Articles | Volume 30, issue 4
https://doi.org/10.5194/npg-30-553-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/npg-30-553-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
29 Nov 2023
Research article |
| 29 Nov 2023
| 29 Nov 2023
Downscaling of surface wind forecasts using convolutional neural networks
CEA, DES, IRESNE, DTN, Laboratory for Environmental Transfer Modeling, Cadarache, France
Laboratoire d’Aérologie, Université de Toulouse, CNRS, UPS, Toulouse, France
Pierre Durand
Laboratoire d’Aérologie, Université de Toulouse, CNRS, UPS, Toulouse, France
Thierry Hedde
CEA, DES, IRESNE, DTN, Laboratory for Environmental Transfer Modeling, Cadarache, France
Related authors
No articles found.
Philippe Ricaud, Pierre Durand, Paolo Grigioni, Massimo Del Guasta, Giuseppe Camporeale, Axel Roy, Jean-Luc Attié, and John Bognar
Atmos. Meas. Tech., 17, 5071–5089, https://doi.org/10.5194/amt-17-5071-2024, https://doi.org/10.5194/amt-17-5071-2024, 2024
Short summary
Short summary
Clouds in Antarctica are key elements affecting climate evolution. Some clouds are composed of supercooled liquid water (SLW; water held in liquid form below 0 °C) and are difficult to forecast by models. We performed in situ observations of SLW clouds at Concordia Station using SLW sondes attached to meteorological balloons in summer 2021–2022. The SLW clouds were observed in a saturated layer at the top of the planetary boundary layer in agreement with ground-based lidar observations.
Philippe Ricaud, Massimo Del Guasta, Angelo Lupi, Romain Roehrig, Eric Bazile, Pierre Durand, Jean-Luc Attié, Alessia Nicosia, and Paolo Grigioni
Atmos. Chem. Phys., 24, 613–630, https://doi.org/10.5194/acp-24-613-2024, https://doi.org/10.5194/acp-24-613-2024, 2024
Short summary
Short summary
Clouds affect the Earth's climate in ways that depend on the type of cloud (solid/liquid water). From observations at Concordia (Antarctica), we show that in supercooled liquid water (liquid water for temperatures below 0°C) clouds (SLWCs), temperature and SLWC radiative forcing increase with liquid water (up to 70 W m−2). We extrapolated that the maximum SLWC radiative forcing can reach 40 W m−2 over the Antarctic Peninsula, highlighting the importance of SLWCs for global climate prediction.
Philippe Ricaud, Massimo Del Guasta, Eric Bazile, Niramson Azouz, Angelo Lupi, Pierre Durand, Jean-Luc Attié, Dana Veron, Vincent Guidard, and Paolo Grigioni
Atmos. Chem. Phys., 20, 4167–4191, https://doi.org/10.5194/acp-20-4167-2020, https://doi.org/10.5194/acp-20-4167-2020, 2020
Short summary
Short summary
Thin (~ 100 m) supercooled liquid water (SLW, water staying in liquid phase below 0 °C) clouds have been detected, analysed, and modelled over the Dome C (Concordia, Antarctica) station during the austral summer 2018–2019 using observations and meteorological analyses. The SLW clouds were observed at the top of the planetary boundary layer and the SLW content was always strongly underestimated by the model indicating an incorrect simulation of the surface energy budget of the Antarctic Plateau.
Federica Pacifico, Claire Delon, Corinne Jambert, Pierre Durand, Eleanor Morris, Mat J. Evans, Fabienne Lohou, Solène Derrien, Venance H. E. Donnou, Arnaud V. Houeto, Irene Reinares Martínez, and Pierre-Etienne Brilouet
Atmos. Chem. Phys., 19, 2299–2325, https://doi.org/10.5194/acp-19-2299-2019, https://doi.org/10.5194/acp-19-2299-2019, 2019
Short summary
Short summary
Biogenic fluxes from soil at a local and regional scale are crucial to study air pollution and climate. Here we present field measurements of soil fluxes of nitric oxide (NO) and ammonia (NH3) observed over four different land cover types, i.e. bare soil, grassland, maize field, and forest, at an inland rural site in Benin, West Africa, during the DACCIWA field campaign in
June and July 2016.
