Melola Discovery

← Melola Discovery

Journal

A Regime-Aware Deep Learning for Long-Term Hydrometeorological Disaster Forecasting (2008–2029): A PELT-LSTM Framework Applied to Indonesia

Jurnal Geografi : Media Informasi Pengembangan dan Profesi Kegeografian · Vol. 23 No. 1 (2026) · pp. 67–80

DOI
10.15294/jg.v23i1.49495
ISSN
2549-3094, 2549-3078
Published
2026-08-03
Publisher
Universitas Negeri Semarang
Language
eng

Abstract

Indonesia's escalating hydrometeorological disaster frequency demands robust predictive frameworks capable of capturing non-stationary climate dynamics. This study aimed to analyze statistical correlations among disaster types and generate long-term flood frequency projections using advanced computational methods applied to national disaster data. Pearson correlation analysis was first conducted to quantify inter-disaster relationships, revealing strong associations between extreme weather, floods, and landslides (r = 0.79–0.86), alongside inverse relationships with drought. The Pruned Exact Linear Time (PELT) algorithm subsequently identified three significant regime shifts in 2012, 2017, and 2022, confirming the progressive non-stationarity of Indonesia's disaster patterns. A Long Short-Term Memory (LSTM) deep learning model was then trained on these regime-structured data to generate predictive forecasts. The model achieved high directional accuracy, successfully capturing the 2025 peak and 2026 decline, with an RMSE of 816.67 and MAPE of 43.77%. Projections for 2027–2029 estimate flood events reaching 2,278, 2,542, and 2,021 incidents respectively, indicating a sustained high-frequency disaster regime that necessitates urgent adaptive infrastructure and evidence-based climate resilience planning.

Keywords

Collaboration network of the authors

10 authors · 19 co-authorship links · 1 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • National Central University
  • Yogyakarta State University
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Supandi SupandiAffiliation unknown1
Marita AhdiyanaAffiliation unknown1
Nurul KhotimahAffiliation unknown1
Dyah Respati Suryo SumunarAffiliation unknown1
Arif AshariAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/JG/oai, first harvested 5 Nov 2026, last seen 8 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">A Regime-Aware Deep Learning for Long-Term Hydrometeorological Disaster Forecasting (2008–2029): A PELT-LSTM Framework Applied to Indonesia</dc:title>
	<dc:creator xml:lang="en">yolius anggara, Yonatan</dc:creator>
	<dc:creator xml:lang="en">Rosyid Shidiq Hidayatulloh</dc:creator>
	<dc:creator xml:lang="en">Nurul Khotimah</dc:creator>
	<dc:creator xml:lang="en">Bambang Syaeful Hadi</dc:creator>
	<dc:creator xml:lang="en">Suhadi Purwantara</dc:creator>
	<dc:subject xml:lang="en">Changepoint detection</dc:subject>
	<dc:subject xml:lang="en">hydrometeorological disasters</dc:subject>
	<dc:subject xml:lang="en">Indonesia flood projection</dc:subject>
	<dc:subject xml:lang="en">LSTM deep learning</dc:subject>
	<dc:subject xml:lang="en">regime shift</dc:subject>
	<dc:description xml:lang="en">Indonesia's escalating hydrometeorological disaster frequency demands robust predictive frameworks capable of capturing non-stationary climate dynamics. This study aimed to analyze statistical correlations among disaster types and generate long-term flood frequency projections using advanced computational methods applied to national disaster data. Pearson correlation analysis was first conducted to quantify inter-disaster relationships, revealing strong associations between extreme weather, floods, and landslides (r = 0.79–0.86), alongside inverse relationships with drought. The Pruned Exact Linear Time (PELT) algorithm subsequently identified three significant regime shifts in 2012, 2017, and 2022, confirming the progressive non-stationarity of Indonesia's disaster patterns. A Long Short-Term Memory (LSTM) deep learning model was then trained on these regime-structured data to generate predictive forecasts. The model achieved high directional accuracy, successfully capturing the 2025 peak and 2026 decline, with an RMSE of 816.67 and MAPE of 43.77%. Projections for 2027–2029 estimate flood events reaching 2,278, 2,542, and 2,021 incidents respectively, indicating a sustained high-frequency disaster regime that necessitates urgent adaptive infrastructure and evidence-based climate resilience planning.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2026-08-03</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/JG/article/view/49495</dc:identifier>
	<dc:identifier>10.15294/jg.v23i1.49495</dc:identifier>
	<dc:source xml:lang="en">Jurnal Geografi : Media Informasi Pengembangan dan Profesi Kegeografian; Vol. 23 No. 1 (2026): Volume 23 No 1, June 2026; 67-80</dc:source>
	<dc:source>2549-3094</dc:source>
	<dc:source>2549-3078</dc:source>
	<dc:source>10.15294/jg.v23i1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/JG/article/view/49495/10893</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2026 Jurnal Geografi : Media Informasi Pengembangan dan Profesi Kegeografian</dc:rights>
</oai_dc:dc>