Natural Hazards and Earth System Sciences
Natural Hazards and Earth System Sciences
NHESS
Articles | Volume 26, issue 1
Articles | Volume 26, issue 1
https://doi.org/10.5194/nhess-26-315-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Collection:
https://doi.org/10.5194/nhess-26-315-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 26, issue 1
Research article
 | 
20 Jan 2026
Research article |  | 20 Jan 2026

Meteorological Drought Trend Analysis and Forecasting Using a Hybrid SG-CEEMDAN-ARIMA-LSTM Model Based on SPI from Rain Gauge Data

Siphamandla Sibiya, Shaun Ramroop, Sileshi Melesse, and Nkanyiso Mbatha

Viewed

Total article views: 5,166 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
3,964 1,076 126 5,166 112 152
  • HTML: 3,964
  • PDF: 1,076
  • XML: 126
  • Total: 5,166
  • BibTeX: 112
  • EndNote: 152
Views and downloads (calculated since 08 Jul 2025)
Cumulative views and downloads (calculated since 08 Jul 2025)

Viewed (geographical distribution)

Total article views: 5,166 (including HTML, PDF, and XML) Thereof 5,166 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 10 May 2026
Download
Short summary
This study aimed to improve drought forecasting in uMkhanyakude, where water scarcity affects agriculture and livelihoods. It analyzed rainfall trends using modified Mann-Kendall and innovative trend analysis on the Standardized Precipitation Index. A hybrid model combining Savitzky–Golay, decomposition methods, and neural networks showed high accuracy, highlighting its value for early drought warning and water resource planning.
Read more
Share
Collection
Water extremes: innovative approaches to managing floods and...
Altmetrics
Final-revised paper
Preprint