Evelyn Freney, Karine Sellegri, Mounir Chrit, Kouji Adachi, Joel Brito, Antoine Waked, Agnès Borbon, Aurélie Colomb, Régis Dupuy, Jean-Marc Pichon, Laetitia Bouvier, Claire Delon, Corinne Jambert, Pierre Durand, Thierry Bourianne, Cécile Gaimoz, Sylvain Triquet, Anaïs Féron, Matthias Beekmann, François Dulac, and Karine Sartelet
Atmos. Chem. Phys., 18, 7041–7056, https://doi.org/10.5194/acp-18-7041-2018, https://doi.org/10.5194/acp-18-7041-2018, 2018
Short summary
Short summary
The focus of these experiments, within the ChArMEx project, were to better understand the chemical properties of ambient aerosols over the Mediterranean region. A series of airborne measurements were performed aboard the French research aircraft, the ATR42, during the summer period. Aerosol and gas-phase chemical mass spectrometry allowed us to understand the sources and formation of organic aerosols. Numerical models were incorporated into this study to help interpret our observations.
Jean-Baptiste Renard, François Dulac, Pierre Durand, Quentin Bourgeois, Cyrielle Denjean, Damien Vignelles, Benoit Couté, Matthieu Jeannot, Nicolas Verdier, and Marc Mallet
Atmos. Chem. Phys., 18, 3677–3699, https://doi.org/10.5194/acp-18-3677-2018, https://doi.org/10.5194/acp-18-3677-2018, 2018
Short summary
Short summary
A campaign was performed in the summer of 2013 above the Mediterranean basin, including in situ counting balloon-borne aerosol measurements (LOAC), for the detection of mineral dust. Three modes in the dust particle volume size distributions were detected, at roughly 0.2, 4, and 30 mm. Particles larger than 40 mm were often observed. They were lifted several days before and their persistence after transport over long distances is in conflict with dust sedimentation calculations.
François Gheusi, Pierre Durand, Nicolas Verdier, François Dulac, Jean-Luc Attié, Philippe Commun, Brice Barret, Claude Basdevant, Antoine Clenet, Solène Derrien, Alexis Doerenbecher, Laaziz El Amraoui, Alain Fontaine, Emeric Hache, Corinne Jambert, Elodie Jaumouillé, Yves Meyerfeld, Laurent Roblou, and Flore Tocquer
Atmos. Meas. Tech., 9, 5811–5832, https://doi.org/10.5194/amt-9-5811-2016, https://doi.org/10.5194/amt-9-5811-2016, 2016
Short summary
Short summary
Boundary-layer pressurised balloons allow for horizontal multi-day flights in the lower atmosphere, carrying light scientific payloads. Ozonesondes, usually used for balloon soundings have too short a lifetime for such flights. An adaptation is proposed, whereby conventional sondes are operated with short measurement phases alternating with longer periods of dormancy. The sondes were operated over the western Mediterranean, offering an original perspective on tropospheric ozone.
M. Mallet, F. Dulac, P. Formenti, P. Nabat, J. Sciare, G. Roberts, J. Pelon, G. Ancellet, D. Tanré, F. Parol, C. Denjean, G. Brogniez, A. di Sarra, L. Alados-Arboledas, J. Arndt, F. Auriol, L. Blarel, T. Bourrianne, P. Chazette, S. Chevaillier, M. Claeys, B. D'Anna, Y. Derimian, K. Desboeufs, T. Di Iorio, J.-F. Doussin, P. Durand, A. Féron, E. Freney, C. Gaimoz, P. Goloub, J. L. Gómez-Amo, M. J. Granados-Muñoz, N. Grand, E. Hamonou, I. Jankowiak, M. Jeannot, J.-F. Léon, M. Maillé, S. Mailler, D. Meloni, L. Menut, G. Momboisse, J. Nicolas, T. Podvin, V. Pont, G. Rea, J.-B. Renard, L. Roblou, K. Schepanski, A. Schwarzenboeck, K. Sellegri, M. Sicard, F. Solmon, S. Somot, B Torres, J. Totems, S. Triquet, N. Verdier, C. Verwaerde, F. Waquet, J. Wenger, and P. Zapf
Atmos. Chem. Phys., 16, 455–504, https://doi.org/10.5194/acp-16-455-2016, https://doi.org/10.5194/acp-16-455-2016, 2016
Short summary
Short summary
The aim of this article is to present an experimental campaign over the Mediterranean focused on aerosol-radiation measurements and modeling. Results indicate an important atmospheric loading associated with a moderate absorbing ability of mineral dust. Observations suggest a complex vertical structure and size distributions characterized by large aerosols within dust plumes. The radiative effect is highly variable, with negative forcing over the Mediterranean and positive over northern Africa.
