trec: An R package for trend estimation and classification to support integrated assessment of the marine ecosystem and environmental factors

TL;DR

The paper introduces an R package called trec that implements a trend estimation and classification approach for multivariate time series in marine ecosystem assessment, enhancing stakeholder communication.

Contribution

This work provides a new R package version of the TREC method with revised trend estimation, classification features, and automatic icon assignment, based on the original MATLAB implementation.

Findings

The package enables trend estimation from multivariate data.

It classifies patterns into categories with automatic icon assignment.

It facilitates communication among marine ecosystem stakeholders.

Abstract

Solvang and Planque (2020) provided a trend estimation and classification (TREC) approach to estimating dominant common trends among multivariate time series observations. This approach was developed to improve communication among stakeholders like marine managers, industry representatives, non-governmental organizations, and governmental agencies as they investigate the common tendencies between a biological community in a marine ecosystem and the local environmental factors. The entire calculation procedure was originally implemented using MATLAB (ver.R2018b). In this paper, we present R package trec, which was motivated by the requests of readers of the Journal of Marine Science, published by the International Council for the Exploration of the Sea. The tasks of trend estimation and classification in the original program have been revised, and new features include an automatic icon assignment algorithm using a multinomial logistic discriminator. Implementation of this package involves three partitions corresponding to TREC1) estimating trends from observed time series data; TREC2) classifying two/three rough patterns; and TREC3) generating a table summarizing categories of common configurations and the automatic icon assignments to them.