ABSTRACT
Hurricanes constitute major natural disasters that lead to destruction and loss of lives. Therefore, to reduce economic loss and to save human lives, an accurate forecast of hurricane occurrences is crucial. Despite the availability of data and advanced forecasting techniques, there is a need for effective methods with higher accuracy of prediction. We propose a sparse Recurrent Neural Network (RNN) with flexible topology for trajectory prediction of the Atlantic hurricanes. Topology of the RNN along with the strength of the connections are evolved by a customized Genetic Algorithm. The network is particularly suitable for modeling of hurricanes which have complex systems with unknown dynamics. For prediction of the future trajectories of a target hurricane, the Dynamic Time Warping (DTW) distances between direction of the target hurricane over time, and other hurricanes in the dataset are determined and compared. The most similar hurricanes to the target hurricane are then used for training of the network. Comparisons between the actual tracks of the hurricanes DEAN, SANDY, ISSAC and HUMBERTO, and the generated predictions by the sparse RNN for one and two steps ahead of time show that our approach is quite promising for this aim.
- Atlantic tropical storm tracking by year. http://weather.unisys.com/hurricane/atlantic/.Google Scholar
- National hurricane center, latitude/longitude distance calculator. http://www.nhc.noaa.gov/gccalc.shtml.Google Scholar
- National hurricane center, track and intensity models. http://www.nhc.noaa.gov/modelsummary.shtml.Google Scholar
- J. Aach and G. M. Church. Aligning gene expression time series with time warping algorithms. Bioinformatics, 17(6):495--508, 2001.Google Scholar
- D. J. Berndt and J. Clifford. Using dynamic time warping to find patterns in time series. In KDD workshop, volume 10, pages 359--370. Seattle, WA, 1994.Google ScholarDigital Library
- D. Dasgupta and S. Forrest. Novelty detection in time series data using ideas from immunology. In Proceedings of the international conference on intelligent systems, pages 82--87, 1996.Google Scholar
- J. J. R. Diez and C. J. A. González. Applying boosting to similarity literals for time series classification. In Multiple Classifier Systems, pages 210--219. Springer, 2000. Google ScholarDigital Library
- J. L. Elman. Finding structure in time. Cognitive Science, 14(2):179--211, 1990.Google ScholarCross Ref
- S. B. Goldenberg, C. W. Landsea, A. M. Mestas-Nu\ nez, and W. M. Gray. The recent increase in atlantic hurricane activity: Causes and implications. Science, 293(5529):474--479, 2001.Google ScholarCross Ref
- S. G. Gopalakrishnan, S. Goldenberg, T. Quirino, X. Zhang, F. Marks Jr, K.-S. Yeh, R. Atlas, and V. Tallapragada. Toward improving high-resolution numerical hurricane forecasting: Influence of model horizontal grid resolution, initialization, and physics. Weather and Forecasting, 27(3):647--666, 2012.Google ScholarCross Ref
- M. Gorji Sefidmazgi and M. Farrokhi. Online Calibration of Inertial Sensors Using Kalman Filters and Artificial Neural Networks. In 17th Iranian Conference on Electrical Engineering (ICEE), volume 7, pages 249--253, 2009.Google Scholar
- M. Gorji Sefidmazgi, M. Moradi Kordmahalleh, and A. Homaifar. Identification of switched models in non-stationary time series based on coordinate-descent and genetic algorithm. In Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, GECCO Companion '15, pages 1399--1400, New York, NY, USA, 2015. ACM. Google ScholarDigital Library
- M. Gorji Sefidmazgi, M. Sayemuzzaman, A. Homaifar, M. K. Jha, and S. Liess. Trend analysis using non-stationary time series clustering based on the finite element method. Nonlinear Processes in Geophysics, 21(3):605--615, 2014.Google ScholarCross Ref
- T. M. Hall and S. Jewson. Statistical modelling of north atlantic tropical cyclone tracks. Tellus A, 59(4):486--498, 2007.Google ScholarCross Ref
- M. Islam, A. Sattar, F. Amin, X. Yao, and K. Murase. A new adaptive merging and growing algorithm for designing artificial neural networks. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 39(3):705--722, June 2009. Google ScholarDigital Library
- M. I. Jordan. Supervised learning and systems with excess degrees of freedom. Report, University of Massachusetts, 1988. Google ScholarDigital Library
- S. Kang and C. Isik. Partially connected feedforward neural networks structured by input types. IEEE transactions on neural networks, 16(1):175--184, 2005. Google ScholarDigital Library
- E. Keogh and C. A. Ratanamahatana. Exact indexing of dynamic time warping. Knowledge and information systems, 7(3):358--386, 2005.Google Scholar
