Probabilistic Classification and Uncertainty Quantification of Sahara Desert Climate Using Feedforward Neural Networks

TL;DR

This paper introduces a probabilistic neural network framework for climate classification, providing uncertainty quantification and temporal analysis of Sahara Desert climate zones over 30 years.

Contribution

It develops an efficient neural network-based method for probabilistic climate classification, capturing uncertainties and temporal dynamics in Sahara climate zones.

Findings

The model accurately classifies Sahara climate zones with uncertainty estimates.

Probabilistic classification reveals transitional zones and climate flux over time.

Comparison shows advantages over traditional deterministic KT classification.

Abstract

Climate classification plays a vital role in agricultural planning, hydrological studies, and climate science. One of the most widely used systems for classifying global climate zones is the K\"oppen-Trewartha (KT) classification. However, the KT classification is fundamentally deterministic, offering discrete labels to spatial locations without accounting for uncertainties in classification. In this paper, we provide a framework for probabilistic modeling of climatic zones. We implement a feedforward artificial neural network (ANN) for classification, allowing for efficient, uncertainty-aware categorization of climatic regions, thereby offering a more nuanced understanding of transitional climate zones compared to traditional deterministic methods. We apply this method to the Sahara Desert region over the 30-year period of 1960 - 1989, using data at more than 400,000 space-time locations from the first 11 years to train our model. We assess the model's short- and long-term classification capabilities to evaluate its stability and accuracy over time. We also compare the probabilistic classification from our model with the traditional KT classification. In addition, we use fluctuation analysis methods to highlight the temporal evolution of climatic zones across the Sahara region and identify areas undergoing significant flux of probabilities of their climate classes, providing insights into broader trends in desertification.