Sophisticated tools for spatio-temporal data exploration

Abstract

: Spatio-temporal data underpin many critical processes such as weather, crop production, wildfire spread and epidemiological and disease function. Models of these processes can reveal changing characteristics in both space and time and can help inform decision-makers. A recent example is during the pandemic years, spatio-temporal models were used to inform public policy. While there are many spatio-temporal modelling methods and packages, tools specifically designed for exploratory data analysis are somewhat lacking. Exploratory data analysis is a vital step in the end-to-end process of statistical and machine learning modelling. A lack of tools for exploratory spatio-temporal data analysis may lead to researchers starting the modelling process prematurely and make suboptimal modelling choices. We aim to fill this gap by contributing stxplore – an R package equipped with useful functionality designed for spatio-temporal data exploration. All functions in stxplore are designed to provide visually useful outputs. Furthermore, all computations can be performed using either data frames or stars objects in the R framework. Data frames are traditional, general purpose data structures in R, used for tabular data, while s tars objects cater for geospatial data. These object classes are defined in the R package stars , which has gained popularity within the research community, and are a newer addition to the R geospatial package ecosystem. The package stxplore can work with either of these objects, i.e. the functions in stxplore can take either data frames or stars objects as input. The