Search Results

You are looking at 11 - 20 of 833 items for :

  • Deep learning x
  • All content x
Clear All
Yang Liu, Laurens Bogaardt, Jisk Attema, and Wilco Hazeleger

to forecast Arctic sea ice with a statistical model. This brings contemporary machine learning techniques into scope. Machine learning approaches, especially deep learning, are widely embraced by many fields and are increasingly used to deal with problems like clustering, classification, and regression ( LeCun et al. 2015 ). Benefiting from large volumes of data of Earth system ( Knüsel et al. 2019 ), those deep learning methods may be appropriate for the weather and climate domain ( Reichstein

Open access
Stephan Rasp, Hauke Schulz, Sandrine Bony, and Bjorn Stevens

identification. In these situations, machine learning techniques, particularly deep learning (see “Deep learning for vision tasks in the geosciences” sidebar), have demonstrated their ability to mimic the human capacity for identifying patterns, also from satellite cloud imagery (e.g., Wood and Hartmann 2006 ). However, the application and assessment of such techniques is often limited by the tedious task of obtaining sufficient training data, so much so that (in cloud studies at least) these approaches

Full access
Anthony Wimmers, Christopher Velden, and Joshua H. Cossuth

1. Introduction Deep learning (DL) is a newly popular, powerful and often confounding computational tool for developing predictive models in the sciences. It builds on a long legacy of neural network modeling, with a key feature being the organization of neural connections into multiple layers of nonlinear operations, enabling models to apply high levels of abstraction in their tasks. New hardware innovations, particularly in accessing graphical processing units (GPUs), have enabled DL

Full access
Veljko Petković, Marko Orescanin, Pierre Kirstetter, Christian Kummerow, and Ralph Ferraro

observations and storm morphology, little, if any, room has been left for a potentially novel physically based approach to emerge. However, recent advances in deep learning methods with neural networks may offer perhaps not new but for the first time fully applicable models that could better exploit the information content in PMW observations. This study seeks to investigate such a possibility through the use of deep learning for both retrieving precipitation types and improving the performance of PMW

Full access
Kuai Fang and Chaopeng Shen

function can be regarded as piecewise linear, to be estimated locally at each pixel. However, it is not clear if such a linear model could fully describe the process of soil moisture change, and, especially, provide strong performance for forecasts with a few days of latency. Deep learning (DL) is well known for its ability to learn nonlinear mapping relationships and model dynamical systems ( Shen 2018 ; LeCun et al. 2015 ; Schmidhuber 2015 ). In our previous work ( Fang et al. 2017 ), we employed

Free access
Imme Ebert-Uphoff and Kyle Hilburn

) for deeper study. From simple neurons to powerful neural networks. An artificial neural network (ANN; or NN for short) is a machine learning method loosely inspired by the human brain. An NN consists of a set of neurons (aka nodes ) that are connected by synapses which pass signals between the neurons. In sequential NNs , which are the primary type considered here, all neurons are arranged in a sequence of layers, and signals pass in a one-directional manner from the input layer through

Full access
Tao Song, Zihe Wang, Pengfei Xie, Nisheng Han, Jingyu Jiang, and Danya Xu

optimization of machine-learning methods may be hard, and overfitting is really a tough problem to be solved ( Jiang et al. 2018 ; Siahkoohi et al. 2019 ). In recent decades, deep-learning methods, especially recurrent neural network (RNN), have been widely used for time series data processing and value prediction. RNN introduces the recurrent unit structure and allows the internal connection between the hidden units, so it is suitable for analyzing and processing time series data ( Krizhevsky et al. 2012

Free access
Momme C. Hell, Bruce D. Cornelle, Sarah T. Gille, Arthur J. Miller, and Peter D. Bromirski

conventional wave observations. We use these data as a training set to develop a new method to characterize ocean swell observations. Feature comparison in geophysical data is often challenging because the observations are noisy, and the models are too simple. As we outline below, the combination of optimization and Monte Carlo methods enables us to improve our model understanding of the data, while we use the model to identify the relevant data. This is a “machine learning” approach that is constrained by

Full access
Jing-Yi Zhuo and Zhe-Min Tan


A deep learning-based method augmented by prior knowledge of tropical cyclones (TCs), called DeepTCNet, is introduced to estimate TC intensity and wind radii from infrared (IR) imagery over the North Atlantic Ocean. While standard deep learning practices have many advantages over conventional analysis approaches and can produce reliable estimates of TCs, the data-driven models informed by machine-readable physical knowledge of TCs could achieve higher performance. To this end, two approaches are explored to develop the physics-augmented DeepTCNet: (i) infusing the auxiliary physical information of TCs into models for single-task learning; (ii) learning auxiliary physical tasks for multi-task learning. More specifically, augmented by auxiliary information of TC fullness (a measure of the radial decay of the TC wind field), the DeepTCNet yielded a 12% improvement in estimating TC intensity over the non-augmented one. By learning TC wind radii and auxiliary TC intensity task simultaneously, the model’s wind radii estimation skill is improved by 6% over only learning four wind radii tasks, and by 9% over separately learning a single wind radii task. The evaluation results showed that the DeepTCNet is in-line with the Satellite Consensus technique (SATCON) but systematically outperforms the Advanced Dvorak Technique (ADT) at all intensity scales with an averaged 39% enhancement in TC intensity estimation. The DeepTCNet also surpasses the Multi-platform Tropical Cyclone Surface Wind Analysis technique (MTCSWA) with an average improvement of 32% in wind radii estimation.

Restricted access
Massimo Bonavita, Rossella Arcucci, Alberto Carrassi, Peter Dueben, Alan J. Geer, Bertrand Le Saux, Nicolas Longépé, Pierre-Philippe Mathieu, and Laure Raynaud

First ECMWF–ESA Workshop on Machine Learning for Earth System Observation and Prediction What : ECMWF and ESA convened a workshop to explore the current status, prospects, and opportunities in the application of machine learning/deep learning for Earth system observation and prediction. When : 5–8 October 2020 Where : Online; Almost 400 researchers from across the world joined the first ECMWF–ESA Workshop on Machine Learning for Earth System Observation and

Full access