Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM
Accurate and reliable relative humidity forecasting is important when evaluating the impacts of climate change on humans and ecosystems. However, the complex interactions among geophysical parameters are challenging and may result in inaccurate weather forecasting. This study combines long short-ter...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2023-11-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/905 |
| _version_ | 1797403441499209728 |
|---|---|
| author | Kurnianingsih Kurnianingsih Anindya Wirasatriya Lutfan Lazuardi Adi Wibowo I Ketut Agung Enriko Wei Hong Chin Naoyuki Kubota |
| author_facet | Kurnianingsih Kurnianingsih Anindya Wirasatriya Lutfan Lazuardi Adi Wibowo I Ketut Agung Enriko Wei Hong Chin Naoyuki Kubota |
| author_sort | Kurnianingsih Kurnianingsih |
| collection | DOAJ |
| description | Accurate and reliable relative humidity forecasting is important when evaluating the impacts of climate change on humans and ecosystems. However, the complex interactions among geophysical parameters are challenging and may result in inaccurate weather forecasting. This study combines long short-term memory (LSTM) and extreme learning machines (ELM) to create a hybrid model-based forecasting technique to predict relative humidity to improve the accuracy of forecasts. Detailed experiments with univariate and multivariate problems were conducted, and the results show that LSTM-ELM and ELM-LSTM have the lowest MAE and RMSE results compared to stand-alone LSTM and ELM for the univariate problem. In addition, LSTM-ELM and ELM-LSTM result in lower computation time than stand-alone LSTM. The experiment results demonstrate that the proposed hybrid models outperform the comparative methods in relative humidity forecasting. We employed the recursive feature elimination (RFE) method and showed that dewpoint temperature, temperature, and wind speed are the factors that most affect relative humidity. A higher dewpoint temperature indicates more air moisture, equating to high relative humidity. Humidity levels also rise as the temperature rises. |
| first_indexed | 2024-03-09T02:38:36Z |
| format | Article |
| id | doaj.art-a4bf0df939844839887ffd48b5ea948f |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-03-09T02:38:36Z |
| publishDate | 2023-11-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-a4bf0df939844839887ffd48b5ea948f2023-12-06T06:59:49ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612023-11-019353755010.26555/ijain.v9i3.905266Big data analytics for relative humidity time series forecasting based on the LSTM network and ELMKurnianingsih Kurnianingsih0Anindya Wirasatriya1Lutfan Lazuardi2Adi Wibowo3I Ketut Agung Enriko4Wei Hong Chin5Naoyuki Kubota6Department of Electrical Engineering, Politeknik Negeri SemarangDepartment of Oceanography, Universitas DiponegoroFaculty of Medicine, Universitas Gadjah MadaDepartment of Computer Science, Universitas DiponegoroDepartment of Electrical Engineering, Institut Teknologi Telkom PurwokertoGraduate School of Systems Design, Tokyo Metropolitan UniversityGraduate School of Systems Design, Tokyo Metropolitan UniversityAccurate and reliable relative humidity forecasting is important when evaluating the impacts of climate change on humans and ecosystems. However, the complex interactions among geophysical parameters are challenging and may result in inaccurate weather forecasting. This study combines long short-term memory (LSTM) and extreme learning machines (ELM) to create a hybrid model-based forecasting technique to predict relative humidity to improve the accuracy of forecasts. Detailed experiments with univariate and multivariate problems were conducted, and the results show that LSTM-ELM and ELM-LSTM have the lowest MAE and RMSE results compared to stand-alone LSTM and ELM for the univariate problem. In addition, LSTM-ELM and ELM-LSTM result in lower computation time than stand-alone LSTM. The experiment results demonstrate that the proposed hybrid models outperform the comparative methods in relative humidity forecasting. We employed the recursive feature elimination (RFE) method and showed that dewpoint temperature, temperature, and wind speed are the factors that most affect relative humidity. A higher dewpoint temperature indicates more air moisture, equating to high relative humidity. Humidity levels also rise as the temperature rises.http://ijain.org/index.php/IJAIN/article/view/905big data analyticsrelative humiditytime series forecastinglstmelm |
| spellingShingle | Kurnianingsih Kurnianingsih Anindya Wirasatriya Lutfan Lazuardi Adi Wibowo I Ketut Agung Enriko Wei Hong Chin Naoyuki Kubota Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM IJAIN (International Journal of Advances in Intelligent Informatics) big data analytics relative humidity time series forecasting lstm elm |
| title | Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM |
| title_full | Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM |
| title_fullStr | Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM |
| title_full_unstemmed | Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM |
| title_short | Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM |
| title_sort | big data analytics for relative humidity time series forecasting based on the lstm network and elm |
| topic | big data analytics relative humidity time series forecasting lstm elm |
| url | http://ijain.org/index.php/IJAIN/article/view/905 |
| work_keys_str_mv | AT kurnianingsihkurnianingsih bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT anindyawirasatriya bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT lutfanlazuardi bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT adiwibowo bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT iketutagungenriko bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT weihongchin bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm AT naoyukikubota bigdataanalyticsforrelativehumiditytimeseriesforecastingbasedonthelstmnetworkandelm |