C. Darbieu, F. Lohou, M. Lothon, J. Vilà-Guerau de Arellano, F. Couvreux, P. Durand, D. Pino, E. G. Patton, E. Nilsson, E. Blay-Carreras, and B. Gioli
Atmos. Chem. Phys., 15, 10071–10086, https://doi.org/10.5194/acp-15-10071-2015, https://doi.org/10.5194/acp-15-10071-2015, 2015
Short summary
Short summary
A case study of the BLLAST experiment is considered to explore the decay of turbulence that occurs in the convective boundary layer over land during the afternoon. Based on observations and on a large-eddy simulation, the analysis reveals two phases in the afternoon: a first quasi-stationary phase when the turbulent kinetic energy slowly decays without significant change in the turbulence structure and a second phase of more rapid decay with a change in spectral turbulence characteristics.
H. P. Pietersen, J. Vilà-Guerau de Arellano, P. Augustin, A. van de Boer, O. de Coster, H. Delbarre, P. Durand, M. Fourmentin, B. Gioli, O. Hartogensis, F. Lohou, M. Lothon, H. G. Ouwersloot, D. Pino, and J. Reuder
Atmos. Chem. Phys., 15, 4241–4257, https://doi.org/10.5194/acp-15-4241-2015, https://doi.org/10.5194/acp-15-4241-2015, 2015
M. Lothon, F. Lohou, D. Pino, F. Couvreux, E. R. Pardyjak, J. Reuder, J. Vilà-Guerau de Arellano, P Durand, O. Hartogensis, D. Legain, P. Augustin, B. Gioli, D. H. Lenschow, I. Faloona, C. Yagüe, D. C. Alexander, W. M. Angevine, E Bargain, J. Barrié, E. Bazile, Y. Bezombes, E. Blay-Carreras, A. van de Boer, J. L. Boichard, A. Bourdon, A. Butet, B. Campistron, O. de Coster, J. Cuxart, A. Dabas, C. Darbieu, K. Deboudt, H. Delbarre, S. Derrien, P. Flament, M. Fourmentin, A. Garai, F. Gibert, A. Graf, J. Groebner, F. Guichard, M. A. Jiménez, M. Jonassen, A. van den Kroonenberg, V. Magliulo, S. Martin, D. Martinez, L. Mastrorillo, A. F. Moene, F. Molinos, E. Moulin, H. P. Pietersen, B. Piguet, E. Pique, C. Román-Cascón, C. Rufin-Soler, F. Saïd, M. Sastre-Marugán, Y. Seity, G. J. Steeneveld, P. Toscano, O. Traullé, D. Tzanos, S. Wacker, N. Wildmann, and A. Zaldei
Atmos. Chem. Phys., 14, 10931–10960, https://doi.org/10.5194/acp-14-10931-2014, https://doi.org/10.5194/acp-14-10931-2014, 2014
R. Baghi, P. Durand, C. Jambert, C. Jarnot, C. Delon, D. Serça, N. Striebig, M. Ferlicoq, and P. Keravec
Atmos. Meas. Tech., 5, 3119–3132, https://doi.org/10.5194/amt-5-3119-2012, https://doi.org/10.5194/amt-5-3119-2012, 2012
Related subject area
Subject: Time series, machine learning, networks, stochastic processes, extreme events | Topic: Climate, atmosphere, ocean, hydrology, cryosphere, biosphere | Techniques: Big data and artificial intelligence
Evaluation of forecasts by a global data-driven weather model with and without probabilistic post-processing at Norwegian stations
Characterisation of Dansgaard-Oeschger events in palaeoclimate time series using the Matrix Profile
The sampling method for optimal precursors of El Niño–Southern Oscillation events
A comparison of two causal methods in the context of climate analyses
A two-fold deep-learning strategy to correct and downscale winds over mountains
Representation learning with unconditional denoising diffusion models for dynamical systems
Data-driven methods to estimate the committor function in conceptual ocean models
Exploring meteorological droughts' spatial patterns across Europe through complex network theory
Integrated hydrodynamic and machine learning models for compound flooding prediction in a data-scarce estuarine delta
Predicting sea surface temperatures with coupled reservoir computers
Using neural networks to improve simulations in the gray zone
The blessing of dimensionality for the analysis of climate data
Producing realistic climate data with generative adversarial networks
Identification of droughts and heatwaves in Germany with regional climate networks
Extracting statistically significant eddy signals from large Lagrangian datasets using wavelet ridge analysis, with application to the Gulf of Mexico
