Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Jurnal Sains Dasar ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Jurnal Teknik Informatika UNIKA Santo Thomas Social, Humanities, and Educational Studies (SHEs): Conference Series Jurnal Teknik Informatika Unika Santo Thomas (JTIUST)
Rachmawardani, Agustina
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Rancang Bangun Kalibrator untuk Sensor Kadar Air Tanah Aulia Rahman, Marlita; Rachmawardani, Agustina; Sofwan Lukito, Ibnu
Jurnal Sains Dasar Vol 8, No 1 (2019): April 2019
Publisher : Faculty of Mathematics and Natural Science, Universitas Negeri Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jsd.v8i1.38696

Abstract

Kadar air tanah merupakan salah satu unsur iklim yang diamati di BMKG (Badan Meteorologi Klimatologi dan Geofisika). Alat ukur kadar air tanah wajib dikalibrasi minimal 1 tahun sekali. Penelitian ini bertujuan membuat kalibrator untuk sensor kadar air tanah tersebut. Komponen yang digunakan yaitu sensor Profile Probe PR2/6, LCD 20×4, Arduino mega 2560, RTC DS3231, keypad 3x4, micro-SD card, dan adaptor sebagai catu daya. Hasil pengukuran dapat ditampilkan melalui LCD dan aplikasi pada PC (Personal Computer). Pengujian alat dilakukan dalam 4 tahap, yaitu uji komparasi, uji port alat, uji kinerja alat, dan uji tampilan PC. Hasil pengujian komparasi alat menunjukkan bahwa alat dapat beroperasi dengan baik dengan nilai simpangan baku dan ketidakpastian yang masuk dalam batas toleransi WMO sebesar ±5 %. Hasil pengujian lainnya yaitu pengujian port, pengujian kinerja alat, dan pengujian tampilan PC menunjukkan bahwa alat dapat bekerja dengan baik.
Prediksi Banjir menggunakan ANFIS-PCA sebagai Peringatan Dini Bencana Banjir RACHMAWARDANI, AGUSTINA; WIJAYA, SASTRA KUSUMA; PRAWITO, PRAWITO; SOPAHELUWAKAN, ARSHASENA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 2: Published April 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i2.335

Abstract

ABSTRAKDi antara kejadian bencana yang terjadi di Indonesia, 76 persen terdiri dari bencana hidrometeorologi seperti banjir, badai, longsor, dan kebakaran hutan. Provinsi DKI Jakarta sebagai daerah perkotaan sangat rentan terhadap banjir. Persamaan matematis yang kompleks dapat digunakan untuk memodelkan kejadian banjir secara fisik. Sistem pembelajar (machine learning) adalah sistem yang merancang dan mengembangkan algoritma yang menggunakan data historis untuk melakukan prediksi banjir. Dengan menggunakan data ini, sistem pembelajar dapat menghasilkan nilai probabilitas dasar, yang sangat membantu sistem prediksi, memberikan solusi yang lebih hemat biaya dan kinerja yang lebih baik. Prediksi yang akurat dan tepat dapat membantu strategi pengelolaan sumber daya air, analisis kebijakan dan rekomendasi serta pemodelan evakuasi lebih lanjut. Penelitian ini akan dibahas tentang Perancangan Sistem Peringatan Dini Banjir berbasis Ensemble Machine Learning sebagai mitigasi bencana banjir. Hasil dari penelitian menunjukkan nilai RMSE dari algoritma ANFIS – PCA adalah sebesar 0.12 dan koefisen korelasi (R2) sebesar 0.856.Kata kunci: Prediksi Banjir, Machine Learning, ANFIS, ANFIS – PCA ABSTRACTThe nation of Indonesia is prone to disaster, with 76% of natural disasters being hydrometeorological, such as floods, landslides, tropical cyclones, and droughts. Flood occurrences can be physically modeled using complex mathematical equations. Machine Learning serves as a system for designing and developing algorithms that can predict flood events using historical data. Machine learning systems can leverage existing data to produce underlying probability values, making significant contributions to prediction systems that offer better performance and cost-effective solutions. Accurate predictions contribute to water resource management strategies, policy recommendations, and further evacuation modeling. This research will discuss an Early Warning Flood System design based on Ensemble Machine Learning as a flood disaster mitigation measure. The research results show that the RMSE value and coefficient correlation (R2) for the ANFIS - PCA algorithm are 0.12 and 0.856, respectively. Keywords: Flood Early Warning, Machine Learning, ANFIS, ANFIS – PCA
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

Abstract

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

Abstract

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.
State of the Art of Remote Sensing in Flood Early Warning System: Review Article Rachmawardani, Agustina; Giarno, Giarno; Nugroho, Hapsoro A.; Suharni, Suharni; Sucahyono, Dedi; Hariyanto, Hariyanto; Wijaya, Sastra K.
Social, Humanities, and Educational Studies (SHES): Conference Series Vol 5, No 4 (2022): Social, Humanities, and Educational Studies (SHEs): Conference Series
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (827.046 KB) | DOI: 10.20961/shes.v5i4.68977

Abstract

Sebagai negara tropis, Indonesia khususnya Jakarta sebagai ibukota negara mempunyai resiko terjadinya banjir yang cukup tinggi. Dampak banjir akan berpengaruh pada seluruh aspek kehidupan manusia. Selama kejadian banjir, laporan situasi yang tepatwaktu dan terperinci diperlukan oleh otoritas manajemen bencana untuk menemukan dan mengidentifikasi daerah yang terkena dampak  untuk menerapkan mitigasi kerusakan. Peringatan dini  banjir konvensional memanfaatkan data-data pengamatan ground station seperti data curah hujan, ketinggian aliran sungai maupun data debit sungai. Tidak semua wilayah yang terdampak banjir dicover oleh jaringan sensor ground station. Penginderaan jauh menyediakan data yang tepat dan berbiaya rendah dibanding dengan pengamatan lapangan, selain itu sistem penginderaan jauh juga dapat melakukan deteksi banjir lebih tepat dan mendekati real time. Sistem penginderaan jauh pada satelit dapat memberikan banyak informasi yang diperlukan untuk menggambarkan daerah yang terkena dampak banjir, menilai kerusakan, dan input yang tepat pada pemodelan banjir sehingga dapat memprediksi kerentanan banjir di daerah yang terkena dampak banjir.
Co-Authors AA Sudharmawan, AA Aulia Rahman, Marlita Giarno Giarno Hadi, Ahmad Fauzi Faishal HARIYANTO HARIYANTO Marzuki, Sinambela Nugroho, Hapsoro A. Sastra Kusuma Wijaya Sofwan Lukito, Ibnu SOPAHELUWAKAN, ARSHASENA Sucahyono, Dedi Suharni Suharni Trihadi, Edward Wijaya, Sastra K.