# Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

- We proposed a hybrid framework of BLSTM and GRU for rainfall prediction.
- No prior deep learning techniques have been used on the dataset. The results of this paper will serve as the baseline for future researchers.
- A detailed analysis of the proposed framework is presented through extensive experiments.
- Finally, a comparison with different deep learning models is also discussed.

## 2. Literature Review

## 3. Proposed System

#### 3.1. Dataset Description

#### 3.2. Data Preprocessing

#### 3.3. Evaluation Metrics

#### 3.4. BLSTM

#### 3.5. GRU

#### 3.6. BLSTM-GRU Model

## 4. Experiment and Results

#### 4.1. Result Summary

#### 4.2. Comparative Analysis

## 5. Conclusions and Future Work

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Toth, E.; Brath, A.; Montanari, A. Comparison of short-term rainfall prediction models for real-time flood forecasting. J. Hydrol.
**2000**, 239, 132–147. [Google Scholar] [CrossRef] - Jia, Y.; Zhao, H.; Niu, C.; Jiang, Y.; Gan, H.; Xing, Z.; Zhao, X.; Zhao, Z. A webgis-based system for rainfall-runoff prediction and real-time water resources assessment for beijing. Comput. Geosci.
**2009**, 35, 1517–1528. [Google Scholar] [CrossRef] - Walcott, S.M. Thimphu. Cities
**2009**, 26, 158–170. [Google Scholar] [CrossRef] - Abhishek, K.; Kumar, A.; Ranjan, R.; Kumar, S. A rainfall prediction model using artificial neural network. In Proceedings of the Control and System Graduate Research Colloquium (ICSGRC), Shah Alam, Malaysia, 16–17 July 2012; pp. 82–87. [Google Scholar]
- Darji, M.P.; Dabhi, V.K.; Prajapati, H.B. Rainfall forecasting using neural network: A survey. In Proceedings of the 2015 International Conference on Advances in Computer Engineering and Applications (ICACEA), Ghaziabad, India, 19–20 March 2015; pp. 706–713. [Google Scholar]
- Kim, J.-H.; Kim, B.; Roy, P.P.; Jeong, D.-M. Efficient facial expression recognition algorithm based on hierarchical deep neural network structure. IEEE Access
**2019**, 7, 41273–41285. [Google Scholar] [CrossRef] - Mukherjee, S.; Saini, R.; Kumar, P.; Roy, P.P.; Dogra, D.P.; Kim, B.G. Fight detection in hockey videos using deep network. J. Multimed. Inf. Syst.
**2017**, 4, 225. [Google Scholar] - Anh, D.T.; Dang, T.D.; Van, S.P. Improved rainfall prediction using combined pre-processing methods and feed-forward neural networks. J—Multidiscip. Sci. J.
**2019**, 2, 65. [Google Scholar] - Mesinger, F.; Arakawa, A. Numerical Methods Used in Atmospheric Models; Global Atmospheric Research Program World Meteorological Organization: Geneva, Switzerland, 1976. [Google Scholar]
- Nayak, D.R.; Mahapatra, A.; Mishra, P. A survey on rainfall prediction using artificial neural network. Int. J. Comput. Appl.
**2013**, 72. [Google Scholar] - Hung, N.Q.; Babel, M.S.; Weesakul, S.; Tripathi, N.K. An artificial neural network model for rainfall forecasting in bangkok, thailand. Hydrol. Earth Syst. Sci.
**2009**, 13, 1413–1425. [Google Scholar] [CrossRef][Green Version] - Luk, K.C.; Ball, J.E.; Sharma, A. An application of artificial neural networks for rainfall forecasting. Math. Comput. Model.
**2001**, 33, 683–693. [Google Scholar] [CrossRef] - Kashiwao, T.; Nakayama, K.; Ando, S.; Ikeda, K.; Lee, M.; Bahadori, A. A neural network-based local rainfall prediction system using meteorological data on the internet: A case study using data from the japan meteorological agency. Appl. Soft Comput.
**2017**, 56, 317–330. [Google Scholar] [CrossRef] - Hernández, E.; Sanchez-Anguix, V.; Julian, V.; Palanca, J.; Duque, A.N. Rainfall prediction: A deep learning approach. In Lecture Notes in Computer Science, Proceedings of the International Conference on Hybrid Artificial Intelligence Systems, Seville, Spain, 18–20 April 2016; Springer: Cham, Switzerland, 2016; pp. 151–162. [Google Scholar]
- Khajure, S.; Mohod, S.W. Future weather forecasting using soft computing techniques. Procedia Comput. Sci.
**2016**, 78, 402–407. [Google Scholar] [CrossRef][Green Version] - Wahyuni, I.; Mahmudy, W.F.; Iriany, A. Rainfall prediction in tengger region indonesia using tsukamoto fuzzy inference system. In Proceedings of the International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Yogyakarta, Indonesia, 23–24 August 2016; pp. 130–135. [Google Scholar]
- Mishra, N.; Soni, H.K.; Sharma, S.; Upadhyay, A.K. Development and analysis of artificial neural network models for rainfall prediction by using time-series data. Int. J. Intell. Syst. Appl.
