Evaluation of Deep Learning techniques to address environmental issues

Mata Aguilar, Luis (2020). Evaluation of Deep Learning techniques to address environmental issues. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S.I. de Sistemas Informáticos (UPM), Madrid.

Description

Title: Evaluation of Deep Learning techniques to address environmental issues
Author/s:
  • Mata Aguilar, Luis
Contributor/s:
  • Gómez Canaval, Sandra
Item Type: Final Project
Degree: Grado en Ingeniería del Software
Date: August 2020
Subjects:
Freetext Keywords: Deforestación tropical; Imágenes multiespectrales
Faculty: E.T.S.I. de Sistemas Informáticos (UPM)
Department: Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img] PDF - Users in campus UPM only - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (3MB)

Abstract

Los bosques tropicales tienen implicaciones importantes para la conservación de la biodiversidad, cambio climático y necesidades humanas. Una de las principales causas de la reducción de biodiversidad es la deforestación causada por el ser humano. La deforestación es afectada también por el incremento de temperatura más allá de la periferia de los bosques y es causa de otros fenómenos destructivos. En este estudio se evalúa la utilidad de técnicas Deep Learning (DL) junto con el uso de diferentes datasets de imágenes multiespectrales para dirigir uno de los problemas medioambientales más importantes. Los datos usados son abiertos, sometidos a seguros de calidad (QA) y disponibles para el público general para su uso no comercial. Abstract: Tropical forests have important implications for biodiversity, climate change and human needs. One of the main causes of biodiversity reduction is human-driven deforestation. It also affects the surface temperature increment in non-local areas of the forests and are the cause of other destructive phenomena. In this study, the usefulness of deep learning (DL) techniques is evaluated along with the use of diverse remote multispectral sensory imagery datasets to assess environmental issues. The data used is open, submitted to quality assurance (QA) and available to the general public for non-commercial use.

More information

Item ID: 64923
DC Identifier: http://oa.upm.es/64923/
OAI Identifier: oai:oa.upm.es:64923
Deposited by: Biblioteca Universitaria Campus Sur
Deposited on: 22 Oct 2020 13:57
Last Modified: 22 Oct 2020 13:57
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM