{"type":"ScholarlyArticle","title":"DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data","authors":[{"name":"Asadullah Hill Galib","slug":"asadullah-hill-galib","given":"Asadullah Hill","family":"Galib","affiliation":"Department of Computer Science & Engineering , Michigan State University"},{"name":"Andrew McDonald","slug":"andrew-mcdonald","given":"Andrew","family":"McDonald","affiliation":"Department of Computer Science & Engineering , Michigan State University"},{"name":"Tyler Wilson","slug":"tyler-wilson","given":"Tyler","family":"Wilson","affiliation":"Department of Computer Science & Engineering , Michigan State University"},{"name":"Lifeng Luo","slug":"lifeng-luo","given":"Lifeng","family":"Luo","affiliation":"Department of Geography, Environment, and Spatial Sciences , Michigan State University"},{"name":"Pang-Ning Tan","slug":"pang-ning-tan","given":"Pang-Ning","family":"Tan","affiliation":"Department of Computer Science & Engineering , Michigan State University"}],"abstract":"Accurate forecasting of extreme values in time series is critical due to the significant impact of extreme events on human and natural systems. This paper presents DeepExtrema, a novel framework that combines a deep neural network (DNN) with generalized extreme value (GEV) distribution to forecast the block maximum value of a time series. Implementing such a network is a challenge as the framework must preserve the inter-dependent constraints among the GEV model parameters even when the DNN is initialized. We describe our approach to address this challenge and present an architecture that enables both conditional mean and quantile prediction of the block maxima. The extensive experiments performed on both real-world and synthetic data demonstrated the superiority of DeepExtrema compared to other baseline methods.","doi":"10.24963/ijcai.2022/413","url":"https://ijcai.org/proceedings/2022/413","pdf":"https://ijcai.org/proceedings/2022/0413.pdf","markdown":"https://ijcai.org/proceedings/2022/413.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/413","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":413,"pages":{"first":2980,"last":2986},"keywords":["Data Mining: Mining Spatial and/or Temporal Data","Data Mining: Anomaly/Outlier Detection","Machine Learning: Regression","Machine Learning: Time-series; Data Streams"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986797","length_sec":89,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984940","length_sec":358,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Aliabadi et al., 2020] Majid Moradi Aliabadi, Hajar Emami, Ming Dong, and Yinlun Huang. Attention-based recurrent neural network for multistep-ahead predic- tion of process performance. Computers & Chemical Engineering, 140:106931, 2020.","title":"Attention-based recurrent neural network for multistep-ahead prediction of process performance","authors":"Hajar Majid Moradi Aliabadi, Ming Emami, Yinlun Dong, Huang","year":"2020","venue":"Computers & Chemical Engineering","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bai et al., 2018] Shaojie Bai, J. Zico Kolter, and Vladlen Koltun. An Empirical Evaluation of Generic Convolu- tional and Recurrent Networks for Sequence Modeling. arXiv:1803.01271 [cs], April 2018. arXiv: 1803.01271.","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","authors":"J Zico Shaojie Bai, Vladlen Kolter, Koltun","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bishop, 2006] Christopher M Bishop. Pattern recognition. Springer, New York, 2006.","title":"Pattern recognition","authors":"M Christopher, Bishop","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Coles et al., 2001] Stuart Coles, Joanna Bawa, Lesley Tren- ner, and Pat Dorazio. An introduction to statistical model- ing of extreme values, volume 208. Springer, 2001.","title":"An introduction to statistical modeling of extreme values","authors":"Stuart Coles, Joanna Bawa, Lesley Trenner, Pat Dorazio","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding et al., 2019] Daizong Ding, Mi Zhang, Xudong Pan, Min Yang, and Xiangnan He. Modeling extreme events in time series prediction. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discov- ery & Data Mining, pages 1114-1122, 2019.","title":"Modeling extreme events in time series prediction","authors":"Ding","year":"2019","venue":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kharin and Zwiers, 2005] Viatcheslav V Kharin and Fran- cis W Zwiers. Estimating extremes in transient climate change simulations. Journal of Climate, 18(8):1156-1173, 2005.","title":"Estimating extremes in transient climate change simulations","authors":"V Viatcheslav, Francis W Kharin, Zwiers","year":"2005","venue":"Journal of Climate","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Landsea and Franklin, 2013] Christopher W Landsea and James L Franklin. Atlantic hurricane database uncer- tainty and presentation of a new database format. Monthly Weather Review, 141(10):3576-3592, 2013.","title":"Atlantic hurricane database uncertainty and presentation of a new database format","authors":"W Christopher, James L Landsea, Franklin","year":"2013","venue":"Monthly Weather Review","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Laptev et al., 2017] Nikolay Laptev, Jason Yosinski, Li Er- ran Li, and Slawek Smyl. Time-series extreme event fore- casting with neural networks at uber. In International con- ference on machine learning, volume 34, pages 1-5, 2017.","title":"Time-series extreme event forecasting with neural networks at uber","authors":"Nikolay Laptev, Jason Yosinski, Li Erran Li, Slawek Smyl","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Masum et al., 2018] Shamsul Masum, Ying Liu, and John Chiverton. Multi-step time series forecasting of electric load using machine learning models. In International con- ference on artificial intelligence and soft computing, pages 148-159. Springer, 2018.","title":"Multi-step time series forecasting of electric load using machine learning models","authors":"Shamsul