A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies

Abstract Several approaches were proposed to describe the geomorphology of drainage networks and the abiotic/biotic factors determining their morphology. There is an intrinsic complexity of the explicit qualification of the morphological variations in response to various types of control factors and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Carlo Donadio, Massimo Brescia, Alessia Riccardo, Giuseppe Angora, Michele Delli Veneri, Giuseppe Riccio
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/84e40cd38a2a44389f6d3641cdcbf6b7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:84e40cd38a2a44389f6d3641cdcbf6b7
record_format	dspace
spelling	oai:doaj.org-article:84e40cd38a2a44389f6d3641cdcbf6b72021-12-02T13:31:11ZA novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies10.1038/s41598-021-85254-x2045-2322https://doaj.org/article/84e40cd38a2a44389f6d3641cdcbf6b72021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85254-xhttps://doaj.org/toc/2045-2322Abstract Several approaches were proposed to describe the geomorphology of drainage networks and the abiotic/biotic factors determining their morphology. There is an intrinsic complexity of the explicit qualification of the morphological variations in response to various types of control factors and the difficulty of expressing the cause-effect links. Traditional methods of drainage network classification are based on the manual extraction of key characteristics, then applied as pattern recognition schemes. These approaches, however, have low predictive and uniform ability. We present a different approach, based on the data-driven supervised learning by images, extended also to extraterrestrial cases. With deep learning models, the extraction and classification phase is integrated within a more objective, analytical, and automatic framework. Despite the initial difficulties, due to the small number of training images available, and the similarity between the different shapes of the drainage samples, we obtained successful results, concluding that deep learning is a valid way for data exploration in geomorphology and related fields.Carlo DonadioMassimo BresciaAlessia RiccardoGiuseppe AngoraMichele Delli VeneriGiuseppe RiccioNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Carlo Donadio Massimo Brescia Alessia Riccardo Giuseppe Angora Michele Delli Veneri Giuseppe Riccio A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
description	Abstract Several approaches were proposed to describe the geomorphology of drainage networks and the abiotic/biotic factors determining their morphology. There is an intrinsic complexity of the explicit qualification of the morphological variations in response to various types of control factors and the difficulty of expressing the cause-effect links. Traditional methods of drainage network classification are based on the manual extraction of key characteristics, then applied as pattern recognition schemes. These approaches, however, have low predictive and uniform ability. We present a different approach, based on the data-driven supervised learning by images, extended also to extraterrestrial cases. With deep learning models, the extraction and classification phase is integrated within a more objective, analytical, and automatic framework. Despite the initial difficulties, due to the small number of training images available, and the similarity between the different shapes of the drainage samples, we obtained successful results, concluding that deep learning is a valid way for data exploration in geomorphology and related fields.
format	article
author	Carlo Donadio Massimo Brescia Alessia Riccardo Giuseppe Angora Michele Delli Veneri Giuseppe Riccio
author_facet	Carlo Donadio Massimo Brescia Alessia Riccardo Giuseppe Angora Michele Delli Veneri Giuseppe Riccio
author_sort	Carlo Donadio
title	A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
title_short	A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
title_full	A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
title_fullStr	A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
title_full_unstemmed	A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
title_sort	novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/84e40cd38a2a44389f6d3641cdcbf6b7
work_keys_str_mv	AT carlodonadio anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT massimobrescia anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT alessiariccardo anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT giuseppeangora anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT micheledelliveneri anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT giuseppericcio anovelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT carlodonadio novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT massimobrescia novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT alessiariccardo novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT giuseppeangora novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT micheledelliveneri novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies AT giuseppericcio novelapproachtotheclassificationofterrestrialdrainagenetworksbasedondeeplearningandpreliminaryresultsonsolarsystembodies
_version_	1718392865548140544

A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies

Ejemplares similares