A novel random forest approach to revealing interactions and controls on chlorophyll concentration and bacterial communities during coastal phytoplankton blooms

Yiwei Cheng,Ved N Bhoot,Marilou P Sison-Mangus,Raphael Kudela,Michelle E Newcomer,Karl Kumbier,James B Brown

doi:10.1038/s41598-021-98110-9

Abstract

Increasing occurrence of harmful algal blooms across the land–water interface poses significant risks to coastal ecosystem structure and human health. Defining significant drivers and their interactive impacts on blooms allows for more effective analysis and identification of specific conditions supporting phytoplankton growth. A novel iterative Random Forests (iRF) machine-learning model was developed and applied to two example cases along the California coast to identify key stable interactions: (1) phytoplankton abundance in response to various drivers due to coastal conditions and land-sea nutrient fluxes, (2) microbial community structure during algal blooms. In Example 1, watershed derived nutrients were identified as the least significant interacting variable associated with Monterey Bay phytoplankton abundance. In Example 2, through iRF analysis of field-based 16S OTU bacterial community and algae datasets, we independently found stable interactions of prokaryote abundance patterns associated with phytoplankton abundance that have been previously identified in laboratory-based studies. Our study represents the first iRF application to marine algal blooms that helps to identify ocean, microbial, and terrestrial conditions that are considered dominant causal factors on bloom dynamics.

Highlights

Increasing occurrence of harmful algal blooms across the land–water interface poses significant risks to coastal ecosystem structure and human health
We demonstrate the utility of a novel Random Forest (RF) algorithm, iterative random forest[39], in extracting stable nonlinear interactions in two algal bloom related biological scenarios in Northern California, USA
The novel iterative random forest model was applied to two algal bloom related cases along the California coast to identify key governing factors and stable interactions surrounding: (1) phytoplankton abundance in response to coastal conditions and inland nutrient fluxes, and (2) microbial abundance and harmful algal bloom environmental and biological conditions

Summary

Introduction

Increasing occurrence of harmful algal blooms across the land–water interface poses significant risks to coastal ecosystem structure and human health. A novel iterative Random Forests (iRF) machine-learning model was developed and applied to two example cases along the California coast to identify key stable interactions: (1) phytoplankton abundance in response to various drivers due to coastal conditions and land-sea nutrient fluxes, (2) microbial community structure during algal blooms. Studies along the U.S East Coast of Florida have pointed to elevated nitrogen and phosphorus concentrations in agricultural runoff as a major cause of these toxic algae o utbreaks[15,16,17], while Howard et al.[18] reported that in southern California, wastewater effluent can provide a significant source of nitrogen to coastal waters, promoting the development of HABs. In addition to the abiotic factors, biotic factors such as microbial community assemblage have been hypothesized to be key factors that dynamically interact with HAB. The synergistic interactions of both biotic and abiotic conditions in regulating HAB occurrences remain a key knowledge gap in phytoplankton bloom ecology

Methods

Results

Conclusion