Predicting coastal algal blooms with environmental factors by machine learning methods

Harmful algal blooms are a major type of marine disaster that endangers the marine ecological environment and human health. Since the algal bloom is a complex nonlinear process with time characteristics, traditional statistical methods often cannot provide good predictions. In this paper, we propose...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Peixuan Yu, Rui Gao, Dezhen Zhang, Zhi-Ping Liu
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Harmful algal bloom Machine learning Feature selection GBDT Feature importance Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/15fe8bd8888b466a98c1735883b26190
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:15fe8bd8888b466a98c1735883b26190
record_format	dspace
spelling	oai:doaj.org-article:15fe8bd8888b466a98c1735883b261902021-12-01T04:43:07ZPredicting coastal algal blooms with environmental factors by machine learning methods1470-160X10.1016/j.ecolind.2020.107334https://doaj.org/article/15fe8bd8888b466a98c1735883b261902021-04-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X20312760https://doaj.org/toc/1470-160XHarmful algal blooms are a major type of marine disaster that endangers the marine ecological environment and human health. Since the algal bloom is a complex nonlinear process with time characteristics, traditional statistical methods often cannot provide good predictions. In this paper, we propose a method based on machine learning with the aim to predict the occurrence of algal blooms by environmental parameters. The features related to algal bloom growth have been experimented for achieving a good prediction of algal concentrations by a combination strategy. We validate the prediction performance on two real datasets from two locations in US and China, i.e., Scripps Pier, California and Sishili Bay, Shandong, respectively. The models and feature subsets have been selected to complete the missing data and predict the phytoplankton concentration. The results demonstrate the efficiency of our method in the short-term prediction of concentrations by selecting appropriate features. The comparison studies prove the advantage of our developed machine learning method. The importance of every features for the prediction performance reveals crucial factors for the outbreak of harmful algal blooms.Peixuan YuRui GaoDezhen ZhangZhi-Ping LiuElsevierarticleHarmful algal bloomMachine learningFeature selectionGBDTFeature importanceEcologyQH540-549.5ENEcological Indicators, Vol 123, Iss , Pp 107334- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Harmful algal bloom Machine learning Feature selection GBDT Feature importance Ecology QH540-549.5
spellingShingle	Harmful algal bloom Machine learning Feature selection GBDT Feature importance Ecology QH540-549.5 Peixuan Yu Rui Gao Dezhen Zhang Zhi-Ping Liu Predicting coastal algal blooms with environmental factors by machine learning methods
description	Harmful algal blooms are a major type of marine disaster that endangers the marine ecological environment and human health. Since the algal bloom is a complex nonlinear process with time characteristics, traditional statistical methods often cannot provide good predictions. In this paper, we propose a method based on machine learning with the aim to predict the occurrence of algal blooms by environmental parameters. The features related to algal bloom growth have been experimented for achieving a good prediction of algal concentrations by a combination strategy. We validate the prediction performance on two real datasets from two locations in US and China, i.e., Scripps Pier, California and Sishili Bay, Shandong, respectively. The models and feature subsets have been selected to complete the missing data and predict the phytoplankton concentration. The results demonstrate the efficiency of our method in the short-term prediction of concentrations by selecting appropriate features. The comparison studies prove the advantage of our developed machine learning method. The importance of every features for the prediction performance reveals crucial factors for the outbreak of harmful algal blooms.
format	article
author	Peixuan Yu Rui Gao Dezhen Zhang Zhi-Ping Liu
author_facet	Peixuan Yu Rui Gao Dezhen Zhang Zhi-Ping Liu
author_sort	Peixuan Yu
title	Predicting coastal algal blooms with environmental factors by machine learning methods
title_short	Predicting coastal algal blooms with environmental factors by machine learning methods
title_full	Predicting coastal algal blooms with environmental factors by machine learning methods
title_fullStr	Predicting coastal algal blooms with environmental factors by machine learning methods
title_full_unstemmed	Predicting coastal algal blooms with environmental factors by machine learning methods
title_sort	predicting coastal algal blooms with environmental factors by machine learning methods
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/15fe8bd8888b466a98c1735883b26190
work_keys_str_mv	AT peixuanyu predictingcoastalalgalbloomswithenvironmentalfactorsbymachinelearningmethods AT ruigao predictingcoastalalgalbloomswithenvironmentalfactorsbymachinelearningmethods AT dezhenzhang predictingcoastalalgalbloomswithenvironmentalfactorsbymachinelearningmethods AT zhipingliu predictingcoastalalgalbloomswithenvironmentalfactorsbymachinelearningmethods
_version_	1718405766128336896

Predicting coastal algal blooms with environmental factors by machine learning methods

Ejemplares similares