Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Community Development and Disaster Management

LSTM-Based PM2.5 Prediction Enhanced by Polynomial Features: Case Study in South Tangerang Wardani, Wulan Kusuma
Journal of Community Development and Disaster Management Vol 7 No 1 (2025): Journal of Community Development and Disaster Management
Publisher : Institut Agama Islam Sunan Giri Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/jcd.v7i1.6953

Abstract

The significant impact of air pollution, particularly PM2.5, has driven mitigation efforts to reduce health and environmental risks through more accurate prediction systems. In this study, a Deep Learning approach using the LSTM method with the addition of Polynomial transformation features is proposed to predict PM2.5 concentrations. Historical PM2.5 data from South Tangerang City, Banten, was used to train and test the model. The results show that LSTM with polynomial features effectively captures temporal and non-linear patterns in the data, producing accurate and consistent predictions for both training and testing data compared to conventional machine learning methods such as XGBoost and SVR. Polynomial feature transformation significantly improved model performance, as evidenced by the reduction in prediction errors and increased accuracy compared to LSTM without polynomial features. The model also demonstrates adaptability to sudden fluctuations in air quality data. Although the prediction results closely align with actual values, slight discrepancies may arise due to external factors or model limitations. Therefore, the LSTM approach with polynomial feature transformation is an effective and promising method for PM2.5 prediction.
Perancangan Sistem Pembangkit Listrik Tenaga Surya (PLTS) Off-Grid Pada Gedung Perkuliahan Fauzsan, Achmad Yamani; Yunesti, Putty; Wardani, Wulan Kusuma; Soelami, FX Nugroho; Friansa, Koko; Bangun Persada, Guna; Wira Buana, Setiadi
Journal of Community Development and Disaster Management Vol 7 No 1 (2025): Journal of Community Development and Disaster Management
Publisher : Institut Agama Islam Sunan Giri Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/jcd.v7i1.6965

Abstract

Off-Grid Solar Power Plant (PLTS) system planning at Building F of the Sumatra Institute of Technology, South Lampung Regency, Lampung Province is one of the efforts or strategies in reducing the use of conventional electrical energy from the main supplier, namely the State Electricity Company (PLN), and helping to succeed the government's efforts to increase the consumption of new and renewable energy. In PLTS system planning, the aspects that will be analyzed in this research are technical aspects with the help of PVsyst software to collect data regarding technical indicators such as performance ratios and energy production generated by Off-Grid PLTS. In this research, the required land area is 52 m2 from a total of 930 m2 of available land. The simulation results show that the planned rooftop solar system has a capacity of 10.8 kWp using 24 units of AE SOLAR MC144 430-450 W type solar modules, with the capacity of each module being 450 Wp. The PLTS system uses 1 inverter with the type Victron Quattro 48/15000 (15 kW) with a capacity of 15,000 W and uses a battery with the type LUNA2000-15- S0 which has a capacity of 15 kW in each unit. In this study, the solar module received solar irradiation of 4,616 kWh/m2 per day and 1,684 kWh/m2 per year. The production obtained in this study amounted to 14,475 kWh per year. The percentage of the Performance Ratio (PR) value produced by the designed OffGrid PLTS system is 73.01%.