cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Marzuki Sinambela
Contact Email
adm.jocpes@gmail.com
Phone
-
Journal Mail Official
adm.jocpes@gmail.com
Editorial Address
Jl. Bunga Terompet Komplek Cipta Pesona 2 No.D.25, Simpang Selayang, Medan Tuntungan, Medan, 20131, Medan, North Sumatera, Indonesia
Location
Unknown,
Unknown
INDONESIA
Journal of Computation Physics and Earth Science
Published by Yayasan Kita Menulis
ISSN : -     EISSN : 27762521     DOI : https://doi.org/10.63581/JoCPES
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Physics
Journal of Computation Physics and Earth Science (JoCPES) publishes cutting-edge research in computational physics and earth sciences. It offers a platform for researchers to share insights on computational methods, physical sciences, environmental science, and more. Topics include computational physics, material science, meteorology, climatology, geophysics, scientific computing, numerical analysis, earth sciences and etc. JoCPES accepts original research articles. JoCPES welcomes original research in: Computational Physics Computational Methods Physical Sciences Material Science Meteorology Climatology Geophysics Scientific Computing Numerical Analysis Data Analysis Modeling and Simulation Earth Sciences Interdisciplinary Research Environmental Science Physics Applications Physics Data Science Internet Of Things Digital Signal Processing Computer Science Artificial Intelligence Machine Learning Deep Learning
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 55 Documents
 2   3   4   5   6 
Analisis Perbandingan Model Regresi Linier dan XGBoost untuk Mengkaji Dampak ENSO terhadap Curah Hujan di Kota Ternate Tahun 2023 Amra, Firman Almaliky Gapri; Widodo, Anton; Nugraha, Muchamad Rizqy
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.v5i1.02

Abstract

The purpose of this study is to evaluate how well two prediction models—linear regression and XGBoost—perform in assessing how ENSO (El Niño-Southern Oscillation) affects rainfall in Ternate City in 2023. The Meteorology, Climatology, and Geophysics Agency (BMKG) provided monthly rainfall data, while the Bureau of Meteorology (BOM) in Australia provided ENSO index data. Performance indicators such Pearson correlation analysis, the coefficient of determination (R-squared), and mean squared error (MSE) were used in the evaluation. According to the findings, the two models perform differently when it comes to capturing the pattern of the link between rainfall and ENSO; XGBoost is more adaptable but has a tendency to overfit on small amounts of data, whereas linear regression obtains a better R-squared value.
Evaluasi Model XGBoost untuk Prediksi dan Klasifikasi Curah Hujan Menggunakan Data BMKG dan OpenWeather API Syah, Muhammad Saori Isjayan; Nardi; Rachmawardani, Agustina
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.v5i1.03

Abstract

Indonesia, situated between two continents and two oceans, experiences significant climate variability, with rainfall patterns shaped by geographical and topographical factors, as well as phenomena like the El Niño Southern Oscillation (ENSO). Accurate rainfall forecasting plays a critical role in disaster mitigation, agricultural planning, and water resource management. This study focuses on developing a rainfall prediction and classification model using the Extreme Gradient Boosting (XGBoost) algorithm. The model leverages historical rainfall data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG) and real-time data from the OpenWeather API. The output includes rainfall trend graphs and classification of rainfall intensity into categories such as light, moderate, or heavy. Model performance is assessed through metrics like accuracy, precision, RMS (Root Mean Square), and RMSE (Root Mean Square Error). This research highlights the integration of historical and real-time data for weather forecasting and demonstrates the application of advanced machine learning techniques like XGBoost to build robust and precise prediction models. The findings are expected to offer practical insights for disaster risk reduction, agricultural strategy planning, and effective water resource management.
Model Prediksi Konsentrasi PM2.5 di Wilayah Jakarta Menggunakan Algoritma Random Forest Arsy, Muhammad Naufal Afif Al; Yasir, Ahmad Meijlan
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.v5i1.04

Abstract

This study predicts PM2.5 concentrations in Jakarta using the Random Forest algorithm with historical air quality data from 2015 to 2024. Hyperparameter tuning was performed to optimize model performance, focusing on parameters such as n_estimators, max_depth, and min_samples_split. The model achieved a Mean Absolute Error (MAE) of 14.44, a Root Mean Square Error (RMSE) of 18.75, and an R² Score of 0.61. While the model captured general PM2.5 fluctuation patterns, deviations at certain points indicate room for improvement. Descriptive analysis showed an average PM2.5 concentration of 94.46 µg/m³, with peaks up to 209 µg/m³, exceeding healthy air quality thresholds. The model can be integrated into real-time monitoring systems and support data-driven policies. Future work could incorporate meteorological variables and evaluate longer-term trends to enhance accuracy.
Analisis Otomatis Data Suhu Radiosonde Menggunakan Python: Studi Homogenisasi Data dan Tren Iklim yang Diamati di Sta. Bertemu. Kelas I Sultan Iskandar Muda - Banda Aceh Faiz, Muhammad; Marpaung, Hafifuddin Hasfa
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.v5i1.05

