Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach

To effectively plan and manage the use of agricultural land, it is crucial to identify and evaluate the multiple human and environmental factors that influence it. In this study, we propose a model framework to identify the factors potentially explaining the use of agricultural land for wheat, maize...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cláudia M. Viana, Maurício Santos, Dulce Freire, Patrícia Abrantes, Jorge Rocha
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Cropland Interpretability Artificial intelligence xAI LIME Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/214ec55220a846e7910bffcad1440efe
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:214ec55220a846e7910bffcad1440efe
record_format	dspace
spelling	oai:doaj.org-article:214ec55220a846e7910bffcad1440efe2021-12-01T05:00:36ZEvaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach1470-160X10.1016/j.ecolind.2021.108200https://doaj.org/article/214ec55220a846e7910bffcad1440efe2021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21008657https://doaj.org/toc/1470-160XTo effectively plan and manage the use of agricultural land, it is crucial to identify and evaluate the multiple human and environmental factors that influence it. In this study, we propose a model framework to identify the factors potentially explaining the use of agricultural land for wheat, maize, and olive grove plantations at the regional level. By developing a machine-learning model coupled with a model-agnostic approach, we provide global and local interpretations of the most influential factors. We collected nearly 140 variables related to biophysical, bioclimatic, and agricultural socioeconomic conditions. Overall, the results indicated that biophysical and bioclimatic conditions were more influential than socioeconomic conditions. At the global interpretation level, the proposed model identified a strong contribution of conditions related to drainage density, slope, and soil type. In contrast, the local interpretation level indicated that socioeconomic conditions such as the degree of mechanisation could be influential in specific parcels of wheat. As demonstrated, the proposed analytical approach has the potential to serve as a decision-making tool instrument to better plan and control the use of agricultural land.Cláudia M. VianaMaurício SantosDulce FreirePatrícia AbrantesJorge RochaElsevierarticleCroplandInterpretabilityArtificial intelligencexAILIMEEcologyQH540-549.5ENEcological Indicators, Vol 131, Iss , Pp 108200- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cropland Interpretability Artificial intelligence xAI LIME Ecology QH540-549.5
spellingShingle	Cropland Interpretability Artificial intelligence xAI LIME Ecology QH540-549.5 Cláudia M. Viana Maurício Santos Dulce Freire Patrícia Abrantes Jorge Rocha Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
description	To effectively plan and manage the use of agricultural land, it is crucial to identify and evaluate the multiple human and environmental factors that influence it. In this study, we propose a model framework to identify the factors potentially explaining the use of agricultural land for wheat, maize, and olive grove plantations at the regional level. By developing a machine-learning model coupled with a model-agnostic approach, we provide global and local interpretations of the most influential factors. We collected nearly 140 variables related to biophysical, bioclimatic, and agricultural socioeconomic conditions. Overall, the results indicated that biophysical and bioclimatic conditions were more influential than socioeconomic conditions. At the global interpretation level, the proposed model identified a strong contribution of conditions related to drainage density, slope, and soil type. In contrast, the local interpretation level indicated that socioeconomic conditions such as the degree of mechanisation could be influential in specific parcels of wheat. As demonstrated, the proposed analytical approach has the potential to serve as a decision-making tool instrument to better plan and control the use of agricultural land.
format	article
author	Cláudia M. Viana Maurício Santos Dulce Freire Patrícia Abrantes Jorge Rocha
author_facet	Cláudia M. Viana Maurício Santos Dulce Freire Patrícia Abrantes Jorge Rocha
author_sort	Cláudia M. Viana
title	Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
title_short	Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
title_full	Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
title_fullStr	Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
title_full_unstemmed	Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach
title_sort	evaluation of the factors explaining the use of agricultural land: a machine learning and model-agnostic approach
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/214ec55220a846e7910bffcad1440efe
work_keys_str_mv	AT claudiamviana evaluationofthefactorsexplainingtheuseofagriculturallandamachinelearningandmodelagnosticapproach AT mauriciosantos evaluationofthefactorsexplainingtheuseofagriculturallandamachinelearningandmodelagnosticapproach AT dulcefreire evaluationofthefactorsexplainingtheuseofagriculturallandamachinelearningandmodelagnosticapproach AT patriciaabrantes evaluationofthefactorsexplainingtheuseofagriculturallandamachinelearningandmodelagnosticapproach AT jorgerocha evaluationofthefactorsexplainingtheuseofagriculturallandamachinelearningandmodelagnosticapproach
_version_	1718405587644973056

Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach

Ejemplares similares