A systematic review of predictor screening methods for downscaling of numerical climate models

Abstract

Effective selection of climate predictors is a fundamental aspect of climate modeling research. Predictor Screening (PS) plays a crucial role in identifying regional climate drivers, reducing noise, expediting convergence, and minimizing time consumption, ultimately leading to the development of robust models. This review delves into the complex landscape of PS techniques within the context of Numerical Climate Modeling (NCM), with a specific focus on their applicability across various Köppen climate classifications and PS model structures. The analysis revealed substantial variations in the performance of PS methods, shedding light on their ability to capture –and prioritize predictors related to precipitation and temperature within distinct climate contexts. Furthermore, the provided methods have been categorized into two subsections: Feature Selection (FS) and Feature Extraction (FE), with FS encompassing filter, wrapper, embedded, and ensemble/hybrid techniques, and FE covering Linear Feature Extraction (LFE), Time-Domain Analysis (TDA), deep learning, and clustering methods. The initial compilation of papers, acquired through a keyword search on Scopus, consisted of 3650 documents. Following a meticulous evaluation process, 206 papers were identified as fitting for inclusion in the literature review, covering the time frame from 1974 to November 3, 2023. In conclusion, the results provide a detailed understanding of the strengths and limitations of each approach, establishing a hierarchy of effectiveness contingent upon the specific climate context. Additionally, insights into promising avenues for future research in this field are offered. This review follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) standard as its foundation.