rene Dechow, Henrik Eckersten, Thomas Gaiser, Balasz Grosz, Edwin Haas, Kurt-Christian Kersebaum, Ralf Kiese, Steffen Klatt, Elisabet Lewan, Claas Nendel, Helene Raynal, Carmen Sosa, Xenia Specka, Edmar Teixeira, Enli Wang, Lutz Weihermueller, Gang Zhao, Zhigan Zhao, Stephen Ogle, Frank Ewert
EUROPEAN JOURNAL OF AGRONOMY
(2017)
Article
Agronomy
Fulu Tao, Reimund P. Roetter, Taru Palosuo, C. G. H. Diaz-Ambrona, M. Ines Minguez, Mikhail A. Semenov, Kurt Christian Kersebaum, Claas Nendel, Davide Cammarano, Holger Hoffmann, Frank Ewert, Anaelle Dambreville, Pierre Martre, Lucia Rodriguez, Margarita Ruiz-Ramos, Thomas Gaiser, Jukka G. Hohn, Tapio Salo, Roberto Ferrise, Marco Bindi, Alan H. Schulman
EUROPEAN JOURNAL OF AGRONOMY
(2017)
Article
Agriculture, Multidisciplinary
Stefan Fronzek, Nina Pirttioja, Timothy R. Carter, Marco Bindi, Holger Hoffmann, Taru Palosuo, Margarita Ruiz-Ramos, Fulu Tao, Miroslav Trnka, Marco Acutis, Senthold Asseng, Piotr Baranowski, Bruno Basso, Per Bodin, Samuel Buis, Davide Cammarano, Paola Deligios, Marie-France Destain, Benjamin Dumont, Frank Ewert, Roberto Ferrise, Louis Francois, Thomas Gaiser, Petr Hlavinka, Ingrid Jacquemin, Kurt Christian Kersebaum, Chris Kollas, Jaromir Krzyszczak, Ignacio J. Lorite, Julien Minet, M. Ines Minguez, Manuel Montesino, Marco Moriondo, Christoph Mueller, Claas Nendel, Isik Ozturk, Alessia Perego, Alfredo Rodriguez, Alex C. Ruane, Francoise Ruget, Mattia Sanna, Mikhail A. Semenov, Cezary Slawinski, Pierre Stratonovitch, Iwan Supit, Katharina Waha, Enli Wang, Lianhai Wu, Zhigan Zhao, Reimund P. Rotter
AGRICULTURAL SYSTEMS
(2018)
Article
Soil Science
Elsa Coucheney, Henrik Eckersten, Holger Hoffmann, Per-Erik Jansson, Thomas Gaiser, Franck Ewert, Elisabet Lewan
Article
Biodiversity Conservation
Fulu Tao, Reimund P. Roetter, Taru Palosuo, Carlos Gregorio Hernandez Diaz-Ambrona, M. Ines Minguez, Mikhail A. Semenov, Kurt Christian Kersebaum, Claas Nendel, Xenia Specka, Holger Hoffmann, Frank Ewert, Anaelle Dambreville, Pierre Martre, Lucia Rodriguez, Margarita Ruiz-Ramos, Thomas Gaiser, Jukka G. Hohn, Tapio Salo, Roberto Ferrise, Marco Bindi, Davide Cammarano, Alan H. Schulman
GLOBAL CHANGE BIOLOGY
(2018)
Article
Agronomy
A. Rodriguez, M. Ruiz-Ramos, T. Palosuo, T. R. Carter, S. Fronzek, I. J. Lorite, R. Ferrise, N. Pirttioja, M. Bindi, P. Baranowski, S. Buis, D. Cammarano, Y. Chen, B. Dumont, F. Ewert, T. Gaiser, P. Hlavinka, H. Hoffmann, J. G. Hohn, F. Jurecka, K. C. Kersebaum, J. Krzyszczak, M. Lana, A. Mechiche-Alami, J. Minet, M. Montesino, C. Nendel, J. R. Porter, F. Ruget, M. A. Semenov, Z. Steinmetz, P. Stratonovitch, I. Supit, F. Tao, M. Trnka, A. de Wit, R. P. Roetter
AGRICULTURAL AND FOREST METEOROLOGY
(2019)
Article
Agronomy
Ganga Ram Maharjan, Holger Hoffmann, Heidi Webber, Amit Kumar Srivastava, Lutz Weihermueller, Ana Villa, Elsa Coucheney, Elisabet Lewan, Giacomo Trombi, Marco Moriondo, Marco Bindi, Balazs Grosz, Rene Dechow, Mathias Kuhnert, Luca Doro, Kurt-Christian Kersebaum, Tommaso Stella, Xenia Specka, Claas Nendel, Julie Constantin, Helene Raynal, Frank Ewert, Thomas Gaiser
EUROPEAN JOURNAL OF AGRONOMY
(2019)
Article
Environmental Sciences
Andreas Tewes, Holger Hoffmann, Manuel Nolte, Gunther Krauss, Fabian Schaefer, Christian Kerkhoff, Thomas Gaiser
Article
Agronomy
Andreas Tewes, Holger Hoffmann, Gunther Krauss, Fabian Schaefer, Christian Kerkhoff, Thomas Gaiser
Article
Agronomy
Andreas Tewes, Carsten Montzka, Manuel Nolte, Gunther Krauss, Holger Hoffmann, Thomas Gaiser
Article
Agronomy
Jaromir Krzyszczak, Piotr Baranowski, Monika Zubik, Holger Hoffmann
AGRICULTURAL AND FOREST METEOROLOGY
(2017)
Article
Agriculture, Multidisciplinary
Xiaogang Yin, Kurt Christian Kersebaum, Chris Kollas, Kiril Manevski, Sanmohan Baby, Nicolas Beaudoin, Isik Ozturk, Thomas Gaiser, Lianhai Wu, Munir Hoffmann, Monia Charfeddine, Tobias Conradt, Julie Constantin, Frank Ewert, Inaki Garcia de Cortazar-Atauri, Luisa Giglio, Petr Hlavinka, Holger Hoffmann, Marie Launay, Gaetan Louarn, Remy Manderscheid, Bruno Mary, Wilfried Mirschel, Claas Nendel, Andreas Pacholskin, Taru Palosuo, Dominique Ripoche-Wachter, Reimund P. Roetter, Francoise Ruget, Behzad Sharif, Mirek Trnka, Domenico Ventrella, Hans-Joachim Weigel, Jorgen E. Olesen
AGRICULTURAL SYSTEMS
(2017)
Article
Agronomy
Holger Hoffmann, Piotr Baranowski, Jaromir Krzyszczak, Monika Zubik, Cezary Slawinski, Thomas Gaiser, Frank Ewert
AGRICULTURAL AND FOREST METEOROLOGY
(2017)