Ensemble-based statistical interpolation with Gaussian anamorphosis for the spatial analysis of precipitation
Applications of matrix factorization methods to climate data
Detecting dynamical anomalies in time series from different palaeoclimate proxy archives using windowed recurrence network analysis
Remember the past: a comparison of time-adaptive training schemes for non-homogeneous regression
John Bjørnar Bremnes, Thomas N. Nipen, and Ivar A. Seierstad
Nonlin. Processes Geophys., 31, 247–257, https://doi.org/10.5194/npg-31-247-2024, https://doi.org/10.5194/npg-31-247-2024, 2024
Short summary
Short summary
During the last 2 years, tremendous progress has been made in global data-driven weather models trained on reanalysis data. In this study, the Pangu-Weather model is compared to several numerical weather prediction models with and without probabilistic post-processing for temperature and wind speed forecasting. The results confirm that global data-driven models are promising for operational weather forecasting and that post-processing can improve these forecasts considerably.
Susana Barbosa, Maria Eduarda Silva, and Denis-Didier Rousseau
Nonlin. Processes Geophys. Discuss., https://doi.org/10.5194/npg-2024-13, https://doi.org/10.5194/npg-2024-13, 2024
Revised manuscript accepted for NPG
Short summary
Short summary
The characterisation of abrupt transitions in palaeoclimate records allows the understanding of millennial climate variability and of potential tipping points in the context of current climate change. In our study an algorithmic method, the matrix profile, is employed to characterise abrupt warmings designated as Dansgaard-Oeschger (DO) events and to identify the most similar transitions in the palaeoclimate time series.
Bin Shi and Junjie Ma
Nonlin. Processes Geophys., 31, 165–174, https://doi.org/10.5194/npg-31-165-2024, https://doi.org/10.5194/npg-31-165-2024, 2024
Short summary
Short summary
Different from traditional deterministic optimization algorithms, we implement the sampling method to compute the conditional nonlinear optimal perturbations (CNOPs) in the realistic and predictive coupled ocean–atmosphere model, which reduces the first-order information to the zeroth-order one, avoiding the high-cost computation of the gradient. The numerical performance highlights the importance of stochastic optimization algorithms to compute CNOPs and capture initial optimal precursors.
David Docquier, Giorgia Di Capua, Reik V. Donner, Carlos A. L. Pires, Amélie Simon, and Stéphane Vannitsem
Nonlin. Processes Geophys., 31, 115–136, https://doi.org/10.5194/npg-31-115-2024, https://doi.org/10.5194/npg-31-115-2024, 2024
Short summary
Short summary
Identifying causes of specific processes is crucial in order to better understand our climate system. Traditionally, correlation analyses have been used to identify cause–effect relationships in climate studies. However, correlation does not imply causation, which justifies the need to use causal methods. We compare two independent causal methods and show that these are superior to classical correlation analyses. We also find some interesting differences between the two methods.
Louis Le Toumelin, Isabelle Gouttevin, Clovis Galiez, and Nora Helbig
Nonlin. Processes Geophys., 31, 75–97, https://doi.org/10.5194/npg-31-75-2024, https://doi.org/10.5194/npg-31-75-2024, 2024
Short summary
Short summary
Forecasting wind fields over mountains is of high importance for several applications and particularly for understanding how wind erodes and disperses snow. Forecasters rely on operational wind forecasts over mountains, which are currently only available on kilometric scales. These forecasts can also be affected by errors of diverse origins. Here we introduce a new strategy based on artificial intelligence to correct large-scale wind forecasts in mountains and increase their spatial resolution.
