Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Indo-MathEdu Intellectuals Journal
Putri, Salma Azzahra
Unknown Affiliation
Mathematics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Extreme Gradent Boosting Method Forecasting Rainfall in Lembang District, West Java Province Putri, Salma Azzahra; Darmawan , Gumgum; Arisanti, Restu; Clarissa Clorinda, Chrysentia
Indo-MathEdu Intellectuals Journal Vol. 4 No. 3 (2023): Indo-MathEdu Intellectuals Journal
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/imeij.v4i3.452

Abstract

Lembang is a notable regional tourism destination that bears considerable significance within the urban area of Bandung. Lembang is widely recognized for its flourishing agricultural sector, which supports a significant community of farmers engaged in the cultivation of fruits, vegetables, and ornamental plants, in addition to its intrinsic scenic beauty. Therefore, the acquisition of precipitation data is of considerable significance for individuals live in the area to maintain their economic endeavors. This study employs daily historical data from the period of 2018 to 2021, wherein approximately 70% of the data is categorized as sparse. This discourse aims to examine the utilization of the Extreme Gradient Boosting (XGboost) technique for predicting rainfall in the Lembang region, specifically emphasizing its effectiveness in handling limited data. The findings indicate that the model, when trained and tested using a 7:3 data split ratio, achieved a mean absolute error (MAE) of 1.834 for training and 4.473 for testing. Additionally, the root mean square error (RMSE) was calculated to be 3.319 for training and 7.637 for testing. The optimal hyperparameters consist of a learning rate of 0.005, a max_depth value of 10, and the utilization of 300 decision trees as n_estimators. The model effectively captures the pattern of sparse time series data and non-rainy days data, as evidenced by its low error metrics. However, it slightly underestimates the rainfall rate on the days with intense precipitation
Extreme Gradent Boosting Method Forecasting Rainfall in Lembang District, West Java Province Putri, Salma Azzahra; Darmawan , Gumgum; Arisanti, Restu; Clarissa Clorinda, Chrysentia
Indo-MathEdu Intellectuals Journal Vol. 4 No. 3 (2023): Indo-MathEdu Intellectuals Journal
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/imeij.v4i3.452

Abstract

Lembang is a notable regional tourism destination that bears considerable significance within the urban area of Bandung. Lembang is widely recognized for its flourishing agricultural sector, which supports a significant community of farmers engaged in the cultivation of fruits, vegetables, and ornamental plants, in addition to its intrinsic scenic beauty. Therefore, the acquisition of precipitation data is of considerable significance for individuals live in the area to maintain their economic endeavors. This study employs daily historical data from the period of 2018 to 2021, wherein approximately 70% of the data is categorized as sparse. This discourse aims to examine the utilization of the Extreme Gradient Boosting (XGboost) technique for predicting rainfall in the Lembang region, specifically emphasizing its effectiveness in handling limited data. The findings indicate that the model, when trained and tested using a 7:3 data split ratio, achieved a mean absolute error (MAE) of 1.834 for training and 4.473 for testing. Additionally, the root mean square error (RMSE) was calculated to be 3.319 for training and 7.637 for testing. The optimal hyperparameters consist of a learning rate of 0.005, a max_depth value of 10, and the utilization of 300 decision trees as n_estimators. The model effectively captures the pattern of sparse time series data and non-rainy days data, as evidenced by its low error metrics. However, it slightly underestimates the rainfall rate on the days with intense precipitation
Co-Authors Arisanti, Restu Clarissa Clorinda, Chrysentia Darmawan , Gumgum