Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach
In the present work, a wavelet-based multiscale deep learning approach is developed to forecast precipitation using the lagged monthly rainfall, local climate variables, and global teleconnections such as IOD, PDO, NAO, and Nino 3.4 as predictors. The conventional methods are limited by their inabil...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/18/3244 |
| _version_ | 1797576340698824704 |
|---|---|
| author | Pavan Kumar Yeditha G. Sree Anusha Siva Sai Syam Nandikanti Maheswaran Rathinasamy |
| author_facet | Pavan Kumar Yeditha G. Sree Anusha Siva Sai Syam Nandikanti Maheswaran Rathinasamy |
| author_sort | Pavan Kumar Yeditha |
| collection | DOAJ |
| description | In the present work, a wavelet-based multiscale deep learning approach is developed to forecast precipitation using the lagged monthly rainfall, local climate variables, and global teleconnections such as IOD, PDO, NAO, and Nino 3.4 as predictors. The conventional methods are limited by their inability to capture the high precipitation variability in time and space. The proposed multiscale method was tested and validated over the Krishna River basin in India. The results from the proposed methods were compared with contemporary models based on Multiple Linear Regression and Neural Networks. Overall, the forecasting accuracy was higher using the wavelet-based hybrid models than the single-scale models. The wavelet-based methods yielded results with 13–34% reduced error when compared with the best single-scale models. The proposed multi-scale model was then applied to the different climatic regions of the country, and it was shown that the model could forecast rainfall with reasonable accuracy for different climate zones of the country. |
| first_indexed | 2024-03-10T21:51:49Z |
| format | Article |
| id | doaj.art-b707544f904e4cfcaa566032153a2876 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T21:51:49Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-b707544f904e4cfcaa566032153a28762023-11-19T13:25:52ZengMDPI AGWater2073-44412023-09-011518324410.3390/w15183244Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning ApproachPavan Kumar Yeditha0G. Sree Anusha1Siva Sai Syam Nandikanti2Maheswaran Rathinasamy3Department of Civil and Environmental Engineering, Universitat Politècnica de Catalunya, UPC, 08034 Barcelona, SpainDepartment of Climate Change, Indian Institute of Technology (IIT), Hyderabad 502284, IndiaDepartment of Civil Engineering, Indian Institute of Technology (IIT), Hyderabad 502284, IndiaDepartment of Climate Change, Indian Institute of Technology (IIT), Hyderabad 502284, IndiaIn the present work, a wavelet-based multiscale deep learning approach is developed to forecast precipitation using the lagged monthly rainfall, local climate variables, and global teleconnections such as IOD, PDO, NAO, and Nino 3.4 as predictors. The conventional methods are limited by their inability to capture the high precipitation variability in time and space. The proposed multiscale method was tested and validated over the Krishna River basin in India. The results from the proposed methods were compared with contemporary models based on Multiple Linear Regression and Neural Networks. Overall, the forecasting accuracy was higher using the wavelet-based hybrid models than the single-scale models. The wavelet-based methods yielded results with 13–34% reduced error when compared with the best single-scale models. The proposed multi-scale model was then applied to the different climatic regions of the country, and it was shown that the model could forecast rainfall with reasonable accuracy for different climate zones of the country.https://www.mdpi.com/2073-4441/15/18/3244monthly precipitation forecastwavelet-based machine learningteleconnections |
| spellingShingle | Pavan Kumar Yeditha G. Sree Anusha Siva Sai Syam Nandikanti Maheswaran Rathinasamy Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach Water monthly precipitation forecast wavelet-based machine learning teleconnections |
| title | Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach |
| title_full | Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach |
| title_fullStr | Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach |
| title_full_unstemmed | Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach |
| title_short | Development of Monthly Scale Precipitation-Forecasting Model for Indian Subcontinent using Wavelet-Based Deep Learning Approach |
| title_sort | development of monthly scale precipitation forecasting model for indian subcontinent using wavelet based deep learning approach |
| topic | monthly precipitation forecast wavelet-based machine learning teleconnections |
| url | https://www.mdpi.com/2073-4441/15/18/3244 |
| work_keys_str_mv | AT pavankumaryeditha developmentofmonthlyscaleprecipitationforecastingmodelforindiansubcontinentusingwaveletbaseddeeplearningapproach AT gsreeanusha developmentofmonthlyscaleprecipitationforecastingmodelforindiansubcontinentusingwaveletbaseddeeplearningapproach AT sivasaisyamnandikanti developmentofmonthlyscaleprecipitationforecastingmodelforindiansubcontinentusingwaveletbaseddeeplearningapproach AT maheswaranrathinasamy developmentofmonthlyscaleprecipitationforecastingmodelforindiansubcontinentusingwaveletbaseddeeplearningapproach |