Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JOURNAL OF APPLIED INFORMATICS AND COMPUTING Journal of Intelligent Networks and IoT Global
Cahya Sugiarto
Sekolah Tinggi Meteorologi Klimatologi Dan Geofisika
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Analysis of LSTM, BiLSTM, Stacked LSTM, and Attention-LSTM for Multi-Resolution Rainfall Forecasting in Bali Muhammad Nur Rizqi; Cahya Sugiarto; Wisnu Syahid
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13615

Abstract

Accurate rainfall forecasting remains challenging in tropical islands such as Bali, Indonesia, where localized convective rainfall limits the reliability of physics-based models. While deep learning architectures based on Long Short-Term Memory (LSTM) are increasingly used for rainfall forecasting, most prior studies compare LSTM variants at a single temporal resolution without a classical baseline, leaving it untested whether their reported advantage holds across resolutions or is an artifact of the resolution chosen. This study evaluates four recurrent architectures — LSTM, BiLSTM, Stacked LSTM, and Attention-LSTM — for univariate rainfall forecasting at daily, decadal, and monthly resolutions, using 26 years (2000–2025) of observations from a BMKG station in Bali, benchmarked against three classical baselines (Persistence, Climatology, and ARIMA) and tuned via random search. Results show that inter-architecture differences within a single resolution are small and inconsistent, with no architecture winning across all resolutions: Stacked LSTM is marginally best at daily (RMSE 15.26 mm/day) and decadal (73.53 mm/decade) scales, while BiLSTM leads at the monthly scale (154.64 mm/month). More critically, the deep learning models' advantage over classical baselines is strongly resolution-dependent: substantial at daily and decadal resolutions, but nearly indistinguishable from Persistence and ARIMA at the monthly resolution, where only 312 training sequences are available. These findings indicate that model selection for rainfall forecasting should be conditioned on temporal resolution and data availability rather than treated as a fixed architectural choice, and that simpler LSTM models offer a more computationally efficient default than their more complex variants for tropical, data-limited settings.
Evaluasi Performa Random Forest Dalam Prediksi Thunderstorm Berbasis Indeks Labilitas Atmosfer Di Cilacap Cahya Sugiarto; Resti Maulina Chusnul Chotimah; Yosafat Donni Haryanto
Journal Of Intelligent Networks and IoT Global Vol 4 No 1 (2026)
Publisher : Universitas Indo Global Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jinig.v4i1.7451

Abstract

Thunderstorm (TS) merupakan salah satu fenomena cuaca signifikan yang berpotensi menimbulkan dampak hidrometeorologi, sehingga diperlukan pendekatan prediktif berbasis parameter udara atas untuk meningkatkan upaya mitigasi. Penelitian ini bertujuan membangun model prediksi kejadian TS di wilayah Cilacap menggunakan indeks labilitas atmosfer yang dihitung dari data radiosonde serta observasi cuaca permukaan. Dataset mencakup periode 2020–2024 dan terdiri dari lima indeks labilitas atmosfer, yaitu Showalter Index (SI), Lifted Index (LI), K-Index (KI), Totals Totals Index (TT), dan Convective Available Potential Energy (CAPE), yang dipadukan dengan data present weather untuk menentukan label kejadian TS. Model Random Forest Classifier digunakan dengan pembagian data latih dan uji sebesar 7:3, serta pengaturan class_weight = 'balanced' untuk menangani ketidakseimbangan kelas. Hasil evaluasi menunjukkan akurasi sebesar 79% dan nilai Area Under Curve (AUC) sebesar 0.74 yang mengindikasikan kemampuan diskriminasi model berada pada kategori cukup baik. Analisis feature importance menunjukkan bahwa KI merupakan prediktor paling dominan, diikuti TT, SI, dan LI, sedangkan CAPE memberikan kontribusi terendah. Temuan ini menunjukkan bahwa pemodelan kejadian thunderstorm berbasis indeks labilitas atmosfer menggunakan algoritma Random Forest memiliki potensi diterapkan sebagai pendekatan prediktif pada wilayah Cilacap.
Co-Authors Muhammad Nur Rizqi Resti Maulina Chusnul Chotimah Wisnu Syahid Yosafat Donni Haryanto