Tobias Sebastian Finn, Lucas Disson, Alban Farchi, Marc Bocquet, and Charlotte Durand
EGUsphere, https://doi.org/10.5194/egusphere-2023-2261, https://doi.org/10.5194/egusphere-2023-2261, 2023
Short summary
Short summary
We train neural networks as denoising diffusion models for state generation in the Lorenz 1963 system and demonstrate that they learn an internal representation of the system. We make use of this learned representation and the pre-trained model in two downstream tasks: surrogate modelling and ensemble generation. For both tasks, the diffusion model can outperform other more common approaches. Thus, we see a potential of representation learning with diffusion models for dynamical systems.
Valérian Jacques-Dumas, René M. van Westen, Freddy Bouchet, and Henk A. Dijkstra
Nonlin. Processes Geophys., 30, 195–216, https://doi.org/10.5194/npg-30-195-2023, https://doi.org/10.5194/npg-30-195-2023, 2023
Short summary
Short summary
Computing the probability of occurrence of rare events is relevant because of their high impact but also difficult due to the lack of data. Rare event algorithms are designed for that task, but their efficiency relies on a score function that is hard to compute. We compare four methods that compute this function from data and measure their performance to assess which one would be best suited to be applied to a climate model. We find neural networks to be most robust and flexible for this task.
Domenico Giaquinto, Warner Marzocchi, and Jürgen Kurths
Nonlin. Processes Geophys., 30, 167–181, https://doi.org/10.5194/npg-30-167-2023, https://doi.org/10.5194/npg-30-167-2023, 2023
Short summary
Short summary
Despite being among the most severe climate extremes, it is still challenging to assess droughts’ features for specific regions. In this paper we study meteorological droughts in Europe using concepts derived from climate network theory. By exploring the synchronization in droughts occurrences across the continent we unveil regional clusters which are individually examined to identify droughts’ geographical propagation and source–sink systems, which could potentially support droughts’ forecast.
Joko Sampurno, Valentin Vallaeys, Randy Ardianto, and Emmanuel Hanert
Nonlin. Processes Geophys., 29, 301–315, https://doi.org/10.5194/npg-29-301-2022, https://doi.org/10.5194/npg-29-301-2022, 2022
Short summary
Short summary
In this study, we successfully built and evaluated machine learning models for predicting water level dynamics as a proxy for compound flooding hazards in a data-scarce delta. The issues that we tackled here are data scarcity and low computational resources for building flood forecasting models. The proposed approach is suitable for use by local water management agencies in developing countries that encounter these issues.
Benjamin Walleshauser and Erik Bollt
Nonlin. Processes Geophys., 29, 255–264, https://doi.org/10.5194/npg-29-255-2022, https://doi.org/10.5194/npg-29-255-2022, 2022
Short summary
Short summary
As sea surface temperature (SST) is vital for understanding the greater climate of the Earth and is also an important variable in weather prediction, we propose a model that effectively capitalizes on the reduced complexity of machine learning models while still being able to efficiently predict over a large spatial domain. We find that it is proficient at predicting the SST at specific locations as well as over the greater domain of the Earth’s oceans.
Raphael Kriegmair, Yvonne Ruckstuhl, Stephan Rasp, and George Craig
Nonlin. Processes Geophys., 29, 171–181, https://doi.org/10.5194/npg-29-171-2022, https://doi.org/10.5194/npg-29-171-2022, 2022
Short summary
Short summary
Our regional numerical weather prediction models run at kilometer-scale resolutions. Processes that occur at smaller scales not yet resolved contribute significantly to the atmospheric flow. We use a neural network (NN) to represent the unresolved part of physical process such as cumulus clouds. We test this approach on a simplified, yet representative, 1D model and find that the NN corrections vastly improve the model forecast up to a couple of days.
Bo Christiansen
Nonlin. Processes Geophys., 28, 409–422, https://doi.org/10.5194/npg-28-409-2021, https://doi.org/10.5194/npg-28-409-2021, 2021
Short summary
Short summary
In geophysics we often need to analyse large samples of high-dimensional fields. Fortunately but counterintuitively, such high dimensionality can be a blessing, and we demonstrate how this allows simple analytical results to be derived. These results include estimates of correlations between sample members and how the sample mean depends on the sample size. We show that the properties of high dimensionality with success can be applied to climate fields, such as those from ensemble modelling.
