Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem
Prediction of daily rainfall is important for flood forecasting, reservoir operation, and many other hydrological applications. The artificial intelligence (AI) algorithm is generally used for stochastic forecasting rainfall which is not capable to simulate unseen extreme rainfall events which becom...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/6631564 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560006601375744 |
|---|---|
| author | Lu Ye Saadya Fahad Jabbar Musaddak M. Abdul Zahra Mou Leong Tan |
| author_facet | Lu Ye Saadya Fahad Jabbar Musaddak M. Abdul Zahra Mou Leong Tan |
| author_sort | Lu Ye |
| collection | DOAJ |
| description | Prediction of daily rainfall is important for flood forecasting, reservoir operation, and many other hydrological applications. The artificial intelligence (AI) algorithm is generally used for stochastic forecasting rainfall which is not capable to simulate unseen extreme rainfall events which become common due to climate change. A new model is developed in this study for prediction of daily rainfall for different lead times based on sea level pressure (SLP) which is physically related to rainfall on land and thus able to predict unseen rainfall events. Daily rainfall of east coast of Peninsular Malaysia (PM) was predicted using SLP data over the climate domain. Five advanced AI algorithms such as extreme learning machine (ELM), Bayesian regularized neural networks (BRNNs), Bayesian additive regression trees (BART), extreme gradient boosting (xgBoost), and hybrid neural fuzzy inference system (HNFIS) were used considering the complex relationship of rainfall with sea level pressure. Principle components of SLP domain correlated with daily rainfall were used as predictors. The results revealed that the efficacy of AI models is predicting daily rainfall one day before. The relative performance of the models revealed the higher performance of BRNN with normalized root mean square error (NRMSE) of 0.678 compared with HNFIS (NRMSE = 0.708), BART (NRMSE = 0.784), xgBoost (NRMSE = 0.803), and ELM (NRMSE = 0.915). Visual inspection of predicted rainfall during model validation using density-scatter plot and other novel ways of visual comparison revealed the ability of BRNN to predict daily rainfall one day before reliably. |
| format | Article |
| id | doaj-art-e3dc93abfc84412fb6deeec2056bdfa9 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-e3dc93abfc84412fb6deeec2056bdfa92025-02-03T01:28:43ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/66315646631564Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology ProblemLu Ye0Saadya Fahad Jabbar1Musaddak M. Abdul Zahra2Mou Leong Tan3School of Computer Science, Baoji University of Arts and Sciences, Baoji 721007, ChinaCollege of Education for Human Science-ibn Rushed, University of Baghdad, Baghdad, IraqComputer Techniques Engineering Department, Al-Mustaqbal University College, 51001 Hillah, Babil, IraqGeoinformatic Unit, Geography Section, School of Humanities, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, MalaysiaPrediction of daily rainfall is important for flood forecasting, reservoir operation, and many other hydrological applications. The artificial intelligence (AI) algorithm is generally used for stochastic forecasting rainfall which is not capable to simulate unseen extreme rainfall events which become common due to climate change. A new model is developed in this study for prediction of daily rainfall for different lead times based on sea level pressure (SLP) which is physically related to rainfall on land and thus able to predict unseen rainfall events. Daily rainfall of east coast of Peninsular Malaysia (PM) was predicted using SLP data over the climate domain. Five advanced AI algorithms such as extreme learning machine (ELM), Bayesian regularized neural networks (BRNNs), Bayesian additive regression trees (BART), extreme gradient boosting (xgBoost), and hybrid neural fuzzy inference system (HNFIS) were used considering the complex relationship of rainfall with sea level pressure. Principle components of SLP domain correlated with daily rainfall were used as predictors. The results revealed that the efficacy of AI models is predicting daily rainfall one day before. The relative performance of the models revealed the higher performance of BRNN with normalized root mean square error (NRMSE) of 0.678 compared with HNFIS (NRMSE = 0.708), BART (NRMSE = 0.784), xgBoost (NRMSE = 0.803), and ELM (NRMSE = 0.915). Visual inspection of predicted rainfall during model validation using density-scatter plot and other novel ways of visual comparison revealed the ability of BRNN to predict daily rainfall one day before reliably.http://dx.doi.org/10.1155/2021/6631564 |
| spellingShingle | Lu Ye Saadya Fahad Jabbar Musaddak M. Abdul Zahra Mou Leong Tan Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem Complexity |
| title | Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem |
| title_full | Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem |
| title_fullStr | Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem |
| title_full_unstemmed | Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem |
| title_short | Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem |
| title_sort | bayesian regularized neural network model development for predicting daily rainfall from sea level pressure data investigation on solving complex hydrology problem |
| url | http://dx.doi.org/10.1155/2021/6631564 |
| work_keys_str_mv | AT luye bayesianregularizedneuralnetworkmodeldevelopmentforpredictingdailyrainfallfromsealevelpressuredatainvestigationonsolvingcomplexhydrologyproblem AT saadyafahadjabbar bayesianregularizedneuralnetworkmodeldevelopmentforpredictingdailyrainfallfromsealevelpressuredatainvestigationonsolvingcomplexhydrologyproblem AT musaddakmabdulzahra bayesianregularizedneuralnetworkmodeldevelopmentforpredictingdailyrainfallfromsealevelpressuredatainvestigationonsolvingcomplexhydrologyproblem AT mouleongtan bayesianregularizedneuralnetworkmodeldevelopmentforpredictingdailyrainfallfromsealevelpressuredatainvestigationonsolvingcomplexhydrologyproblem |