# Environment, taxonomy, and socioeconomics predict non-imperilment in freshwater fishes

## TL;DR

This study uses machine learning to identify factors that predict which freshwater fish species are at risk of extinction, combining environmental, socioeconomic, and biological data.

## Contribution

The novel contribution is a machine learning framework that integrates global environmental, socioeconomic, and species-level data to predict freshwater fish imperilment.

## Key findings

- The model achieves 90.1% accuracy in predicting non-imperiled species and 81.8% for imperiled species.
- Key predictors include habitat variables, taxonomic order, hydrological characteristics, and disturbance indicators.
- The study highlights the interplay between ecology, geography, and human pressures in determining species imperilment.

## Abstract

Freshwater fishes are among the most threatened taxa, yet conservation assessments remain incomplete for many species. Freshwater fishes provide essential ecosystem services such as food security, recreational opportunities, and cultural significance. Despite heavy alterations to freshwater ecosystems, the reasons for species’ sensitivity and resistance to imperilment are unclear. To address this need, we develop a machine learning framework to predict global imperilment status for 10,631 freshwater fish species using a comprehensive set of environmental, socioeconomic, and intrinsic species-level predictors. Using updated IUCN Red List data, we train and validate Random Forest classifiers to distinguish imperiled (Vulnerable, Endangered, Critically Endangered) from non-imperiled species. We examine the relative influence of 52 variables derived from 12 global sources describing extrinsic environmental and socioeconomic factors and intrinsic species-specific characteristics. Our models achieve higher accuracy for non-imperiled species (90.1%) compared to imperiled species (81.8%), reflecting the greater heterogeneity of threats and conditions driving imperilment. Across models, key predictors include habitat variables, taxonomic order, hydrological characteristics, and disturbance indicators, underscoring the interplay between ecology, geography, and human pressures. This integrative, reproducible approach demonstrates the utility of machine learning for guiding proactive conservation and provides a scalable framework for global biodiversity risk assessment.

Freshwater ecosystems and biodiversity are declining quickly. By integrating global environmental, socioeconomic, and biological data, this study identifies the key conditions associated with imperilment of freshwater fishes.