Camille Besombes, Olivier Pannekoucke, Corentin Lapeyre, Benjamin Sanderson, and Olivier Thual
Nonlin. Processes Geophys., 28, 347–370, https://doi.org/10.5194/npg-28-347-2021, https://doi.org/10.5194/npg-28-347-2021, 2021
Short summary
Short summary
This paper investigates the potential of a type of deep generative neural network to produce realistic weather situations when trained from the climate of a general circulation model. The generator represents the climate in a compact latent space. It is able to reproduce many aspects of the targeted multivariate distribution. Some properties of our method open new perspectives such as the exploration of the extremes close to a given state or how to connect two realistic weather states.
Gerd Schädler and Marcus Breil
Nonlin. Processes Geophys., 28, 231–245, https://doi.org/10.5194/npg-28-231-2021, https://doi.org/10.5194/npg-28-231-2021, 2021
Short summary
Short summary
We used regional climate networks (RCNs) to identify past heatwaves and droughts in Germany. RCNs provide information for whole areas and can provide many details of extreme events. The RCNs were constructed on the grid of the E-OBS data set. Time series correlation was used to construct the networks. Network metrics were compared to standard extreme indices and differed considerably between normal and extreme years. The results show that RCNs can identify severe and moderate extremes.
Jonathan M. Lilly and Paula Pérez-Brunius
Nonlin. Processes Geophys., 28, 181–212, https://doi.org/10.5194/npg-28-181-2021, https://doi.org/10.5194/npg-28-181-2021, 2021
Short summary
Short summary
Long-lived eddies are an important part of the ocean circulation. Here a dataset for studying eddies in the Gulf of Mexico is created through the analysis of trajectories of drifting instruments. The method involves the identification of quasi-periodic signals, characteristic of particles trapped in eddies, from the displacement records, followed by the creation of a measure of statistical significance. It is expected that this dataset will be of use to other authors studying this region.
Cristian Lussana, Thomas N. Nipen, Ivar A. Seierstad, and Christoffer A. Elo
Nonlin. Processes Geophys., 28, 61–91, https://doi.org/10.5194/npg-28-61-2021, https://doi.org/10.5194/npg-28-61-2021, 2021
Short summary
Short summary
An unprecedented amount of rainfall data is available nowadays, such as ensemble model output, weather radar estimates, and in situ observations from networks of both traditional and opportunistic sensors. Nevertheless, the exact amount of precipitation, to some extent, eludes our knowledge. The objective of our study is precipitation reconstruction through the combination of numerical model outputs with observations from multiple data sources.
Dylan Harries and Terence J. O'Kane
Nonlin. Processes Geophys., 27, 453–471, https://doi.org/10.5194/npg-27-453-2020, https://doi.org/10.5194/npg-27-453-2020, 2020
Short summary
Short summary
Different dimension reduction methods may produce profoundly different low-dimensional representations of multiscale systems. We perform a set of case studies to investigate these differences. When a clear scale separation is present, similar bases are obtained using all methods, but when this is not the case some methods may produce representations that are poorly suited for describing features of interest, highlighting the importance of a careful choice of method when designing analyses.
Jaqueline Lekscha and Reik V. Donner
Nonlin. Processes Geophys., 27, 261–275, https://doi.org/10.5194/npg-27-261-2020, https://doi.org/10.5194/npg-27-261-2020, 2020
Moritz N. Lang, Sebastian Lerch, Georg J. Mayr, Thorsten Simon, Reto Stauffer, and Achim Zeileis
Nonlin. Processes Geophys., 27, 23–34, https://doi.org/10.5194/npg-27-23-2020, https://doi.org/10.5194/npg-27-23-2020, 2020
Short summary
Short summary
Statistical post-processing aims to increase the predictive skill of probabilistic ensemble weather forecasts by learning the statistical relation between historical pairs of observations and ensemble forecasts within a given training data set. This study compares four different training schemes and shows that including multiple years of data in the training set typically yields a more stable post-processing while it loses the ability to quickly adjust to temporal changes in the underlying data.