- H. S. Kim, C. H. Ho, J. H. Kim, and P. S. Chu. Track-pattern-based model for seasonal prediction of tropical cyclone activity in the western north pacific. Journal of Climate, 25(13):4660--4678, 2012.Google ScholarCross Ref
- H. S. Kim, J. H. Kim, C. H. Ho, and P. S. Chu. Pattern classification of typhoon tracks using the fuzzy c-means clustering method. Journal of Climate, 24(2):488--508, 2011.Google ScholarCross Ref
- M. M. Kordmahalleh, A. Homaifar, and D. Bkc. Hierarchical multi-label gene function prediction using adaptive mutation in crowding niching. In Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on, pages 1--6, Nov 2013.Google ScholarCross Ref
- M. M. Kordmahalleh, M. G. Sefidmazgi, and A. Homaifar. A bilevel parameter tuning strategy of partially connected anns. In 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pages 793--798, Dec 2015.Google ScholarCross Ref
- M. M. Kordmahalleh, M. G. Sefidmazgi, A. Homaifar, A. Karimoddini, A. Guiseppi-Elie, and J. L. Graves. Delayed and hidden variables interactions in gene regulatory networks. In Bioinformatics and Bioengineering (BIBE), 2014 IEEE International Conference on, pages 23--29, Nov 2014. Google ScholarDigital Library
- T. N. Krishnamurti, C. Kishtawal, Z. Zhang, T. LaRow, D. Bachiochi, E. Williford, S. Gadgil, and S. Surendran. Multimodel ensemble forecasts for weather and seasonal climate. Journal of Climate, 13(23):4196--4216, 2000.Google ScholarCross Ref
- R. S. Lee and J. N. Liu. Tropical cyclone identification and tracking system using integrated neural oscillatory elastic graph matching and hybrid rbf network track mining techniques. Neural Networks, IEEE Transactions on, 11(3):680--689, 2000. Google ScholarDigital Library
- S. Macpherson, L. Garand, J. Aparicio, M. Buehner, G. Deblonde, M. Charron, M. Roch, C. Charette, and A. Beaulne. Recent developments in assimilation of satellite data in the msc 4d-var analysis and forecast system. Channels, 4:10.Google Scholar
- M. Moradi Kordmahalleh, M. Gorji Sefidmazgi, A. Homaifar, D. B. KC, and A. Guiseppi-Elie. Time-series forecasting with evolvable partially connected artificial neural network. In Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation, GECCO Comp '14, pages 79--80, New York, NY, USA, 2014. ACM. Google ScholarDigital Library
- T. S. Rao, S. S. Rao, and C. R. Rao. Time Series Analysis: Methods and Applications. Elsevier, 2012.Google Scholar
- O. S. Rozanova, J. L. Yu, and C. K. Hu. Typhoon eye trajectory based on a mathematical model: Comparing with observational data. Nonlinear Analysis: Real World Applications, 11(3):1847--1861, 2010.Google ScholarCross Ref
- Y. Su, S. Chelluboina, M. Hahsler, and M. Dunham. A new data mining model for hurricane intensity prediction. In Data Mining Workshops (ICDMW), 2010 IEEE International Conference on, pages 98--105, Dec 2010. Google ScholarDigital Library
- G. A. Vecchi, M. Zhao, H. Wang, G. Villarini, A. Rosati, A. Kumar, I. M. Held, and R. Gudgel. Statistical-dynamical predictions of seasonal north atlantic hurricane activity. Monthly Weather Review, 139(4):1070--1082, 2011.Google ScholarCross Ref
- Y. Wang, W. Zhang, and W. Fu. Back propogation (bp)-neural network for tropical cyclone track forecast. In Geoinformatics, 2011 19th International Conference on, pages 1--4. IEEE, 2011.Google ScholarCross Ref
- J. M. Zamarre\ no and P. Vega. State space neural network. properties and application. Neural Networks, 11(6):1099--1112, 1998. Google ScholarDigital Library
- L. ZOU, A. REN, F. XU, and X. ZHANG. Typhoon track forecasting based on gis spatial analyses. Journal of Tsinghua University (Science and Technology), 12:002, 2008.Google Scholar
Index Terms
- A Sparse Recurrent Neural Network for Trajectory Prediction of Atlantic Hurricanes
Recommendations
Landslide Deformation Prediction Based on Recurrent Neural Network
Landslide deformation prediction has significant practical value that can provide guidance for preventing the disaster and guarantee the safety of people's life and property. In this paper, a method based on recurrent neural network (RNN) for landslide ...
Multiresolution-based bilinear recurrent neural network
PAKDD'07: Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data miningA Multiresolution-based BiLinear Recurrent Neural Network (MBLRNN) is proposed in this paper. The proposed M-BLRNN is based on the BLRNN that has been proven to have robust abilities in modeling and predicting time series. The learning process is ...
Attention-based Recurrent Neural Network for Urban Vehicle Trajectory Prediction
AbstractAs the number of various positioning sensors and location-based devices increase, a huge amount of spatial and temporal information data is collected and accumulated. These data are expressed as trajectory data by connecting the data points in ...
Comments