Abstract
Deep neural networks (DNN) have gained remarkable success on many rainfall predictions tasks in recent years. However, the performance of DNN highly relies upon the hyperparameter setting. In order to design DNNs with the best performance, extensive expertise in both the DNN and the problem domain under investigation is required. But many DNN users have not met this requirement. Therefore, it is difficult for the users who have no extensive expertise in DNN to design optimal DNN architectures for their rainfall prediction problems that is to solve. In this paper, we proposed a novel automatic hyperparameters optimization method for DNN by using an improved Gene Expression Programming. The proposed method can automatically optimize the hyperparameters of DNN for precipitation modeling and prediction. Extensive experiments are conducted with three real precipitation datasets to verify the performance of the proposed algorithm in terms of four metrics, including MAE, MSE, RMSE, and R-Squared. The results show that: 1) the DNN optimized by the proposed method outperforms the existing precipitation prediction methods including Multiple Linear Regression (MLR), Back Propagation (BP), Support Vector Machine (SVM), Random Forest (RF) and DNN; 2) the proposed DNN hyperparameter optimization method outperforms state-of-the-art DNN hyperparameter optimization methods, including Genetic Algorithm, Bayes Search, Grid Search, Randomized Search, and Quasi Random Search.
Similar content being viewed by others
References
He X, Guan H, Zhang X, Simmons CT (2014) A wavelet-based multiple linear regression model for forecasting monthly rainfall. Int J Climatol 34(6):1898–1912
Kumar A, Tyagi N (2016) Comparative analysis of backpropagation and RBF neural network on monthly rainfall prediction. In: IEEE international conference on inventive computation technologies (ICICT), pp 1-6
Panaligan D, Razon JA, Caro J, et al (2016) Using machine learning to provide rapid rainfall forecasts based on radar-derived data. In: workshop on computing: Theory & Practice (WCTP), pp 117-131
Yang TC, Yu PS, Lin KH, Kuo CM, Tseng HW (2018) Predictor selection method for the construction of support vector machine (SVM)-based typhoon rainfall forecasting models using a non-dominated sorting genetic algorithm. Meteorol Appl 25(4):510–522
Meyer H, Kühnlein M, Appelhans T, Nauss T (2016) Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals. Atmos Res 169:424–433
Jia Z, Guan Z, Liu Z, Yang DM (2020) Influence of short-term rainfall forecast error on flood forecast operation: a risk assessment based on Bayesian theory. Hum Ecol Risk Assess 2020(2):1–15
Kim S, Seo Y, Lee CJ (2016) Modeling of rainfall by combining neural computation and wavelet technique. Procedia Eng 154:1231–1236
Dufek AS, Augusto DA, Dias PLS, Barbosa HJC (2017) Application of evolutionary computation on ensemble forecast of quantitative precipitation. Comput Geosci 106:139–149
Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. ieee. Computational intelligenCe magazine 13(3):55–75
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Petersen S (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533
Zhang R, Isola P, Efros AA, et al (2016) Colorful image colorization. In: european conference on computer vision, pp 649-666
Vinyals O, Toshev A, Bengio S, et al (2015) Show and tell: a neural image caption generator. In: computer vision and pattern recognition, pp 3156-3164
Shen D, Wu G, Suk H et al (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19(1):221–248
Liu Y, Racah E, Correa J, Khosrowshahi A, Lavers D, Kunkel K, Collins W (2016) Application of deep convolutional neural networks for detecting extreme weather in climate datasets. Computer Vision and Pattern Recognition arXiv 1605:01156
Grover A, Kapoor A, Horvitz E, et al (2015) A deep hybrid model for weather forecasting. In: knowledge discovery and data mining, pp 379-386
Dhar D, Bagchi S, Kayal CK, Mukherjee S, Chatterjee S (2019) Quantitative rainfall prediction: deep neural network-based approach. In: springer proceedings of international ethical hacking conference 2018 Singapore, pp. 455-463
Cramer S, Kampouridis M, Freitas AA, Alexandridis AK (2017) An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives. Expert Syst Appl 85(18):169–181
Akiba T, Sano S, Yanase T, et al (2019) Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 2623-2631
Feurer M, Springenberg JT, Hutter F, el at (2015) Initializing bayesian hyperparameter optimization via meta-learning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 1128–1135
Koch P, Golovidov O, Gardner S, et al (2018) Autotune: a derivative-free optimization framework for hyperparameter tuning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 443-452
Luo R, Tian F, Qin T, et al (2018) Neural architecture optimization. In: neural information processing systems, pp 7816-7827