Abstract

Radiosonde temperature data serve as a cornerstone for understanding atmospheric dynamics and investigating long-term climate trends. Despite their significance, these datasets are often hindered by challenges such as instrumental biases, shifts in observational protocols, and limited vertical resolution, which can obscure critical atmospheric patterns. This study introduces a Python-based automated framework designed to streamline radiosonde data analysis, emphasizing homogenization, vertical resolution enhancement, and advanced visualization techniques. By utilizing robust libraries such as pandas, matplotlib, and seaborn, the framework effectively mitigates inconsistencies and promotes reproducibility. The findings highlight significant improvements in data quality, allowing for more accurate identification of temperature trends across the troposphere and stratosphere. Additionally, this approach reduces analytical biases and enhances the resolution of key atmospheric processes. The proposed framework contributes a valuable methodology for climate researchers, offering new opportunities to advance studies on atmospheric behavior and climate change dynamics.
Pendekatan Machine Learning untuk Klasifikasi Indian Ocean Dipole (IOD) Menggunakan Model Random Forest dan Decision Tree dengan Data SST, MSLP, dan Total Curah Hujan di Perairan Sumatera Barat Pratama, Muhammad Arya Bintang
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.v5i1.06

Abstract

This research investigates the utilization of machine learning methodologies, particularly Random Forest and Decision Tree algorithms, to categorize Indian Ocean Dipole (IOD) occurrences by employing Sea Surface Temperature (SST), Mean Sea Level Pressure (MSLP), and total precipitation datasets derived from the maritime region adjacent to West Sumatra. The study leverages data amassed from 2020 to 2024, concentrating on diverse climatic scenarios linked to IOD. The efficacy of both algorithms is assessed using evaluative criteria such as accuracy, precision, and recall. The findings reveal that the Random Forest algorithm surpasses the Decision Tree algorithm, attaining an accuracy rate exceeding 85%, with SST recognized as the predominant predictor. These results underscore the promise of machine learning techniques in advancing the comprehension of IOD and its ramifications on regional meteorological trends, thereby facilitating enhanced climate forecasting models and guiding decision-making frameworks for climate adaptation.
Analisis Tren Curah Hujan di Kota Tangerang Menggunakan Regresi Linier dan Random Forest Wardana, Rizaldi Wisnu
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.v5i1.07

Abstract

Rainfall is an important element in the hydrological cycle that has a significant impact on the environment and human life, especially in tropical areas such as Tangerang City. This study aims to analyze annual and monthly rainfall trends and compare the performance of Linear Regression and Random Forest methods in predicting daily rainfall. Daily rainfall data from the Soekarno-Hatta Meteorological Station during the period 2019–2024 are used as model input. The results show that Random Forest has superior performance in capturing complex and extreme rainfall fluctuation patterns, with lower Mean Squared Error (MSE) and higher R-squared (R²) compared to Linear Regression. Linear Regression is only able to predict linear trends simply but is less accurate in handling non-linear variations. This study provides practical contributions to flood risk mitigation, water resource management, and urban infrastructure planning. The development of more accurate prediction models, such as Random Forest, is an important step in supporting climate change adaptation and environmental management in urban areas. Further research is recommended to include additional atmospheric variables and more complex validation techniques to improve prediction accuracy.
Model Arsitektur Jaringan Residual untuk Klasifikasi Cuaca Gambar Saputra, Fauzi Hasbi
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.v5i1.08

Abstract

Weather classification plays an important role in many fields, including agriculture, transportation, and meteorology. Traditional methods for weather recognition are usually based on human observation or sensor networks, which are prone to errors and quite costly. To overcome the limitation, this research implements the Convolutional Neural Network method with a Residual Network model architecture for image-based weather classification. Using a dataset of 1,500 images categorized into five weather conditions cloudy, foggy, rainy, sunny and sunrise. The model training accuracy reached a level of 92%, while the validation accuracy reached a level of 94% and resulted in a testing accuracy of 86.7%. The model training accuracy was high for sunny and sunrise conditions. Accuracy was lower in rainy and foggy weather conditions. This research shows that the ResNet model architecture can provide a low-cost, efficient, and high-accuracy solution for weather classification.Weather classification plays an important role in many fields, including agriculture, transportation, and meteorology. Traditional methods for weather recognition are usually based on human observation or sensor networks, which are prone to errors and quite costly. To overcome the limitation, this research implements the Convolutional Neural Network method with a Residual Network model architecture for image-based weather classification. Using a dataset of 1,500 images categorized into five weather conditions cloudy, foggy, rainy, sunny and sunrise. The model training accuracy reached a level of 92%, while the validation accuracy reached a level of 94% and resulted in a testing accuracy of 86.7%. The model training accuracy was high for sunny and sunrise conditions. Accuracy was lower in rainy and foggy weather conditions. This research shows that the ResNet model architecture can provide a low-cost, efficient, and high-accuracy solution for weather classification.
Perbandingan Metode Random Forest dan LSTM untuk Prediksi Suhu Rosyad, Muhammad Asyril Ar; Maghridlo, Aviv
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.v5i1.09

