Aditya Grover
Eric Horvitz
ABSTRACT
Weather forecasting is a canonical predictive challenge that has depended primarily on model-based methods. We explore new directions with forecasting weather as a data-intensive challenge that involves inferences across space and time. We study specifically the power of making predictions via a hybrid approach that combines discriminatively trained predictive models with a deep neural network that models the joint statistics of a set of weather-related variables. We show how the base model can be enhanced with spatial interpolation that uses learned long-range spatial dependencies. We also derive an efficient learning and inference procedure that allows for large scale optimization of the model parameters. We evaluate the methods with experiments on real-world meteorological data that highlight the promise of the approach.
Supplemental Material
- M. J. Beal. Variational algorithms for approximate Bayesian inference. PhD thesis, University of London, 2003.Google Scholar
- L. Chen and X. Lai. Comparison between ARIMA and ANN models used in short-term wind speed forecasting. In Power and Energy Engineering Conference (APPEEC), 2011 Asia-Pacific, pages 1--4. IEEE, 2011. Google ScholarDigital Library
- A. S. Cofıno, R. Cano, C. Sordo, and J. M. Gutierrez. Bayesian networks for probabilistic weather prediction. In 15th Eureopean Conference on Artificial Intelligence (ECAI), 2002.Google Scholar
- I. Durre, R. S. Vose, and D. B. Wuertz. Overview of the Integrated Global Radiosonde Archive. Journal of Climate, 19(1):53--68, 2006.Google ScholarCross Ref
- I. Durre, R. S. Vose, and D. B. Wuertz. Robust automated quality assurance of radiosonde temperatures. Journal of Applied Meteorology and Climatology, 47(8):2081--2095, 2008.Google ScholarCross Ref
- M. Gönen and E. Alpaydın. Multiple kernel learning algorithms. The Journal of Machine Learning Research, 12:2211--2268, 2011. Google ScholarDigital Library
- G. Hinton, S. Osindero, and Y.-W. Teh. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527--1554, 2006. Google ScholarDigital Library
- I. Horenko, R. Klein, S. Dolaptchiev, and C. Schütte. Automated Generation of Reduced Stochastic Weather Models I: simultaneous dimension and model reduction for time series analysis. Multiscale Modeling & Simulation, 6(4):1125--1145, 2008.Google ScholarCross Ref
- A. Kapoor, Z. Horvitz, S. Laube, and E. Horvitz. Airplanes aloft as a sensor network for wind forecasting. In Proceedings of the 13th international symposium on Information Processing in Sensor Networks (IPSN), pages 25--34. IEEE Press, 2014. Google ScholarDigital Library
- V. M. Krasnopolsky and M. S. Fox-Rabinovitz. Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction. Neural Networks, 19(2):122--134, 2006. Google ScholarDigital Library
- R. J. Kuligowski and A. P. Barros. Localized precipitation forecasts from a numerical weather prediction model using artificial neural networks. Weather and Forecasting, 13(4):1194--1204, 1998.Google ScholarCross Ref
- G. Marchuk. Numerical methods in weather prediction. Elsevier, 2012.Google Scholar
- A. McGovern, D. John Gagne, N. Troutman, R. A. Brown, J. Basara, and J. K. Williams. Using spatiotemporal relational random forests to improve our understanding of severe weather processes. Statistical Analysis and Data Mining: The ASA Data Science Journal, 4(4):407--429, 2011. Google ScholarDigital Library
- A. McGovern, T. Supinie, I. Gagne, M. Collier, R. Brown, J. Basara, and J. Williams. Understanding severe weather processes through spatiotemporal relational random forests. In 2010 NASA conference on intelligent data understanding, 2010.Google Scholar
- R. Mittelman, B. Kuipers, S. Savarese, and H. Lee. Structured Recurrent Temporal Restricted Boltzmann Machines. In Proceedings of the 31st International Conference on Machine Learning (ICML), pages 1647--1655, 2014.Google Scholar
- Y. Radhika and M. Shashi. Atmospheric temperature prediction using support vector machines. International Journal of Computer Theory and Engineering, 1(1):1793--8201, 2009.Google Scholar
- C. E. Rasmussen. Gaussian processes for machine learning. 2006. Google ScholarDigital Library
- L. F. Richardson. Weather prediction by numerical process. Cambridge University Press, 2007.Google ScholarCross Ref
- N. I. Sapankevych and R. Sankar. Time series prediction using support vector machines: a survey. Computational Intelligence Magazine, IEEE, 4(2):24--38, 2009. Google ScholarDigital Library
- I. Sutskever, G. E. Hinton, and G. W. Taylor. The Recurrent Temporal Restricted Boltzmann Machine. In Advances in Neural Information Processing Systems, pages 1601--1608, 2009.Google ScholarDigital Library
- C. Voyant, M. Muselli, C. Paoli, and M.-L. Nivet. Numerical Weather Prediction (NWP) and hybrid ARMA/ANN model to predict global radiation. Energy, 39(1):341--355, 2012.Google ScholarCross Ref
Index Terms
- A Deep Hybrid Model for Weather Forecasting
Recommendations
Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningWeather forecasting is usually solved through numerical weather prediction (NWP), which can sometimes lead to unsatisfactory performance due to inappropriate setting of the initial states. In this paper, we design a data-driven method augmented by an ...
XGBoost: A Scalable Tree Boosting System
KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningTree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many ...
ImageNet classification with deep convolutional neural networks
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, ...
Comments