Cited articles
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001. a
de Bode, M., Hedde, T., Roubin, P., and Durand, P.: Fine-Resolution WRF Simulation of Stably Stratified Flows in Shallow Pre-Alpine Valleys: A Case Study of the KASCADE-2017 Campaign, Atmosphere, 12, 1063, https://doi.org/10.3390/atmos12081063, 2021. a
de Bode, M., Hedde, T., Roubin, P., and Durand, P.: A Method to Improve Land Use Representation for Weather Simulations Based on High-Resolution Data Sets-Application to Corine Land Cover Data in the WRF Model, Earth Space Sci., 10, e2021EA002123, https://doi.org/10.1029/2021EA002123, 2023. a
Dupuy, F., Duine, G.-J., Durand, P., Hedde, T., Roubin, P., and Pardyjak, E.: Local-Scale Valley Wind Retrieval Using an Artificial Neural Network Applied to Routine Weather Observations, J. Appl. Meteorol. Clim., 58, 1007–1022, https://doi.org/10.1175/JAMC-D-18-0175.1, 2019. a
Dupuy, F., Duine, G.-J., Durand, P., Hedde, T., Pardyjak, E., and Roubin, P.: Valley Winds at the Local Scale: Correcting Routine Weather Forecast Using Artificial Neural Networks, Atmosphere, 12, 128, https://doi.org/10.3390/atmos12020128, 2021a. a, b
Dupuy, F., Mestre, O., Serrurier, M., Kivachuk Burdá, V., Zamo, M., Cabrera-Gutiérrez, N. C., Bakkay, M. C., Jouhaud, J.-C., Mader, M.-A., and Oller, G.: ARPEGE Cloud Cover Forecast Postprocessing with Convolutional Neural Network, Weather Forecast., 36, 567–586, https://doi.org/10.1175/WAF-D-20-0093.1, 2021b. a
Fiddes, J. and Gruber, S.: TopoSCALE v.1.0: downscaling gridded climate data in complex terrain, Geosci. Model Dev., 7, 387–405, https://doi.org/10.5194/gmd-7-387-2014, 2014. a, b
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press, http://www.deeplearningbook.org (last access: 2 November 2023), 2016. a
Harris, L., McRae, A. T. T., Chantry, M., Dueben, P. D., and Palmer, T. N.: A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts, J. Adv. Model. Earth Sy., 14, e2022MS003120, https://doi.org/10.1029/2022MS003120, 2022. a
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, Proceedings of the 32nd International Conference on Machine Learning, 7–9 July 2015, Lille, France, 448–456, 2015. a
Jammalamadaka, S. R. and SenGupta, A.: Topics in Circular Statistics, World Sci., 1, 1–24, https://doi.org/10.1142/4031, 2001. a
Kruyt, B., Mott, R., Fiddes, J., Gerber, F., Sharma, V., and Reynolds, D.: A Downscaling Intercomparison Study: The Representation of Slope- and Ridge-Scale Processes in Models of Different Complexity, Front. Earth Sci., 10, 789332, https://doi.org/10.3389/feart.2022.789332, 2022. a
Kulkarni, A., Shivananda, A., and Sharma, N. R.: Image Super-Resolution, Apress, Berkeley, CA, 261–295, https://doi.org/10.1007/978-1-4842-8273-1_8, 2022. a
Lagerquist, R., McGovern, A., and Gagne II, D. J.: Deep Learning for Spatially Explicit Prediction of Synoptic-Scale Fronts, Weather Forecast., 34, 1137–1160, https://doi.org/10.1175/WAF-D-18-0183.1, 2019. a
Lang, M. N., Schlosser, L., Hothorn, T., Mayr, G. J., Stauffer, R., and Zeileis, A.: Circular Regression Trees and Forests with an Application to Probabilistic Wind Direction Forecasting, J. Roy. Stat. Soc. C-App., 69, 1357–1374, https://doi.org/10.1111/rssc.12437, 2020. a
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015. a
Leinonen, J., Nerini, D., and Berne, A.: Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network, IEEE T. Geosci. Remote, 59, 7211–7223, https://doi.org/10.1109/TGRS.2020.3032790, 2021. a
Rabin, J., Delon, J., and Gousseau, Y.: Circular Earth Mover's Distance for the comparison of local features, in: 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA, 8–11 December 2008, 1–4, https://doi.org/10.1109/ICPR.2008.4761372, 2008. a
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, CoRR, arXiv [preprint], https://doi.org/10.48550/arXiv.1505.04597, 18 May 2015. a
