Garuda - Garba Rujukan Digital

A Web-Based Machine Learning Approach for Standardized Precipitation Index Prediction Hadi, Ahmad Fauzi Faishal; Sinambela, Marzuki; Rachmawardani, Agustina; Trihadi, Edward
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Accurate and user-friendly drought forecasting tools are crucial for mitigating the impact of meteorological droughts, particularly in vulnerable areas such as South Sumatra, Indonesia. This study introduces an interactive web-based application built to anticipate drought conditions by forecasting the Standardized Precipitation Index (SPI). The system relies on deep learning techniques trained using three decades of rainfall data collected from the Climatological Station in South Sumatra. In evaluating model performance, both Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) architectures were assessed. While both models delivered comparable short-term predictions, the LSTM experienced a significant decline in accuracy over extended forecasting periods (specifically at SPI-6), primarily due to overfitting. In contrast, the RNN displayed more stable and reliable results, making it the preferable model for this geographical context. Specifically, the RNN achieved a lower Mean Absolute Error (MAE) of 0.4007, a reduced Root Mean Squared Error (RMSE) of 0.4684, and a higher coefficient of determination (R²) of 0.7338. These metrics outperformed those of the LSTM, which recorded a MAE of 0.4115, an RMSE of 0.4840, and an R² of 0.7036. Such results confirm that the RNN offers a more precise and dependable fit for the station’s dataset. The web platform also effectively visualizes the model outputs, providing a dynamic and interactive 24-month forecast view that supports early warning efforts and informed decision-making for regional authorities and stakeholders.

A Web-Based Machine Learning Approach for Standardized Precipitation Index Prediction Hadi, Ahmad Fauzi Faishal; Sinambela, Marzuki; Rachmawardani, Agustina; Trihadi, Edward
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

Show Abstract | Download Original | Original Source | Check in Google Scholar

Accurate and user-friendly drought forecasting tools are crucial for mitigating the impact of meteorological droughts, particularly in vulnerable areas such as South Sumatra, Indonesia. This study introduces an interactive web-based application built to anticipate drought conditions by forecasting the Standardized Precipitation Index (SPI). The system relies on deep learning techniques trained using three decades of rainfall data collected from the Climatological Station in South Sumatra. In evaluating model performance, both Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) architectures were assessed. While both models delivered comparable short-term predictions, the LSTM experienced a significant decline in accuracy over extended forecasting periods (specifically at SPI-6), primarily due to overfitting. In contrast, the RNN displayed more stable and reliable results, making it the preferable model for this geographical context. Specifically, the RNN achieved a lower Mean Absolute Error (MAE) of 0.4007, a reduced Root Mean Squared Error (RMSE) of 0.4684, and a higher coefficient of determination (R²) of 0.7338. These metrics outperformed those of the LSTM, which recorded a MAE of 0.4115, an RMSE of 0.4840, and an R² of 0.7036. Such results confirm that the RNN offers a more precise and dependable fit for the station’s dataset. The web platform also effectively visualizes the model outputs, providing a dynamic and interactive 24-month forecast view that supports early warning efforts and informed decision-making for regional authorities and stakeholders.

Desain Ulang Antarmuka Pengguna dan Pengalaman dengan Peningkatan Identitas Merek untuk Situs Web STMKG melalui Implementasi WordPress Aji, Tonny Wahyu; Yasir, Ahmad Meijlan; Nardi; Sorfian; Rachmawardani, Agustina; Jehadun, Marianus Carol; Wastumirad, Adi Widiatmoko; Trihadi, Edward
Journal of Computation Physics and Earth Science (JoCPES) Vol 5 No 1 (2025): Journal of Computation Physics and Earth Science
Publisher : Yayasan Kita Menulis - JoCPES

