Monthly Precipitation Outlooks for Mexico Using El Nino Southern Oscillation Indices Approach

The socioeconomic sector increasingly relies on accessible and cost-effective tools for predicting climatic conditions. This study employs a straightforward decision tree classifier model to identify similar monthly ENSO (El Niño Southern Oscillation) conditions from December 2000 to November 2023,...

Full description

Saved in:
Bibliographic Details
Published in:Atmosphere 2024-08, Vol.15 (8), p.981
Main Authors: Gonzalez-Gonzalez, Miguel Angel, Corrales-Suastegui, Arturo
Format: Article
Language:English
Subjects:
Climate
Climatic conditions
Cooling
decision tree classifier model
Decision trees
Developing countries
Drought
Dry season
Effectiveness
El Nino
El Nino phenomena
El Nino-Southern Oscillation event
ENSO3.4 Indices
Environmental aspects
Forecast accuracy
hindcast
LDCs
Measurement
Monthly
Monthly precipitation
Performance evaluation
Precipitation
Precipitation (Meteorology)
Rain
Rainy season
Seasons
Software
Southern Oscillation
Southern Oscillation Index
Spring
Spring (season)
Summer
Variability
Weather forecasting
Wet season
Winter
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The socioeconomic sector increasingly relies on accessible and cost-effective tools for predicting climatic conditions. This study employs a straightforward decision tree classifier model to identify similar monthly ENSO (El Niño Southern Oscillation) conditions from December 2000 to November 2023, using historically monthly ENSO Indices data from December 1950 to November 2000 as a reference. The latter is to construct monthly precipitation hindcasts for Mexico spanning from December 2000 to November 2023 through historically high-resolution monthly precipitation rasters. The model’s performance is evaluated at a global and local scale across seasonal periods (winter, spring, summer, and fall). Assessment using global Hansen–Kuiper Skill Score and Heidkee Skill Score metrics indicates skillful performance across all seasons (>0.3) nationwide. However, local metrics reveal a higher spatial percent of corrects (>0.40) in winter and spring, corresponding to dry seasons, while a lower percent of corrects (
ISSN:2073-4433
2073-4433
DOI:10.3390/atmos15080981