Abstract

This study compares the performance of Long Short-Term Memory (LSTM) and Random Forest (RF) models in predicting temperature data from Tanjung Priok, Indonesia, using evaluation metrics such as RMSE, MAE, and R² Score. The LSTM model demonstrated its ability to capture temporal dependencies and temperature trends, achieving an R² score of 0.4493 and an MAE of 0.5863. In contrast, the RF model performed better in minimizing prediction errors, with a lower RMSE of 0.6498 and an R² score of 0.4066. While the LSTM model excelled in explaining variance in the temperature data, the RF model was more effective in stable periods, exhibiting lower prediction errors. The results highlight that both models have distinct advantages, with LSTM better suited for capturing long-term temperature trends and RF performing well during periods of stability. Future research could explore hybrid models or further optimization of these techniques to improve prediction accuracy, particularly for dynamic and extreme temperature fluctuations.
Sistem Pemantauan Peringatan Dini Banjir Menggunakan Metode KNN di Kabupaten Bangkalan Ridwan, Iqbal Fariansyah
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.v5i1.10

Abstract

Bangkalan Regency faces serious challenges due to flood disasters that periodically threaten the safety and welfare of the community. The flood phenomenon in this area is caused by a complex combination of geographic and climate factors, including increased extreme rainfall and the dynamics of sea level rise. Annual floods not only cause infrastructure damage but also threaten the livelihoods and lives of residents living around the river flow. This study aims to develop an innovative flood early warning system using the K-Nearest Neighbors (KNN) method to predict potential disasters before floods occur. By using water flow data analysis and machine learning algorithms, this system is designed to provide accurate and timely early estimates. The main advantage of this study is its ability to proactively mitigate disaster risks using modern computer technology. The study produced a prototype of a flood detection and simulation system that can help local governments, related agencies, and the Bangkalan community in taking preventive and mitigation actions at an earlier stage. Therefore, this system is expected to make a significant contribution to reducing the impact of disasters and protecting the lives of Bangkalan Regency residents.
Implementasi Sistem Monitoring Realtime Berbasis Web Menggunakan YOLOv8 untuk Deteksi Green Box dan Capture Otomatis pada Misi Navigasi di Kontes Perahu Indonesia Mahardika, Yobel Eliezer; Aji, Tonny Wahyu; Wiranata, Dimas Aditya; Prasetyaji, Antonius Kukuh
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.v5i1.11

Abstract

This research presents the design and development of a real-time object detection and monitoring system specifically aimed at identifying green box objects using the YOLOv8 model. The system integrates OpenCV for frame-by-frame video processing, MySQL for image storage as Binary Large Objects (BLOBs), and a Flask-based web interface for real-time visualization. Green box objects detected with a confidence score above 0.7 are cropped and stored in the database. A dynamic web interface, updated every 2 seconds using AJAX, enables real-time monitoring and allows users to download the latest detected image for further analysis. Experimental results demonstrate that the YOLOv8 model achieves high detection accuracy, as measured by precision, recall, and mean average precision (mAP). The proposed system effectively combines object detection, data storage, and web-based visualization to provide a robust and scalable solution for real-time monitoring. Tests conducted under real-world conditions confirm the system's efficiency and reliability. Future work may involve hardware acceleration via edge computing, support for multi-object detection, and integration of advanced tracking algorithms to broaden its applicability in autonomous systems and industrial automation.

Page 5 of 6 | Total Record : 55

 2   3   4   5   6 

Filter by Year

2021 2025


Reset
Filter By Issues
All Issue Vol 5 No 1 (2025): Journal of Computation Physics and Earth Science Vol 4 No 2 (2024): Journal of Computation Physics and Earth Science Vol 4 No 1 (2024): Journal of Computation Physics and Earth Science Vol 3 No 2 (2023): Journal of Computation Physics and Earth Science Vol 3 No 1 (2023): Journal of Computation Physics and Earth Science Vol 2 No 2 (2022): Journal of Computation Physics and Earth Science Vol 2 No 1 (2022): Journal of Computation Physics and Earth Science Vol 1 No 2 (2021): Journal of Computation Physics and Earth Science Vol 1 No 1 (2021): Jurnal Fisika Komputasi dan Ilmu Kebumian