Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Samudra Geografi International Journal of Geography, Social, and Multicultural Education (IJGSME)
Yonatan Yolius Anggara
Universitas Negeri Yogyakarta
Humanities Earth & Planetary Sciences Education Environmental Science Social Sciences

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

Found 2 Documents
Search

 1 
PREDICTING GLOBAL NATURAL DISASTER DURATIONS: A COMPARATIVE ANALYSIS OF SEQUENTIAL TREE ENSEMBLES VERSUS DISTANCE-BASED HYPERSPACE MAPPING UNDER EXTREME OUTLIERS Yonatan Yolius Anggara
Jurnal Samudra Geografi Vol 9 No 2 (2026)
Publisher : Program Studi Pendidikan Geografi, Fakultas Keguruan dan Ilmu Pendidikan, Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33059/jsg.v9i2.14884

Abstract

Temporal estimation, specifically predicting the exact continuous duration a natural disaster will last from day one, remains a major operational bottleneck in global emergency management, despite rapid advancements in spatial mapping. This study aims to evaluate and compare the predictive performance of two structurally distinct non-linear machine learning algorithms: the Gradient Boosting Regressor and Support Vector Regression (SVR) utilizing a Radial Basis Function (RBF) kernel. The methodology employs a non-linear quantitative predictive pipeline executed via Python, utilizing empirical historical crisis records extracted from the Global Disaster Alert and Coordination System (GDACS) repository. The final feature matrix integrates localized country profiles, hazard typologies, dynamic environmental severity scales, and monthly seasonal components. The empirical results reveal a sharp contrast in computational performance between the two architectures. The sequential tree-based Gradient Boosting framework demonstrated exceptional estimation capacity, achieving an outstanding Coefficient of Determination (R2) score of 0.9818, with a minimal Mean Absolute Error (MAE) of only 4.1045 days and a robust Root Mean Squared Error (RMSE) of 6.1378 days. Conversely, the distance-based SVR architecture experienced a structural collapse, yielding an R2 score of only 0.1587 and a severely inflated RMSE of 41.7480 days, exposing its critical vulnerability and disorientation when handling heavily skewed target distributions and heavy-tailed temporal outliers. These findings underscore that embedding high-performance ensemble tree structures into digital Decision Support Systems (DSS) can provide highly precise emergency timeline projections from day one, effectively enabling a proactive, data-driven orchestration of humanitarian logistics.
Decoding Climate Teleconnections: An Asymmetric Time-Lag Analysis of the Oceanic Niño Index and Chikungunya Dynamics in Indonesia, 2013–2023 Yonatan Yolius Anggara; Ery Surya Sevriana
International Journal of Geography, Social, and Multicultural Education Vol. 4 No. 2 (2026): 1 October 2026
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/ijgsme.v4n2.p55-64

Abstract

Raw macro-climatic and epidemiological time series are inherently prone to non-stationary biases and linear seasonal trends, causing spurious correlations that mask genuine environmental teleconnections. This study aimed to evaluate and measure the long-distance relationship between the global Oceanic Niño Index (ONI) and local Chikungunya virus (CHIKV) transmission dynamics in Indonesia from January 2012 to December 2023 (n = 144 months). Methodologically, a quantitative associative time-series design was employed within RStudio. Both datasets exhibited non-normal distributions (p=0.000) and raw non-stationarity via Augmented Dickey-Fuller testing (p>0.05). To eliminate mathematical bias, a first-order differencing transformation was applied, successfully achieving stationarity (p=0.0100). The Cross-Correlation Function (CCF) was then calculated across an interaction window from Lag -6 to Lag +6 months. The results revealed a highly dynamic double-peak epidemiological pattern, peaking in 2013 (15,324 cases) and 2023 (6,049 cases). While no instantaneous correlation occurred at Lag 0 (r=-0.0180), a significant, optimal positive cross-correlation emerged at Lag -6 (r=0.1246). This confirms an asymmetric teleconnection where an increase in the ONI—shifting toward an El Niño phase—preceding the current period by six months directly drives increased Chikungunya outbreaks in Indonesia, providing a vital baseline for climate-based Early Warning Systems.
Co-Authors Ery Surya Sevriana