Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach
Rainfall is one of the climatic factors that influence various human activities and affect decision making in daily life activities. High intensity of rainfall can turn into a threat and cause serious problems such as causing various natural disasters. Therefore, it is essential to conduct rainfall...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2023-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2023/1863346 |
| _version_ | 1797362672501522432 |
|---|---|
| author | Gumgum Darmawan Budhi Handoko Defi Yusti Faidah Dian Islamiaty |
| author_facet | Gumgum Darmawan Budhi Handoko Defi Yusti Faidah Dian Islamiaty |
| author_sort | Gumgum Darmawan |
| collection | DOAJ |
| description | Rainfall is one of the climatic factors that influence various human activities and affect decision making in daily life activities. High intensity of rainfall can turn into a threat and cause serious problems such as causing various natural disasters. Therefore, it is essential to conduct rainfall forecasting to anticipate and enable preventive actions and can be used as a decision consideration in increasing the productivity and mobility of human activities. The aim of this study is to compare rainfall accuracy between the Gregorian and the lunar calendars using the bidirectional long short-term memory (Bi-LSTM) machine learning model through the grid search approach. This method was used because it can capture patterns arising from the simultaneous effects of two asynchronous calendars, Gregorian and lunar, which were used in this study by finding the right parameters. Monthly rainfall data from Bogor City, Indonesia, were used from the period of 2001 to 2022. The results show that the MAPE of the lunar calendar is relatively smaller at 14.82% which indicates the better forecasting ability than the Gregorian calendar which is 35.12%. |
| first_indexed | 2024-03-08T16:10:53Z |
| format | Article |
| id | doaj.art-d7e89452427045cb860a31bb7bf0f575 |
| institution | Directory Open Access Journal |
| issn | 1537-744X |
| language | English |
| last_indexed | 2024-03-08T16:10:53Z |
| publishDate | 2023-01-01 |
| publisher | Hindawi Limited |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj.art-d7e89452427045cb860a31bb7bf0f5752024-01-08T01:24:06ZengHindawi LimitedThe Scientific World Journal1537-744X2023-01-01202310.1155/2023/1863346Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search ApproachGumgum Darmawan0Budhi Handoko1Defi Yusti Faidah2Dian Islamiaty3Department of StatisticsDepartment of StatisticsDepartment of StatisticsDepartment of StatisticsRainfall is one of the climatic factors that influence various human activities and affect decision making in daily life activities. High intensity of rainfall can turn into a threat and cause serious problems such as causing various natural disasters. Therefore, it is essential to conduct rainfall forecasting to anticipate and enable preventive actions and can be used as a decision consideration in increasing the productivity and mobility of human activities. The aim of this study is to compare rainfall accuracy between the Gregorian and the lunar calendars using the bidirectional long short-term memory (Bi-LSTM) machine learning model through the grid search approach. This method was used because it can capture patterns arising from the simultaneous effects of two asynchronous calendars, Gregorian and lunar, which were used in this study by finding the right parameters. Monthly rainfall data from Bogor City, Indonesia, were used from the period of 2001 to 2022. The results show that the MAPE of the lunar calendar is relatively smaller at 14.82% which indicates the better forecasting ability than the Gregorian calendar which is 35.12%.http://dx.doi.org/10.1155/2023/1863346 |
| spellingShingle | Gumgum Darmawan Budhi Handoko Defi Yusti Faidah Dian Islamiaty Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach The Scientific World Journal |
| title | Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach |
| title_full | Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach |
| title_fullStr | Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach |
| title_full_unstemmed | Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach |
| title_short | Improving the Forecasting Accuracy Based on the Lunar Calendar in Modeling Rainfall Levels Using the Bi-LSTM Method through the Grid Search Approach |
| title_sort | improving the forecasting accuracy based on the lunar calendar in modeling rainfall levels using the bi lstm method through the grid search approach |
| url | http://dx.doi.org/10.1155/2023/1863346 |
| work_keys_str_mv | AT gumgumdarmawan improvingtheforecastingaccuracybasedonthelunarcalendarinmodelingrainfalllevelsusingthebilstmmethodthroughthegridsearchapproach AT budhihandoko improvingtheforecastingaccuracybasedonthelunarcalendarinmodelingrainfalllevelsusingthebilstmmethodthroughthegridsearchapproach AT defiyustifaidah improvingtheforecastingaccuracybasedonthelunarcalendarinmodelingrainfalllevelsusingthebilstmmethodthroughthegridsearchapproach AT dianislamiaty improvingtheforecastingaccuracybasedonthelunarcalendarinmodelingrainfalllevelsusingthebilstmmethodthroughthegridsearchapproach |