Masum, Ying Liu, John Chiverton","year":"2018","venue":"International conference on artificial intelligence and soft computing","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Muthukumar, 2017] J Muthukumar. Weather dataset. https: //www.kaggle.com/muthuj7/weather-dataset, Dec 2017. Accessed: 2021-09-30.","title":"Weather dataset","authors":"Muthukumar","year":"2017","venue":null,"doi":null,"url":"https://www.kaggle.com/muthuj7/weather-dataset","internal_url":null},{"position":11,"raw":"[Peng et al., 2018] Chenglei Peng, Yang Li, Yao Yu, Yu Zhou, and Sidan Du. Multi-step-ahead host load pre- diction with gru based encoder-decoder in cloud comput- ing. In 2018 10th International Conference on Knowledge and Smart Technology (KST), pages 186-191. IEEE, 2018.","title":"Multi-step-ahead host load prediction with gru based encoder-decoder in cloud computing","authors":"Chenglei Peng, Yang Li, Yao Yu, Yu Zhou, Sidan Du","year":"2018","venue":"10th International Conference on Knowledge and Smart Technology (KST)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Polson and Sokolov, 2020] Michael Polson and Vadim Sokolov. Deep learning for energy markets. Applied Stochastic Models in Business and Industry, 36(1):195- 209, 2020.","title":"Deep learning for energy markets","authors":"Sokolov Polson, Michael Polson, Vadim Sokolov","year":"2020","venue":"Applied Stochastic Models in Business and Industry","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ratnam et al., 2017] Elizabeth L Ratnam, Steven R Weller, Christopher M Kellett, and Alan T Murray. Residential load and rooftop pv generation: an australian distribution network dataset. International Journal of Sustainable En- ergy, 36(8):787-806, 2017.","title":"Residential load and rooftop pv generation: an australian distribution network dataset","authors":"Elizabeth L Ratnam, Steven R Weller, Christopher M Kellett, Alan T Murray","year":"2017","venue":"International Journal of Sustainable Energy","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Sagheer and Kotb, 2019] Alaa Sagheer and Mostafa Kotb. Time series forecasting of petroleum production using deep lstm recurrent networks. Neurocomputing, 323:203- 213, 2019.","title":"Time series forecasting of petroleum production using deep lstm recurrent networks","authors":"Kotb ; Sagheer, Alaa Sagheer, Mostafa Kotb","year":"2019","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Smith, 1985] Richard L. Smith. Maximum likelihood es- timation in a class of nonregular cases. Biometrika, 72(1):67-90, 1985.","title":"Maximum likelihood estimation in a class of nonregular cases","authors":"Richard L Smith","year":"1985","venue":"Biometrika","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[US GAO, 2020] US GAO. Natural disasters: Economic ef- fects of hurricanes katrina, sandy, harvey, and irma. https: //www.gao.gov/products/gao-20-633r, 2020. Accessed: 2021-04-09.","title":"Natural disasters: Economic effects of hurricanes katrina, sandy, harvey, and irma","authors":null,"year":"2020","venue":null,"doi":null,"url":"https://www.gao.gov/products/gao-20-633r,2020","internal_url":null},{"position":17,"raw":"[Wang and Tan, 2021] Ding Wang and Pang-Ning Tan. Jo- han: A joint online hurricane trajectory and intensity fore- casting framework. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 1677-1685, 2021.","title":"Johan: A joint online hurricane trajectory and intensity forecasting framework","authors":"Wang, Tan ; ] Ding Wang, Pang-Ning Tan","year":"2021","venue":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2020] Bin Wang, Tianrui Li, Zheng Yan, Guangquan Zhang, and Jie Lu. Deeppipe: A distribution- free uncertainty quantification approach for time series forecasting. Neurocomputing, 397:11-19, 2020.","title":"Deeppipe: A distributionfree uncertainty quantification approach for time series forecasting","authors":"Wang","year":"2020","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wilson et al., 2022] Tyler Wilson, Pang-Ning Tan, and Lifeng Luo. Deepgpd: A deep learning approach for mod- eling geospatio-temporal extreme events. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022.","title":"Deepgpd: A deep learning approach for modeling geospatio-temporal extreme events","authors":"Tyler Wilson, Pang-Ning Tan, Lifeng Luo","year":"2022","venue":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yang et al., 2015] Jianbo Yang, Minh Nhut Nguyen, Phyo Phyo San, Xiao Li Li, and Shonali Krishnaswamy. Deep convolutional neural networks on multichannel time series for human activity recognition. In Twenty-fourth international joint conference on artificial intelligence, 2015.","title":"Deep convolutional neural networks on multichannel time series for human activity recognition","authors":"Jianbo Yang, Minh Nhut Nguyen, Phyo Phyo San, Xiao Li Li, Shonali Krishnaswamy","year":"2015","venue":"Twenty-fourth international joint conference on artificial intelligence","doi":null,"url":null,"internal_url":"/proceedings/2015/561"},{"position":21,"raw":"[Zhang et al., 2019] Xuan Zhang, Xun Liang, Aakas Zhiyuli, Shusen Zhang, Rui Xu, and Bo Wu. At-lstm: An attention-based lstm model for financial time series pre- diction. In IOP Conference Series: Materials Science and Engineering, volume 569, page 052037. IOP Publishing, 2019.","title":"At-lstm: An attention-based lstm model for financial time series prediction","authors":"Xuan Zhang, Xun Liang, Aakas Zhiyuli, Shusen Zhang, Rui Xu, Bo Wu","year":"2019","venue":"IOP Conference Series: Materials Science and Engineering","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhao et al., 2017] Bendong Zhao, Huanzhang Lu, Shangfeng Chen, Junliang Liu, and Dongya Wu. Convolutional neural networks for time series classifica- tion. Journal of Systems Engineering and Electronics, 28(1):162-169, 2017.","title":"Convolutional neural networks for time series classification","authors":"Zhao","year":"2017","venue":"Journal of Systems Engineering and Electronics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}