Putting machine learning to use in natural resource management - improving model performance

Machine learning models have proven to be very successful in many fields of research. Yet, in natural resource management, modeling with algorithms such as gradient boosting or artificial neural networks is virtually nonexistent. The current state of research on existing applications of machine lear...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Ulrich J. Frey
Formato:	article
Lenguaje:	EN
Publicado:	Resilience Alliance 2020
Materias:	comparability gradient boosting machine learning natural resource management neural networks social-ecological systems Biology (General) QH301-705.5 Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/4dd39f2766b3446a807ca5e568d2cb28
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4dd39f2766b3446a807ca5e568d2cb28
record_format	dspace
spelling	oai:doaj.org-article:4dd39f2766b3446a807ca5e568d2cb282021-12-02T14:37:54ZPutting machine learning to use in natural resource management - improving model performance1708-308710.5751/ES-12124-250445https://doaj.org/article/4dd39f2766b3446a807ca5e568d2cb282020-12-01T00:00:00Zhttps://www.ecologyandsociety.org/vol25/iss4/art45/https://doaj.org/toc/1708-3087Machine learning models have proven to be very successful in many fields of research. Yet, in natural resource management, modeling with algorithms such as gradient boosting or artificial neural networks is virtually nonexistent. The current state of research on existing applications of machine learning in the field of social-ecological systems is outlined in a systematic literature review. For this purpose, a short introduction on fundamental concepts of neural network modeling is provided. The data set used, a prototypical case study collection of social-ecological systems - the common-pool resources database from the Ostrom Workshop - is described. I answer the question of whether neural networks are suitable for the kind of data and problems in this field, and whether they or other machine learning algorithms perform better than standard statistical approaches such as regressions. The results indicate a large performance gain. In addition, I identify obstacles for adapting machine learning and provide suggestions on how to overcome them. By using a freely available data set and open source software, and by providing the full code, I hope to enable the community to add machine learning to the existing tool box of statistical methods.Ulrich J. FreyResilience Alliancearticlecomparabilitygradient boostingmachine learningnatural resource managementneural networkssocial-ecological systemsBiology (General)QH301-705.5EcologyQH540-549.5ENEcology and Society, Vol 25, Iss 4, p 45 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	comparability gradient boosting machine learning natural resource management neural networks social-ecological systems Biology (General) QH301-705.5 Ecology QH540-549.5
spellingShingle	comparability gradient boosting machine learning natural resource management neural networks social-ecological systems Biology (General) QH301-705.5 Ecology QH540-549.5 Ulrich J. Frey Putting machine learning to use in natural resource management - improving model performance
description	Machine learning models have proven to be very successful in many fields of research. Yet, in natural resource management, modeling with algorithms such as gradient boosting or artificial neural networks is virtually nonexistent. The current state of research on existing applications of machine learning in the field of social-ecological systems is outlined in a systematic literature review. For this purpose, a short introduction on fundamental concepts of neural network modeling is provided. The data set used, a prototypical case study collection of social-ecological systems - the common-pool resources database from the Ostrom Workshop - is described. I answer the question of whether neural networks are suitable for the kind of data and problems in this field, and whether they or other machine learning algorithms perform better than standard statistical approaches such as regressions. The results indicate a large performance gain. In addition, I identify obstacles for adapting machine learning and provide suggestions on how to overcome them. By using a freely available data set and open source software, and by providing the full code, I hope to enable the community to add machine learning to the existing tool box of statistical methods.
format	article
author	Ulrich J. Frey
author_facet	Ulrich J. Frey
author_sort	Ulrich J. Frey
title	Putting machine learning to use in natural resource management - improving model performance
title_short	Putting machine learning to use in natural resource management - improving model performance
title_full	Putting machine learning to use in natural resource management - improving model performance
title_fullStr	Putting machine learning to use in natural resource management - improving model performance
title_full_unstemmed	Putting machine learning to use in natural resource management - improving model performance
title_sort	putting machine learning to use in natural resource management - improving model performance
publisher	Resilience Alliance
publishDate	2020
url	https://doaj.org/article/4dd39f2766b3446a807ca5e568d2cb28
work_keys_str_mv	AT ulrichjfrey puttingmachinelearningtouseinnaturalresourcemanagementimprovingmodelperformance
_version_	1718390948954636288

Putting machine learning to use in natural resource management - improving model performance

Ejemplares similares