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63581/JoCPES.v5i1.15

This paper presents the redesign, rebuild, and rebranding of the official website of Sekolah Tinggi Meteorologi Klimatologi dan Geofisika (STMKG) using the WordPress content management system. The project aimed to modernize the institution’s digital presence by enhancing layout consistency, mobile responsiveness, and brand identity. A content audit was conducted to reorganize fragmented navigation and outdated information. The entire development was executed directly within WordPress using Elementor, enabling rapid prototyping without external wireframing tools. Key improvements include structured program sections, a modern news layout, and a standardized footer, all designed in line with STMKG’s visual identity. Performance optimization—though not the primary focus—involved basic caching, compression, and lazy loading, with assessments via GTmetrix indicating areas for future improvement. The project, completed by a sixth-semester cadet, highlights the feasibility of student-led web transformation initiatives within academic institutions. Positive stakeholder feedback confirmed improvements in usability, clarity, and institutional credibility. This work demonstrates the practical application of accessible web technologies to deliver scalable, branded, and user-centered digital solutions in educational settings.

Rancang Bangun Intensitymeter Berbasis MEMS Dengan Algoritma Pendeteksi Kejadian STA/LTA dan Sistem Peringatan Multi-Saluran Rawana, Aziz; Rusanto, Benyamin Heryanto; Trihadi, Edward; Nardi, Nardi
Jurnal Otomasi Kontrol dan Instrumentasi Vol 17 No 2 (2025): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2025.17.2.8

Indonesia is an earthquake-prone country due to its location at the convergence of three major tectonic plates. To support disaster mitigation, a reliable and affordable monitoring system is required. This study presents a low-cost intensitymeter using a MEMS WT61C sensor with the STA/LTA detection algorithm, Raspberry Pi 4 for processing, and a Ublox Neo-M8N GNSS module for time and location synchronization. The system supports online and offline modes with a store-and-forward mechanism and delivers alerts via buzzer, SMS, and Telegram. The WT61C was configured with 20 Hz bandwidth and 100 Hz sampling rate. Tests showed the device detected local earthquakes, calculated Peak Ground Acceleration (PGA), and estimated Modified Mercalli Intensity (MMI). In simulations of the Lombok 2018 earthquake (M7.0), it produced PGA values of 0.5704 g (23.3% error) and 0.7495 g (0.8% error) against the reference 0.744 g, both consistent with MMI VIII. SMS was sent serially with 5–7 s latency, while Telegram worked in real time. Validation was limited to a simulator with one dataset, without diverse soil or magnitude scenarios. In conclusion, the system provides an effective, low-cost solution for earthquake intensity monitoring and has potential for early warning applications.

Design and Construction of Low-Cost Seismometer using Geophone Sensor Based on Single Board Computer FAUZAN, RAIHAN AHMAD; RUSANTO, BENYAMIN HERYANTO; SINAMBELA, MARZUKI; TRIHADI, EDWARD
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 13, No 4: Published November 2025
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v13i4.381

Salah satu faktor utama dalam upaya peningkatan sistem pemantauan seismik adalah penyebaran dan interkoneksi jaringan seismograf secara menyeluruh. Penggunaan geophone dapat menjadi solusi alternatif yang potensial dalam membuat low-cost seismograf untuk meningkatkan cakupan dan efisiensi jaringan pemantauan seismik. Penelitian ini bertujuan untuk merancang low-cost seismometer yang terdiri dari sensor geophone, rangkaian signal conditioning, modul ADC ADS1256, GPS Ublox Neo-7M, dan Raspberry Pi 3 Model B+. Data ditampilkan melalui antarmuka berbasis website secara realtime menggunakan protokol komunikasi MQTT dan disimpan dalam format miniSEED. Hasil pengujian menunjukkan tingkat background noise pada sensor yang cukup baik (84.8% titik frekuensi berada dalam batasan NHNM/NLNM), dengan kemampuan mendeteksi gempa lokal pada magnitude ≥3.0. Prototipe ini memberikan solusi low-cost seismograf yang efektif untuk pemantauan seismik.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search