Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Computation Physics and Earth Science
Firman Almaliky Gapi Amra
STMKG
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Physics

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

Found 2 Documents
Search

 1 
Classification of Disaster Impact Severity in North Maluku Using Random Forest Based on Spatial-Temporal Characteristics Firman Almaliky Gapi Amra
Journal of Computation Physics and Earth Science (JoCPES) Vol. 6 No. 2 (2026): 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.v6i2.04

Abstract

Disaster impact severity is typically assessed only after casualty and damage data have been collected, even though the spatial-temporal characteristics of an event are known from the outset. This study aims to construct a disaster severity index using multi-component Principal Component Analysis (PCA) and to classify it using only spatial-temporal characteristics, deliberately excluding impact variables as predictors to avoid target leakage. The dataset comprises 239 disaster events in North Maluku Province (2021-2025) sourced from DIBI-BNPB. The severity index was built through log1p transformation, standardization, KMO (0.757) and Bartlett's Test (chi- square=1010.81; p<0.001), and Kaiser-criterion PCA yielding four principal components (cumulative variance 64.44%). The severity class was divided into four quartile-based classes and validated through a monotonic relationship with mean affected/displaced victims and a significant ANOVA test (F=17.574; p<0.001). Classification used five spatial-temporal features (year, month, week, regency/city, disaster type) under a temporal split scheme, comparing Random Forest, XGBoost, and a Dummy Classifier. Random Forest achieved the best performance with a Macro-F1 of 0.146 on the 2025 test set, outperforming the baseline (0.041) though the absolute value remains low. An ablation test revealed that a temporal-only feature scenario achieved the highest Macro-F1 (0.180), indicating limitations in the categorical encoding scheme. Sensitivity analysis confirmed the results are robust to changes in the class scheme (Macro-F1 difference of 0.047). The main contribution of this study is a validated severity-index construction methodology and early empirical evidence on the limitations of spatial- temporal features for early disaster severity classification.
Multi-Hazard Risk Typology and Temporal Trends of Disaster Events in East Nusa Tenggara Province (2008–2025) Firman Almaliky Gapi Amra
Journal of Computation Physics and Earth Science (JoCPES) Vol. 6 No. 2 (2026): 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.v6i2.05

Abstract

East Nusa Tenggara (NTT) Province faces complex multi-hazard threats from hydrometeorological and geological disasters. This study developed a multi-hazard risk typology for 22 regencies/cities in NTT and examined temporal trends in disaster frequency over 2008–2025 (complete years; partial 2026 data excluded). The dataset comprised 1,158 records, adjusted to 1,128.5 real events using fractional weights across eight disaster types. Clustering was evaluated across three feature schemes and two algorithms (K-Means and Agglomerative Ward), with the number of clusters validated through a consensus of Silhouette, Davies-Bouldin, and Calinski-Harabasz indices while avoiding degenerate solutions. Temporal trends and change points were evaluated using the Mann-Kendall and Pettitt tests, preceded by lag-1 autocorrelation (ACF) screening. The selected hazard-only Agglomerative Ward model (k = 6; Silhouette = 0.2105, DBI = 1.205, CHI = 5.28) categorized regions into six distinct typologies, from low-risk to high-frequency flood/extreme-weather clusters, with Sabu Raijua identified as an impact-severity outlier. Auto correlation checks confirmed the validity of test assumptions. The Mann-Kendall and Pettitt tests consistently revealed no statistically significant monotonic trend or change point (p > 0.05) across the province, dominant disaster types, and all clusters. This meaningful null result demonstrates that disaster occurrences in NTT are driven by sharp inter-annual fluctuations rather than long-term trends, emphasizing the necessity of continuous preparedness and differentiated, typology-based mitigation strategies.
Co-Authors