Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models
Abstract The application of a novel method of adaptive neuro‐fuzzy inference system (ANFIS) for the prediction of air temperature is investigated. The paper discusses the improvement of the ANFIS when used with genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization for co...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-01-01
|
Series: | Meteorological Applications |
Subjects: | |
Online Access: | https://doi.org/10.1002/met.1817 |
_version_ | 1797900503704666112 |
---|---|
author | Armin Azad Hamed Kashi Saeed Farzin Vijay P. Singh Ozgur Kisi Hojat Karami Hadi Sanikhani |
author_facet | Armin Azad Hamed Kashi Saeed Farzin Vijay P. Singh Ozgur Kisi Hojat Karami Hadi Sanikhani |
author_sort | Armin Azad |
collection | DOAJ |
description | Abstract The application of a novel method of adaptive neuro‐fuzzy inference system (ANFIS) for the prediction of air temperature is investigated. The paper discusses the improvement of the ANFIS when used with genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization for continuous domains (ACOR) and differential evolution (DE). For this purpose, three input of multiple variables are selected in order to predict monthly minimum, average and maximum air temperatures for 34 meteorological stations in Iran. The co‐efficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and Nash–Sutcliffe efficiency (NSE) are used as evaluation criteria. A comparison of suggested fuzzy models indicates that the ANFIS with the GA has the best performance in the prediction of maximum temperatures. It decreases the RMSE of the classic ANFIS model in the validation stage from 1.22 to 1.12°C for Mashhad, from 1.26 to 1.01°C for Zahedan, from 1.20 to 0.98°C for Ahvaz, from 1.76 to 1.24°C for Rasht and from 1.21 to 0.95°C for Tabriz. |
first_indexed | 2024-04-10T08:47:08Z |
format | Article |
id | doaj.art-9fd61a2d66154fde8b09ce59ba52e01f |
institution | Directory Open Access Journal |
issn | 1350-4827 1469-8080 |
language | English |
last_indexed | 2024-04-10T08:47:08Z |
publishDate | 2020-01-01 |
publisher | Wiley |
record_format | Article |
series | Meteorological Applications |
spelling | doaj.art-9fd61a2d66154fde8b09ce59ba52e01f2023-02-22T07:11:33ZengWileyMeteorological Applications1350-48271469-80802020-01-01271n/an/a10.1002/met.1817Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy modelsArmin Azad0Hamed Kashi1Saeed Farzin2Vijay P. Singh3Ozgur Kisi4Hojat Karami5Hadi Sanikhani6Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering Semnan University Semnan IranInstitute for Plant Nutrition and Soil Science, Christian‐Albrechts‐University Kiel Hermann‐Rodewald‐Str 2 Kiel GermanyDepartment of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering Semnan University Semnan IranDepartment of Biological and Agricultural Engineering & Zachry Department of Civil Engineering Texas A&M University College Station TexasFaculty of Natural Sciences and Engineering Ilia State University Tbilisi GeorgiaDepartment of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering Semnan University Semnan IranDepartment of Water Engineering, Agriculture Faculty University of Kurdistan Sanandaj IranAbstract The application of a novel method of adaptive neuro‐fuzzy inference system (ANFIS) for the prediction of air temperature is investigated. The paper discusses the improvement of the ANFIS when used with genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization for continuous domains (ACOR) and differential evolution (DE). For this purpose, three input of multiple variables are selected in order to predict monthly minimum, average and maximum air temperatures for 34 meteorological stations in Iran. The co‐efficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and Nash–Sutcliffe efficiency (NSE) are used as evaluation criteria. A comparison of suggested fuzzy models indicates that the ANFIS with the GA has the best performance in the prediction of maximum temperatures. It decreases the RMSE of the classic ANFIS model in the validation stage from 1.22 to 1.12°C for Mashhad, from 1.26 to 1.01°C for Zahedan, from 1.20 to 0.98°C for Ahvaz, from 1.76 to 1.24°C for Rasht and from 1.21 to 0.95°C for Tabriz.https://doi.org/10.1002/met.1817adaptive neuro‐fuzzy inference system (ANFIS)evolutionary algorithm (EA)extreme and average temperature, genetic algorithm (GA) |
spellingShingle | Armin Azad Hamed Kashi Saeed Farzin Vijay P. Singh Ozgur Kisi Hojat Karami Hadi Sanikhani Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models Meteorological Applications adaptive neuro‐fuzzy inference system (ANFIS) evolutionary algorithm (EA) extreme and average temperature, genetic algorithm (GA) |
title | Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models |
title_full | Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models |
title_fullStr | Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models |
title_full_unstemmed | Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models |
title_short | Novel approaches for air temperature prediction: A comparison of four hybrid evolutionary fuzzy models |
title_sort | novel approaches for air temperature prediction a comparison of four hybrid evolutionary fuzzy models |
topic | adaptive neuro‐fuzzy inference system (ANFIS) evolutionary algorithm (EA) extreme and average temperature, genetic algorithm (GA) |
url | https://doi.org/10.1002/met.1817 |
work_keys_str_mv | AT arminazad novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT hamedkashi novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT saeedfarzin novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT vijaypsingh novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT ozgurkisi novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT hojatkarami novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels AT hadisanikhani novelapproachesforairtemperaturepredictionacomparisonoffourhybridevolutionaryfuzzymodels |