Machine learning models for prediction of rainfall over Nigeria
Investigating climatology and predicting rainfall amounts are crucial for planning and mitigating the risks caused by variable rainfall. This study utilized two multivariate polynomial regressions (MPR) and twelve machine learning algorithms, namely three artificial neural networks (ANN), four adapt...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-07-01
|
| Series: | Scientific African |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468227622001533 |
| _version_ | 1811195161964707840 |
|---|---|
| author | Olusola Samuel Ojo Samuel Toluwalope Ogunjo |
| author_facet | Olusola Samuel Ojo Samuel Toluwalope Ogunjo |
| author_sort | Olusola Samuel Ojo |
| collection | DOAJ |
| description | Investigating climatology and predicting rainfall amounts are crucial for planning and mitigating the risks caused by variable rainfall. This study utilized two multivariate polynomial regressions (MPR) and twelve machine learning algorithms, namely three artificial neural networks (ANN), four adaptive neuro-fuzzy inference system (ANFIS) and five support vector machine (SVM) algorithms, to estimate monthly and annual rainfalls in a tropical location. The ground measured rainfall data were collected from the Nigerian Meteorological Agency (NIMET), Lagos spanning 31 years (1983–2013) spatially distributed across Nigeria. The proposed models employed geoclimatic coordinates such as longitude, latitude, and altitude as input variables. Analyses based on general performance index (c) showed that the adaptive neuro-fuzzy inference system (ANFIS) model’s algorithms outscored the MPR, ANN and SVM models in the ten months of the year. Its the generalized bell-shaped algorithm (ANFIS-GBELL) performed best for January, April, May, July, October and annual rainfalls, the Gaussian algorithm (ANFIS-GAUSS) for November and December, the subtractive clustered algorithms (ANFIS-SC) for August and September rainfalls, and fuzzy c-means algorithms (ANFIS-FCM) for June rainfall. Also, the multivariate polynomial regression of second order (MPR-2) model performed best for February and March rainfalls. These models’ algorithms have general performance index ranging from 0.906 to 0.996 and they are thereby proposed for the estimation of rainfall amounts over Nigeria. |
| first_indexed | 2024-04-12T00:38:49Z |
| format | Article |
| id | doaj.art-c9773980b6c547d99427c62eba21c66d |
| institution | Directory Open Access Journal |
| issn | 2468-2276 |
| language | English |
| last_indexed | 2024-04-12T00:38:49Z |
| publishDate | 2022-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Scientific African |
| spelling | doaj.art-c9773980b6c547d99427c62eba21c66d2022-12-22T03:55:05ZengElsevierScientific African2468-22762022-07-0116e01246Machine learning models for prediction of rainfall over NigeriaOlusola Samuel Ojo0Samuel Toluwalope Ogunjo1Department of Physics, The Federal University of Technology, P.M.B. 704, Akure, Nigeria; Corresponding author.Department of Physics, The Federal University of Technology, Akure, NigeriaInvestigating climatology and predicting rainfall amounts are crucial for planning and mitigating the risks caused by variable rainfall. This study utilized two multivariate polynomial regressions (MPR) and twelve machine learning algorithms, namely three artificial neural networks (ANN), four adaptive neuro-fuzzy inference system (ANFIS) and five support vector machine (SVM) algorithms, to estimate monthly and annual rainfalls in a tropical location. The ground measured rainfall data were collected from the Nigerian Meteorological Agency (NIMET), Lagos spanning 31 years (1983–2013) spatially distributed across Nigeria. The proposed models employed geoclimatic coordinates such as longitude, latitude, and altitude as input variables. Analyses based on general performance index (c) showed that the adaptive neuro-fuzzy inference system (ANFIS) model’s algorithms outscored the MPR, ANN and SVM models in the ten months of the year. Its the generalized bell-shaped algorithm (ANFIS-GBELL) performed best for January, April, May, July, October and annual rainfalls, the Gaussian algorithm (ANFIS-GAUSS) for November and December, the subtractive clustered algorithms (ANFIS-SC) for August and September rainfalls, and fuzzy c-means algorithms (ANFIS-FCM) for June rainfall. Also, the multivariate polynomial regression of second order (MPR-2) model performed best for February and March rainfalls. These models’ algorithms have general performance index ranging from 0.906 to 0.996 and they are thereby proposed for the estimation of rainfall amounts over Nigeria.http://www.sciencedirect.com/science/article/pii/S2468227622001533Statistical modelMachine learningTropical rainfallRainfall modelling |
| spellingShingle | Olusola Samuel Ojo Samuel Toluwalope Ogunjo Machine learning models for prediction of rainfall over Nigeria Scientific African Statistical model Machine learning Tropical rainfall Rainfall modelling |
| title | Machine learning models for prediction of rainfall over Nigeria |
| title_full | Machine learning models for prediction of rainfall over Nigeria |
| title_fullStr | Machine learning models for prediction of rainfall over Nigeria |
| title_full_unstemmed | Machine learning models for prediction of rainfall over Nigeria |
| title_short | Machine learning models for prediction of rainfall over Nigeria |
| title_sort | machine learning models for prediction of rainfall over nigeria |
| topic | Statistical model Machine learning Tropical rainfall Rainfall modelling |
| url | http://www.sciencedirect.com/science/article/pii/S2468227622001533 |
| work_keys_str_mv | AT olusolasamuelojo machinelearningmodelsforpredictionofrainfallovernigeria AT samueltoluwalopeogunjo machinelearningmodelsforpredictionofrainfallovernigeria |