Claim Missing Document
Check
Articles

Found 2 Documents
Search

Comparative Analysis of GRU and MLP Models for Extreme Rainfall Nowcasting Using AWS Hartanto; Sajarwo Sanggai; Taswanda Taryo; Naufal Ananda
Journal of Renewable Energy and Smart Device Vol. 3 No. 2 April 2026
Publisher : PT. Global Research Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66314/joresd.v3i2.421

Abstract

Accurate forecasting of rainfall intensity is critical for hydrometeorological disaster mitigation in tropical regions like Indonesia. While high-resolution AWS data provides an opportunity to improve forecasting over conventional manual gauges, processing this volatile time-series data requires advanced computational models. This study comparatively evaluates predictive performance of static feed-forward MLP and sequential memory GRU deep learning architecture. Utilizing a three-year dataset (2022–2024) from three stations representing coastal, lowland, and mountainous topographies, the study reconstructed minute-aggregated AWS data using a sliding window algorithm. This successfully validated the digital sensors against manual Hellmann-type rain gauges, achieving a strong correlation (R > 0.80) for hourly accumulations. Both deep learning models were then trained using historical rainfall, temperature differences, and humidity differences. The empirical results demonstrate that the GRU model quantitatively outperforms the MLP, achieving a higher average classification accuracy of 96.49% (compared to 95.49%) and a lower RMSE of 1.51 mm (compared to 1.59 mm). The GRU’s gating mechanism proved significantly more robust in handling sharp data fluctuations across diverse terrains. However, the analysis revealed a shared structural limitation: both architectures severely underestimated extreme peak rainfall amplitudes. This anomaly stems from the inherent sparsity of extreme weather data and the mathematical conservatism induced by MSE loss function. Ultimately, while the GRU is highly recommended as a reliable frontline trigger for early warning systems, estimating absolute extreme rainfall magnitudes necessitates future exploration of non-standard loss functions and spatial data integration.
An IoT-Based Smart Onboard Weather Station for Maritime Situational Awareness: Calibration, Field Representativeness, and Exploratory Usability Evaluation Santoso Soekirno; Martarizal; Ahmad Furqon; Naufal Ananda
Journal of Renewable Energy and Smart Device Vol. 4 No. 1 August 2026
Publisher : PT. Global Research Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66314/joresd.v4i1.1263

Abstract

Rapidly varying marine weather requires onboard observations that combine measurement quality, spatial context, continuous data delivery, and clear operational interpretation. This study evaluates an Internet of Things (IoT)-based Smart Onboard Weather Station through controlled calibration, moving-vessel field comparison, preliminary data-continuity assessment, and exploratory usability evaluation. The platform is intended to support bridge officers during onboard weather monitoring and shore-based BMKG personnel reviewing vessel observations; the present usability sample represents the latter professional group. The system integrates a Campbell Scientific ClimaVUE sensor, CR1000X datalogger, GPS receiver, digital compass, camera, LTE/4G communication, time-series storage, and a web dashboard. Calibration across three to five set points produced near-linear responses for air temperature (R² = 0.999), relative humidity (R² = 0.995), atmospheric pressure (R² = 0.990), wind speed (R² = 0.999), and wind direction (R² = 0.990), together with parameter-specific correction and dispersion information. A seven-day deployment on the Merak–Bakauheni route from 21 to 27 December 2025 showed the strongest spatial coherence for atmospheric pressure and useful temporal agreement for air temperature, while wind speed produced the largest vessel-to-coastal differences. Data completeness reached 96.75%, representing preliminary operational data continuity under the tested conditions. The archived distance-summary dataset preserves interval-level statistics, while paired-observation counts fall outside the retained metadata and are carried as a reporting limitation. An exploratory SUS assessment with nine meteorological professionals produced a mean score of 81.39. The next readiness step is a controlled crewed pilot on a second vessel, with wind processing and bridge-user evaluation as the primary operational gates.