Salameh, T., Drobinski, P., Vrac, M., and Naveau, P.: Statistical downscaling of near-surface wind over complex terrain in southern France, Meteorol. Atmos. Phys., 103, 253–265, https://doi.org/10.1007/s00703-008-0330-7, 2009. a
Schmidli, J., Böing, S., and Fuhrer, O.: Accuracy of Simulated Diurnal Valley Winds in the Swiss Alps: Influence of Grid Resolution, Topography Filtering, and Land Surface Datasets, Atmosphere, 9, 196, https://doi.org/10.3390/atmos9050196, 2018. a
Skamarock, W. C., Klemp, J. B., Dudhia, J., Gill, D. O., Liu, Z., Berner, J., Wang, W., Powers, J. G., Duda, M. G., Barker, D. M., and Huang, X.: A description of the advanced research WRF model version 4, National Center for Atmospheric Research: Boulder, CO, USA, 145, 550, https://doi.org/10.5065/1dfh-6p97, 2019. a
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.: Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014. a
Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., and Ganguly, A. R.: Generating High Resolution Climate Change Projections through Single Image Super-Resolution: An Abridged Version, in: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, International Joint Conferences on Artificial Intelligence Organization, Stockholm, Sweden 13–19 July 2018, 5389–5393, https://doi.org/10.24963/ijcai.2018/759, 2018. a
Vannitsem, S., Bremnes, J. B., Demaeyer, J., Evans, G. R., Flowerdew, J., Hemri, S., Lerch, S., Roberts, N., Theis, S., Atencia, A., Bouallègue, Z. B., Bhend, J., Dabernig, M., Cruz, L. D., Hieta, L., Mestre, O., Moret, L., Plenković, I. O., Schmeits, M., Taillardat, M., den Bergh, J. V., Schaeybroeck, B. V., Whan, K., and Ylhaisi, J.: Statistical Postprocessing for Weather Forecasts: Review, Challenges, and Avenues in a Big Data World, B. Am. Meteorol. Soc., 102, E681–E699, https://doi.org/10.1175/BAMS-D-19-0308.1, 2021. a
Wagenbrenner, N. S., Forthofer, J. M., Lamb, B. K., Shannon, K. S., and Butler, B. W.: Downscaling surface wind predictions from numerical weather prediction models in complex terrain with WindNinja, Atmos. Chem. Phys., 16, 5229–5241, https://doi.org/10.5194/acp-16-5229-2016, 2016. a, b
Whiteman, C. D.: Mountain Meteorology: Fundamentals and Applications, Oxford University Press, https://doi.org/10.1093/oso/9780195132717.001.0001, 2000. a
Wilks, D.: Chapter 8 – Forecast Verification, in: Statistical Methods in the Atmospheric Sciences, edited by: Wilks, D. S., vol. 100 of International Geophysics, Academic Press, 301–394, https://doi.org/10.1016/B978-0-12-385022-5.00008-7, 2011. a
Yamartino, R. J.: A Comparison of Several “Single-Pass” Estimators of the Standard Deviation of Wind Direction, J. Appl. Meteorol. Clim. 23, 1362–1366, https://doi.org/10.1175/1520-0450(1984)023<1362:ACOSPE>2.0.CO;2, 1984. a
Yang, W., Zhang, X., Tian, Y., Wang, W., Xue, J.-H., and Liao, Q.: Deep Learning for Single Image Super-Resolution: A Brief Review, IEEE T. Multimedia, 21, 3106–3121, https://doi.org/10.1109/TMM.2019.2919431, 2019. a
Zamo, M., Bel, L., Mestre, O., and Stein, J.: Improved Gridded Wind Speed Forecasts by Statistical Postprocessing of Numerical Models with Block Regression, Weather Forecast., 31, 1929–1945, https://doi.org/10.1175/WAF-D-16-0052.1, 2016. a
Short summary
Forecasting near-surface winds over complex terrain requires high-resolution numerical weather prediction models, which drastically increase the duration of simulations and hinder them in running on a routine basis. A faster alternative is statistical downscaling. We explore different ways of calculating near-surface wind speed and direction using artificial intelligence algorithms based on various convolutional neural networks in order to find the best approach for wind downscaling.
Forecasting near-surface winds over complex terrain requires high-resolution numerical weather...
