Hakim, Muhammad Lutfi (2026) Sistem Prediksi Ketinggian Air Sungai Untuk Deteksi Dini Banjir Menggunakan Prophet Forecasting. Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (148kB) |
|
Text (BAB 1 Pendahuluan)
BAB 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (145kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (152kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (5MB) | Request a copy |
Abstract
Jember Regency, particularly along the Kalijompo River, is a region highly vulnerable to flood disasters. The existing Early Warning System is still reactive, only providing alerts when the water level reaches a critical threshold. This research aims to develop a proactive river water level prediction system using the Prophet Time Series Forecasting method. Data acquisition is conducted automatically through CCTV cameras and processed using digital image processing techniques to detect the water level boundaries. Based on 109 days of testing, the system successfully collected 10,102 time-series data points. The training and parameter optimization results on the Prophet model (using logistic growth, multiplicative seasonality, and a changepoint prior scale of 0.5) proved to significantly improve accuracy. Performance evaluation showed a decrease in the Mean Absolute Error (MAE) from 4.38 cm to 3.76 cm and the Mean Absolute Percentage Error (MAPE) from 24.57% to 16.90%, while the Root Mean Squared Error (RMSE) experienced a slight increase from 10.63 cm to 10.87 cm. The model was also validated to be capable of precisely capturing the daily fluctuation cycle patterns of the river when compared with field data. The results of this study effectively shift the monitoring paradigm from a reactive system to a proactive early warning system, providing a longer lead time for the community and thereby supporting the effectiveness of disaster mitigation in Jember.
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | Prediksi Banjir, Prophet Forecasting, Time Series, Ketinggian Air, Sistem Peringatan Dini, Sungai Kalijompo | ||||||
| Subjects: | 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 462 - Teknologi Informasi |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Muhammad Lutfi Hakim | ||||||
| Date Deposited: | 11 May 2026 01:05 | ||||||
| Last Modified: | 11 May 2026 01:06 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/55813 |
Actions (login required)
 |
View Item |
