Evaluation of classification and decision trees in predicting daily precipitation occurrences
Due to the heterogeneous distribution of precipitation, predicting its occurrence is one of the primary and basic strategies to prevent possible disasters and their damages. Hence, this study aims at evaluating the capabilities of Logistic Model Tree (LMT), J48, Random Forest (RF), and PART classifi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2022-04-01
|
| Series: | Water Supply |
| Subjects: | |
| Online Access: | http://ws.iwaponline.com/content/22/4/3879 |
| _version_ | 1818015543313039360 |
|---|---|
| author | S. Samadianfard F. Mikaeili R. Prasad |
| author_facet | S. Samadianfard F. Mikaeili R. Prasad |
| author_sort | S. Samadianfard |
| collection | DOAJ |
| description | Due to the heterogeneous distribution of precipitation, predicting its occurrence is one of the primary and basic strategies to prevent possible disasters and their damages. Hence, this study aims at evaluating the capabilities of Logistic Model Tree (LMT), J48, Random Forest (RF), and PART classification algorithms in precipitation forecasts at Pars Abad station using previous 1–4 days data of meteorological variables. So, five scenarios were considered based on the cross-correlation function and partial autocorrelation function for validation of the studied methods in the period of 2004–2019. In general, by examining the Kappa, root mean squared error (RMSE), mean absolute error (MAE) indicators, scenario number 1 using the input parameters of 1-day lag was determined as the most appropriate scenario to predict daily precipitation. Also, the obtained results showed that the PART had better performance with more than 80% accuracy in precipitation forecasting. Moreover, the most accurate performance of PART was scenario 1 with Kappa = 0.2007, RMSE = 0.3879 and MAE = 0.2856. The conclusive results indicated that by implementing classification algorithms and decision trees and using meteorological data of the previous days, daily precipitation could be predicted accurately. HIGHLIGHTS
Classification algorithms and decision tree models were tested in precipitation occurrence forecasting.;
The capabilities of Logistic Model Tree, J48, Random Forest and PART were examined using kappa and accuracy criteria.;
PART algorithm indicated more than 80% accuracy.;
By implementing classification algorithms and decision trees and using meteorological data of the previous days, daily precipitation can be predicted accurately.; |
| first_indexed | 2024-04-14T06:59:35Z |
| format | Article |
| id | doaj.art-e277cb6576ee4d8197b9231ee3a7d126 |
| institution | Directory Open Access Journal |
| issn | 1606-9749 1607-0798 |
| language | English |
| last_indexed | 2024-04-14T06:59:35Z |
| publishDate | 2022-04-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Supply |
| spelling | doaj.art-e277cb6576ee4d8197b9231ee3a7d1262022-12-22T02:06:48ZengIWA PublishingWater Supply1606-97491607-07982022-04-012243879389510.2166/ws.2022.017017Evaluation of classification and decision trees in predicting daily precipitation occurrencesS. Samadianfard0F. Mikaeili1R. Prasad2 Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran Department of Science, School of Science and Technology, The University of Fiji, Lautoka, Fiji Due to the heterogeneous distribution of precipitation, predicting its occurrence is one of the primary and basic strategies to prevent possible disasters and their damages. Hence, this study aims at evaluating the capabilities of Logistic Model Tree (LMT), J48, Random Forest (RF), and PART classification algorithms in precipitation forecasts at Pars Abad station using previous 1–4 days data of meteorological variables. So, five scenarios were considered based on the cross-correlation function and partial autocorrelation function for validation of the studied methods in the period of 2004–2019. In general, by examining the Kappa, root mean squared error (RMSE), mean absolute error (MAE) indicators, scenario number 1 using the input parameters of 1-day lag was determined as the most appropriate scenario to predict daily precipitation. Also, the obtained results showed that the PART had better performance with more than 80% accuracy in precipitation forecasting. Moreover, the most accurate performance of PART was scenario 1 with Kappa = 0.2007, RMSE = 0.3879 and MAE = 0.2856. The conclusive results indicated that by implementing classification algorithms and decision trees and using meteorological data of the previous days, daily precipitation could be predicted accurately. HIGHLIGHTS Classification algorithms and decision tree models were tested in precipitation occurrence forecasting.; The capabilities of Logistic Model Tree, J48, Random Forest and PART were examined using kappa and accuracy criteria.; PART algorithm indicated more than 80% accuracy.; By implementing classification algorithms and decision trees and using meteorological data of the previous days, daily precipitation can be predicted accurately.;http://ws.iwaponline.com/content/22/4/3879lagmachine learning methodsmeteorological parametersrainfallstatistical analysis |
| spellingShingle | S. Samadianfard F. Mikaeili R. Prasad Evaluation of classification and decision trees in predicting daily precipitation occurrences Water Supply lag machine learning methods meteorological parameters rainfall statistical analysis |
| title | Evaluation of classification and decision trees in predicting daily precipitation occurrences |
| title_full | Evaluation of classification and decision trees in predicting daily precipitation occurrences |
| title_fullStr | Evaluation of classification and decision trees in predicting daily precipitation occurrences |
| title_full_unstemmed | Evaluation of classification and decision trees in predicting daily precipitation occurrences |
| title_short | Evaluation of classification and decision trees in predicting daily precipitation occurrences |
| title_sort | evaluation of classification and decision trees in predicting daily precipitation occurrences |
| topic | lag machine learning methods meteorological parameters rainfall statistical analysis |
| url | http://ws.iwaponline.com/content/22/4/3879 |
| work_keys_str_mv | AT ssamadianfard evaluationofclassificationanddecisiontreesinpredictingdailyprecipitationoccurrences AT fmikaeili evaluationofclassificationanddecisiontreesinpredictingdailyprecipitationoccurrences AT rprasad evaluationofclassificationanddecisiontreesinpredictingdailyprecipitationoccurrences |