Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh
A noticeable increase in drought frequency and severity has been observed across the globe due to climate change, which attracted scientists in development of drought prediction models for mitigation of impacts. Droughts are usually monitored using drought indices (DIs), most of which are probabilis...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Research
2021
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/96523/1/ShamsuddinShahid2021_ForecastingStandardizedPrecipitationIndex.pdf http://eprints.utm.my/id/eprint/96523/ http://dx.doi.org/10.1038/s41598-021-82977-9 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.96523 |
---|---|
record_format |
eprints |
spelling |
my.utm.965232022-07-26T08:32:41Z http://eprints.utm.my/id/eprint/96523/ Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh Yaseen, Z. M. Ali, M. Sharafati, A. Al-Ansari, N. Shahid, S. TA Engineering (General). Civil engineering (General) A noticeable increase in drought frequency and severity has been observed across the globe due to climate change, which attracted scientists in development of drought prediction models for mitigation of impacts. Droughts are usually monitored using drought indices (DIs), most of which are probabilistic and therefore, highly stochastic and non-linear. The current research investigated the capability of different versions of relatively well-explored machine learning (ML) models including random forest (RF), minimum probability machine regression (MPMR), M5 Tree (M5tree), extreme learning machine (ELM) and online sequential-ELM (OSELM) in predicting the most widely used DI known as standardized precipitation index (SPI) at multiple month horizons (i.e., 1, 3, 6 and 12). Models were developed using monthly rainfall data for the period of 1949–2013 at four meteorological stations namely, Barisal, Bogra, Faridpur and Mymensingh, each representing a geographical region of Bangladesh which frequently experiences droughts. The model inputs were decided based on correlation statistics and the prediction capability was evaluated using several statistical metrics including mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R), Willmott’s Index of agreement (WI), Nash Sutcliffe efficiency (NSE), and Legates and McCabe Index (LM). The results revealed that the proposed models are reliable and robust in predicting droughts in the region. Comparison of the models revealed ELM as the best model in forecasting droughts with minimal RMSE in the range of 0.07–0.85, 0.08–0.76, 0.062–0.80 and 0.042–0.605 for Barisal, Bogra, Faridpur and Mymensingh, respectively for all the SPI scales except one-month SPI for which the RF showed the best performance with minimal RMSE of 0.57, 0.45, 0.59 and 0.42, respectively. Nature Research 2021-12 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/96523/1/ShamsuddinShahid2021_ForecastingStandardizedPrecipitationIndex.pdf Yaseen, Z. M. and Ali, M. and Sharafati, A. and Al-Ansari, N. and Shahid, S. (2021) Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh. Scientific Reports, 11 (1). pp. 1-25. ISSN 2045-2322 http://dx.doi.org/10.1038/s41598-021-82977-9 DOI: 10.1038/s41598-021-82977-9 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
TA Engineering (General). Civil engineering (General) |
spellingShingle |
TA Engineering (General). Civil engineering (General) Yaseen, Z. M. Ali, M. Sharafati, A. Al-Ansari, N. Shahid, S. Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
description |
A noticeable increase in drought frequency and severity has been observed across the globe due to climate change, which attracted scientists in development of drought prediction models for mitigation of impacts. Droughts are usually monitored using drought indices (DIs), most of which are probabilistic and therefore, highly stochastic and non-linear. The current research investigated the capability of different versions of relatively well-explored machine learning (ML) models including random forest (RF), minimum probability machine regression (MPMR), M5 Tree (M5tree), extreme learning machine (ELM) and online sequential-ELM (OSELM) in predicting the most widely used DI known as standardized precipitation index (SPI) at multiple month horizons (i.e., 1, 3, 6 and 12). Models were developed using monthly rainfall data for the period of 1949–2013 at four meteorological stations namely, Barisal, Bogra, Faridpur and Mymensingh, each representing a geographical region of Bangladesh which frequently experiences droughts. The model inputs were decided based on correlation statistics and the prediction capability was evaluated using several statistical metrics including mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R), Willmott’s Index of agreement (WI), Nash Sutcliffe efficiency (NSE), and Legates and McCabe Index (LM). The results revealed that the proposed models are reliable and robust in predicting droughts in the region. Comparison of the models revealed ELM as the best model in forecasting droughts with minimal RMSE in the range of 0.07–0.85, 0.08–0.76, 0.062–0.80 and 0.042–0.605 for Barisal, Bogra, Faridpur and Mymensingh, respectively for all the SPI scales except one-month SPI for which the RF showed the best performance with minimal RMSE of 0.57, 0.45, 0.59 and 0.42, respectively. |
format |
Article |
author |
Yaseen, Z. M. Ali, M. Sharafati, A. Al-Ansari, N. Shahid, S. |
author_facet |
Yaseen, Z. M. Ali, M. Sharafati, A. Al-Ansari, N. Shahid, S. |
author_sort |
Yaseen, Z. M. |
title |
Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
title_short |
Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
title_full |
Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
title_fullStr |
Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
title_full_unstemmed |
Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh |
title_sort |
forecasting standardized precipitation index using data intelligence models: regional investigation of bangladesh |
publisher |
Nature Research |
publishDate |
2021 |
url |
http://eprints.utm.my/id/eprint/96523/1/ShamsuddinShahid2021_ForecastingStandardizedPrecipitationIndex.pdf http://eprints.utm.my/id/eprint/96523/ http://dx.doi.org/10.1038/s41598-021-82977-9 |
_version_ |
1739828091882045440 |
score |
13.222552 |