**2018**, 10, 16. [Google Scholar] [CrossRef] - Hardwinarto, S.; Aipassa, M. Rainfall monthly prediction based on artificial neural network: A case study in tenggarong station, east kalimantan-indonesia. Procedia Comput. Sci.
**2015**, 59, 142–151. [Google Scholar] - Kumar, A.; Tyagi, N. Comparative analysis of backpropagation and rbf neural network on monthly rainfall prediction. In Proceedings of the 2016 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 26–27 August 2016; Volume 1, pp. 1–6. [Google Scholar]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput.
**1997**, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed] - Cho, K.; Van Merriënboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv
**2014**, arXiv:1406.1078. [Google Scholar] - Sutskever, I.; Vinyals, O.; Le, Q.V. Sequence to sequence learning with neural networks. In Proceedings of the 2014 Neural Information Processing Systems(NIPS), Montreal, QC, Canada, 8–13 December 2014; pp. 3104–3112. [Google Scholar]
- Salman, A.G.; Kanigoro, B.; Heryadi, Y. Weather forecasting using deep learning techniques. In Proceedings of the 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Depok, Indonesia, 10–11 October 2015; pp. 281–285. [Google Scholar]
- Qiu, M.; Zhao, P.; Zhang, K.; Huang, J.; Shi, X.; Wang, X.; Chu, W. A short-term rainfall prediction model using multi-task convolutional neural networks. In Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA, 18–21 November 2017; pp. 395–404. [Google Scholar]
- Wheater, H.S.; Isham, V.S.; Cox, D.R.; Chandler, R.E.; Kakou, A.; Northrop, P.J.; Oh, L.; Onof, C.; Rodriguez-Iturbe, I. Spatial-temporal rainfall fields: Modelling and statistical aspects. Hydrol. Earth Syst. Sci. Discuss.
**2000**, 4, 581–601. [Google Scholar] [CrossRef][Green Version] - Hartigan, J.A.; Wong, M.A. Algorithm as 136: A k-means clustering algorithm. J. R. Stat. Soc. Ser. Appl. Stat.
**1979**, 28, 100. [Google Scholar] [CrossRef] - Kim, S.; Hong, S.; Joh, M.; Song, S. Deeprain: Convlstm network for precipitation prediction using multichannel radar data. arXiv
**2017**, arXiv:1711.02316. [Google Scholar] - Chao, Z.; Pu, F.; Yin, Y.; Han, B.; Chen, X. Research on real-time local rainfall prediction based on mems sensors. J. Sens.
**2018**, 2018, 6184713. [Google Scholar] [CrossRef] - Graves, A.; Liwicki, M.; Fernández, S.; Bertolami, R.; Bunke, H.; Schmidhuber, J. A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach.
**2009**, 31, 855–868. [Google Scholar] [CrossRef][Green Version] - Saini, R.; Kumar, P.; Kaur, B.; Roy, P.P.; Prosad Dogra, D.; Santosh, K.C. Kinect sensor-based interaction monitoring system using the blstm neural network in healthcare. Int. J. Mach. Learn. Cybern.
**2019**, 10, 2529–2540. [Google Scholar] [CrossRef] - Mukherjee, S.; Ghosh, S.; Ghosh, S.; Kumar, P.; Pratim Roy, P. Predicting video-frames using encoder-convlstm combination. In Proceedings of the ICASSP 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12–17 May 2019; pp. 2027–2031. [Google Scholar]
- Mittal, A.; Kumar, P.; Roy, P.P.; Balasubramanian, R.; Chaudhuri, B.B. A modified lstm model for continuous sign language recognition using leap motion. IEEE Sens. J.
**2019**, 19, 7056–7063. [Google Scholar] [CrossRef] - Kumar, P.; Mukherjee, S.; Saini, R.; Kaushik, P.; Roy, P.P.; Dogra, D.P. Multimodal gait recognition with inertial sensor data and video using evolutionary algorithm. IEEE Trans. Fuzzy Syst.
**2018**, 27, 956. [Google Scholar] [CrossRef] - Cui, Z.; Ke, R.; Wang, Y. Deep bidirectional and unidirectional lstm recurrent neural network for network-wide traffic speed prediction. arXiv
**2018**, arXiv:1801.02143. [Google Scholar] - Althelaya, K.A.; El-Alfy, E.S.M.; Mohammed, S. Evaluation of bidirectional lstm for short-and long-term stock market prediction. In Proceedings of the 2018 9th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan, 3–5 April 2018; pp. 151–156. [Google Scholar]
- Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation OSDI, Savannah, GA, USA, 2–4 November 2016; Volume 16, pp. 265–283. [Google Scholar]
- Prechelt, L. Early stopping-but when? In Neural Networks: Tricks of the Trade; Springer: Berlin/Heidelberg, Germany, 1998; pp. 55–69. [Google Scholar]
- Kim, Y. Convolutional neural networks for sentence classification. arXiv
**2014**, arXiv:1408.5882. [Google Scholar] - Yang, J.; Nguyen, M.N.; San, P.P.; Li, X.; Krishnaswamy, S. Deep convolutional neural networks on multichannel time series for human activity recognition. Ijcai
**2015**, 15, 3995–4001. [Google Scholar] - Zhao, B.; Lu, H.; Chen, S.; Liu, J.; Wu, D. Convolutional neural networks for time series classification. J. Syst. Eng. Electron.
**2017**, 28, 162–169. [Google Scholar] [CrossRef]