Ying, C, Klein, A, Real E, Christiansen E, Murphy K, Hutter F (2019) NAS-Bench-101: towards reproducible neural architecture search. https://doi.org/10.1007/978-3-030-05318-5_3
Darwish A, Hassanien AE, Das S et al (2020) A survey of swarm and evolutionary computing approaches for deep learning. Artif Intell Rev 53(3):1767–1812
Sun YN, Xue B, Zhang M, Yen GG (2020) Evolving deep convolutional neural networks for image classification. IEEE Trans Evol Comput 24(2):394–407
Sun YN, Xue B, Zhang M, Yen GG (2020) Completely automated CNN architecture design based on blocks. IEEE transactions on neural networks and learning systems 31(4):1242–1254
Suganuma M, Shirakawa S, Nagao T, et al (2017) A genetic programming approach to designing convolutional neural network architectures. In: genetic and evolutionary computation conference, pp 497-504
Wang B, Sun Y, Xue B, et al (2019) A hybrid GA-PSO method for evolving architecture and short connections of deep convolutional neural networks. In: pacific rim international conference on artificial intelligence, pp 650-663
Xie L, Yuille A (2017) Genetic CNN. In: IEEE international conference on computer vision (ICCV), pp 1379-1388
Sun Y, Xue B, Zhang M, et al. (2020) Automatically designing CNN architectures using the genetic Algorithm for image classification[J]. IEEE Transactions on Cybernetics, pp (99):1–15
Hoang N, Tien Bui D (2018) Spatial prediction of rainfall-induced shallow landslides using gene expression programming integrated with GIS: a case study in Vietnam. Nat Hazards 92(3):1871–1887
Peng Y, Changan Y, Jian WC (2010) Multicellular gene expression programming algorithm for function optimization. Control Theory & Applications 27(1):1585–1589
Zhong J, Ong Y, Cai W (2016) Self-learning gene expression programming. IEEE Trans Evol Comput 20(1):65–80
Armaghani DJ, Faradonbeh RS, Rezaei H, Rashid ASA, Amnieh HB (2018) Settlement prediction of the rock-socketed piles through a new technique based on gene expression programming. Neural Comput & Applic 29(11):1115–1125
Faradonbeh RS, Armaghani DJ, Amnieh HB, Mohamad ET (2018) Prediction and minimization of blast-induced flyrock using gene expression programming and firefly algorithm. Neural Comput & Applic 29(6):269–281
Zhong J, Feng L, Cai W et al (2019) Multifactorial genetic programming for symbolic regression problems. IEEE Transactions on Systems, Man, and Cybernetics 25(7):1–14
Nazari A (2019) Application of gene expression programming to predict the compressive damage of lightweight aluminosilicate geopolymer. Neural Comput & Applic 31(2):767–776
Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Complex Systems 13(2):87–129
Deng CY, Peng YZ, Li HY, Gong DQ, Zhang H, Liu ZP (2019) A seft-adaptive multicellular GEP algorithm based on fuzzy control for function optimization. arXiv:2634575
Peng Y, Deng C, Li H, et al (2019) Precipitation modeling and prediction based on fuzzy-control Multicellularular gene expression programming and wavelet transform. In: international conference on intelligent computing, pp 81-92
Ramachandran P, Zoph B, Le QV (2018) Searching for activation functions. International conference on learning representations, arXiv:1710.05941
Dong X, Shen J, Wang W, et al (2018) Hyperparameter optimization for tracking with continuous deep Q-Learning. In: computer vision and pattern recognition, pp 518-527
Lorraine J, Duvenaud D (2018) Stochastic hyperparameter optimization through hypernetworks. arXiv preprint arXiv:1802.09419, 2018
Srivastava N, Hinton GE, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Nazreen PM, Ramakrishnan AG (2018) DNN based speech enhancement for unseen noises using Monte Carlo dropout. In: international conference on signal processing and communication systems, pp 1-6
Komer B, Bergstra J, Eliasmith C (2019) Hyperopt-Sklearn. Springer Cham, Automated Machine Learning, In, pp 97–111
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China Grant #61562008 and #62006051, the Natural Science Foundation of Guangxi Zhuang Autonomous Region Grant #2017GXNSFAA198228 and #2017GXNSFBA198153 and #2018GXNSFAA294079, the Project of Scientific Research and Technology Development in Guangxi Grant #AA18118047 and #AD18126015. Thanks to the support by the BAGUI Scholar Program of Guangxi Zhuang Autonomous Region of China. Yuzhong Peng and Daoqing Gong contributed equally to this work and should be considered co-first authors. Yuzhong Peng and Hao Zhang are the co-corresponding author.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interests
There are no potential competing interests in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Rights and permissions
About this article
Cite this article
Peng, Y., Gong, D., Deng, C. et al. An automatic hyperparameter optimization DNN model for precipitation prediction. Appl Intell 52, 2703–2719 (2022). https://doi.org/10.1007/s10489-021-02507-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02507-y