Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network
Rainfall prediction targets the determination of rainfall conditions over a specific location. It is considered vital for the agricultural industry and other industries. In this paper, we propose a new forecasting method that uses a deep convolutional neural network (CNN) to predict monthly rainfall...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8529196/ |
| _version_ | 1818323687546290176 |
|---|---|
| author | Ali Haidar Brijesh Verma |
| author_facet | Ali Haidar Brijesh Verma |
| author_sort | Ali Haidar |
| collection | DOAJ |
| description | Rainfall prediction targets the determination of rainfall conditions over a specific location. It is considered vital for the agricultural industry and other industries. In this paper, we propose a new forecasting method that uses a deep convolutional neural network (CNN) to predict monthly rainfall for a selected location in eastern Australia. To our knowledge, this is the first time applying a deep CNN in predicting monthly rainfall. The proposed approach was compared against the Australian Community Climate and Earth-System Simulator-Seasonal Prediction System (ACCESS), which is a forecasting model released by the Bureau of Meteorology. In addition, the CNN was compared against a conventional multi-layered perceptron (MLP). The better mean absolute error, root mean square error (RMSE), Pearson correlation (r), and Nash Suttcliff coefficient of efficiency values were obtained with the proposed CNN. A difference of 37.006 mm was obtained in terms of RMSE compared with ACCESS and 15.941 compared with conventional MLP. Further investigation revealed that the CNN was generally performing better in months with higher annual averages, while ACCESS was performing better in months with low annual averages. The generated output is promising and can be widely extended in this type of applications. |
| first_indexed | 2024-12-13T11:16:39Z |
| format | Article |
| id | doaj.art-864d18f695914fdba1178fb8b58561ae |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T11:16:39Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-864d18f695914fdba1178fb8b58561ae2022-12-21T23:48:37ZengIEEEIEEE Access2169-35362018-01-016690536906310.1109/ACCESS.2018.28800448529196Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural NetworkAli Haidar0https://orcid.org/0000-0001-5092-949XBrijesh Verma1Central Queensland University, Sydney, NSW, AustraliaCentral Queensland University, Sydney, NSW, AustraliaRainfall prediction targets the determination of rainfall conditions over a specific location. It is considered vital for the agricultural industry and other industries. In this paper, we propose a new forecasting method that uses a deep convolutional neural network (CNN) to predict monthly rainfall for a selected location in eastern Australia. To our knowledge, this is the first time applying a deep CNN in predicting monthly rainfall. The proposed approach was compared against the Australian Community Climate and Earth-System Simulator-Seasonal Prediction System (ACCESS), which is a forecasting model released by the Bureau of Meteorology. In addition, the CNN was compared against a conventional multi-layered perceptron (MLP). The better mean absolute error, root mean square error (RMSE), Pearson correlation (r), and Nash Suttcliff coefficient of efficiency values were obtained with the proposed CNN. A difference of 37.006 mm was obtained in terms of RMSE compared with ACCESS and 15.941 compared with conventional MLP. Further investigation revealed that the CNN was generally performing better in months with higher annual averages, while ACCESS was performing better in months with low annual averages. The generated output is promising and can be widely extended in this type of applications.https://ieeexplore.ieee.org/document/8529196/Convolutional neural networksrainfall predictionweather forecasting models |
| spellingShingle | Ali Haidar Brijesh Verma Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network IEEE Access Convolutional neural networks rainfall prediction weather forecasting models |
| title | Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network |
| title_full | Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network |
| title_fullStr | Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network |
| title_full_unstemmed | Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network |
| title_short | Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network |
| title_sort | monthly rainfall forecasting using one dimensional deep convolutional neural network |
| topic | Convolutional neural networks rainfall prediction weather forecasting models |
| url | https://ieeexplore.ieee.org/document/8529196/ |
| work_keys_str_mv | AT alihaidar monthlyrainfallforecastingusingonedimensionaldeepconvolutionalneuralnetwork AT brijeshverma monthlyrainfallforecastingusingonedimensionaldeepconvolutionalneuralnetwork |