**Figure 1.**The proposed model is composed of 7 layers including the input and output layers. The embedding is generated by the Bidirectional Long Short Term Memory (BLSTM) and Gated Recurrent Unit (GRU) layer. The batch normalization is used for normalizing the data, and the dense layer performs the prediction.

**Figure 2.**Map of Bhutan showing major river basins and the annual precipitation (mm). The study area is indicated in the legend.

**Figure 4.**Data preprocessing. The data are preprocessed in 6 stages with the arrowheads showing the flow of data.

**Figure 5.**Many (12) to One LSTM utilized in the experiment. Each sample of data contains 12 time-steps of previous data. We used 12 months of previous data to predict the rainfall of the next month (n + 1).

**Figure 6.**RMSE and MSE values of 6 existing models including linear regression and the proposed model. It is clear from the figure that our model outperformed the existing models for the same task.

**Figure 7.**The plots of actual monthly rainfall values over Simtokha collected from NCHM and predicted rainfall values for the years 2016 and 2017, where the x-axis and y-axis represent months and monthly rainfall values (scaled) respectively. The blue line shows the actual values and the orange line shows the predicted values. Subfigure ‘a’ shows that CNN is not able to predict the peak monthly rainfall values correctly. Results of recurrent neural networks shown by subfigure ‘b’, ‘c’ and ‘d’ are better than that of MLP (subfigure ‘e’). Subfigure ‘f’ shows that the proposed model is able to generalize better and gives the best output.

**Figure 9.**Pearson Correlation Coefficient values of 5 existing deep learning models and our proposed model. The score of the proposed model was the highest among the models.

Author & Year | Region (Global or Local) | Daily- Monthly- Yearly | Types of NN | Rainfall Predicting Variables | Accuracy Measure |
---|---|---|---|---|---|

Luk et al. [12] | Western Sydney | 15 min rainfall prediction | MLFN, PRNN, TDNN | NA | NMSE |

Huang et al. [11] | Bangkok | 4 years of hourly data from 1997–2003 | MLP and FFNN | NA | Efficiency index (EI) |

Abhishek et al. [4] | Karnataka, India | 8 months of data from 1960 to 2010 | BPFNN, BPA, LRN and CBP | Average humidity and average wind speed | MSE |

Nayak et al. [10] | Survey Paper | NA | ANN | NA | NA |

Darjee et al. [5] | Survey Paper | Monthly, Yearly | ANN, (FFNN, RNN, TDNN) | Maximum and minimum temperatures | NA |

Hardwinarto et al. [18] | East Kalimantan- Indonesia | Data used from 1986–2008 | BPNN | NA | MSE |

Khajure et al. [15] | NA | Daily records for 5 years | NN and a fuzzy inference system | Temperature, humidity, dew point, visibility, pressure and windspeed. | MSE |

Kumar and Tyagi [19] | Nilgiri district Tamil Nadu, India | Monthly rain- fall prediction (Data from 1972–2002) | BPNN, RBFNN | NA | MSE |

Wahyuni et al. [16] | Tengger East Java | Data used from 2005 to 2014 | BPNN | Changes caused by climate change | RMSE |

Kashiwao et al. [13] | Japan | Rainfall data from the in- ternet as \“big data” was used. | ANN MLP and RBFN | Atm. pressure, precipitation, humidity, temp., vapor pressure, wind, velocity. | Validation using JMA. |

Mishra et al. [17] | North India | North India for the period 1871–2012. | FFNN | Rainfall records of previous 2 months and current month | Regression analysis, MRE and MSE |

Rainfall Parameters | Units |
---|---|

Maximum Temperature (${t}_{max}$) | ${}^{\circ}$C |

Minimum Temperature (${t}_{min}$) | ${}^{\circ}$C |

Rainfall | Millimeters (mm) |

Relative Humidity | Percentage (%) |

Sunshine | Hours (h) |

Wind Speed | Meters per second (m/s) |

Name | Formula |
---|---|

MSE | $\frac{1}{n}{\sum}_{t=1}^{n}{({x}_{i}-{y}_{i})}^{2}$ |

RMSE | $\sqrt{\frac{1}{n}{\sum}_{t=1}^{n}{({x}_{i}-{y}_{i})}^{2}}$ |

${R}^{2}$ | $1-\frac{{\sum}_{i=0}^{{n}_{\mathrm{samples}}-1}{({x}_{i}-{y}_{i})}^{2}}{{\sum}_{i=0}^{{n}_{\mathrm{samples}}-1}{({x}_{i}-\overline{y})}^{2}}$ |

Correlation | $\frac{{\sum}_{i=1}^{n}({x}_{i}-\overline{x})({y}_{i}-\overline{y})}{\sqrt{{\sum}_{i=1}^{n}{({x}_{i}-\overline{x})}^{2}{\sum}_{i=1}^{n}{({y}_{i}-\overline{y})}^{2}}}$ |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Chhetri, M.; Kumar, S.; Pratim Roy, P.; Kim, B.-G.
Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan. *Remote Sens.* **2020**, *12*, 3174.
https://doi.org/10.3390/rs12193174

**AMA Style**

Chhetri M, Kumar S, Pratim Roy P, Kim B-G.
Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan. *Remote Sensing*. 2020; 12(19):3174.
https://doi.org/10.3390/rs12193174

**Chicago/Turabian Style**

Chhetri, Manoj, Sudhanshu Kumar, Partha Pratim Roy, and Byung-Gyu Kim.
2020. "Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan" *Remote Sensing* 12, no. 19: 3174.
https://doi.org/10.3390/rs12193174