Ecosystem modeling using artificial neural networks: An archaeological tool

Prediction of past Normalized Difference Vegetation Index (paleo-NDVI) in Valle de Ambato (Catamarca, Argentina) in the periods of 550–650 and 1550–1650 CE was carried out to test the efficacy of Artificial Neural Network (ANN) to predict past environments for Archaeology. This work shows that both...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Burry, Lidia Susana, Marconetto, María Bernarda, Somoza, Mariano, Palacio, Patricia Irene, Trivi, Matilde Elena, D´Antoni, Héctor
Formato: Artículo publishedVersion
Lenguaje:Inglés
Publicado: Elsevier Ltd 2018
Materias:
Acceso en línea:http://hdl.handle.net/11336/63298
http://suquia.ffyh.unc.edu.ar/handle/11336/63298
Aporte de:
id I10-R181-11336-63298
record_format dspace
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-181
collection Suquía - Instituto de Antropología de Córdoba (IDACOR, CONICET y UNC)
language Inglés
topic ARGENTINA
ARTIFICIAL NEURAL NETWORK
ECOSYSTEM MODELING
HINDCASTING
PALEO-NDVI
Meteorología y Ciencias Atmosféricas
Ciencias de la Tierra y relacionadas con el Medio Ambiente
CIENCIAS NATURALES Y EXACTAS
Historia
Historia y Arqueología
HUMANIDADES
Otras Sociología
Sociología
CIENCIAS SOCIALES
spellingShingle ARGENTINA
ARTIFICIAL NEURAL NETWORK
ECOSYSTEM MODELING
HINDCASTING
PALEO-NDVI
Meteorología y Ciencias Atmosféricas
Ciencias de la Tierra y relacionadas con el Medio Ambiente
CIENCIAS NATURALES Y EXACTAS
Historia
Historia y Arqueología
HUMANIDADES
Otras Sociología
Sociología
CIENCIAS SOCIALES
Burry, Lidia Susana
Marconetto, María Bernarda
Somoza, Mariano
Palacio, Patricia Irene
Trivi, Matilde Elena
D´Antoni, Héctor
Ecosystem modeling using artificial neural networks: An archaeological tool
topic_facet ARGENTINA
ARTIFICIAL NEURAL NETWORK
ECOSYSTEM MODELING
HINDCASTING
PALEO-NDVI
Meteorología y Ciencias Atmosféricas
Ciencias de la Tierra y relacionadas con el Medio Ambiente
CIENCIAS NATURALES Y EXACTAS
Historia
Historia y Arqueología
HUMANIDADES
Otras Sociología
Sociología
CIENCIAS SOCIALES
description Prediction of past Normalized Difference Vegetation Index (paleo-NDVI) in Valle de Ambato (Catamarca, Argentina) in the periods of 550–650 and 1550–1650 CE was carried out to test the efficacy of Artificial Neural Network (ANN) to predict past environments for Archaeology. This work shows that both subtropical Yunga and xerophytic Chaqueña vegetations respond in contrasting fashion to changes in climate forcings. To predict the past an ANN perceptron multilayer model was used. Modern NDVI data and Tree-Ring data were obtained from NOAA-Paleoclimate, and other public sources. These data were used to train the model. Real data and predictions were close (Pearson correlation 0.83–0.90) and warranted the following step, hindcasting. Important paleo-NDVI fluctuations lasting 15 to 20 years were identified in both periods under study. The paleo-NDVI fluctuations in the earlier period were probably related to the unidentified eruption of 583. The fluctuations in the later period appear related to the eruption of 1600 of the Huaynaputina volcano (SW Peru). These findings suggest that the model accurately identified vegetation fluctuations in response to changes in the volcanic forcing. Hence, the ANNs may be considered as apt tools for modeling past environments in support of archaeology.
format Artículo
Artículo
publishedVersion
author Burry, Lidia Susana
Marconetto, María Bernarda
Somoza, Mariano
Palacio, Patricia Irene
Trivi, Matilde Elena
D´Antoni, Héctor
author_facet Burry, Lidia Susana
Marconetto, María Bernarda
Somoza, Mariano
Palacio, Patricia Irene
Trivi, Matilde Elena
D´Antoni, Héctor
author_sort Burry, Lidia Susana
title Ecosystem modeling using artificial neural networks: An archaeological tool
title_short Ecosystem modeling using artificial neural networks: An archaeological tool
title_full Ecosystem modeling using artificial neural networks: An archaeological tool
title_fullStr Ecosystem modeling using artificial neural networks: An archaeological tool
title_full_unstemmed Ecosystem modeling using artificial neural networks: An archaeological tool
title_sort ecosystem modeling using artificial neural networks: an archaeological tool
publisher Elsevier Ltd
publishDate 2018
url http://hdl.handle.net/11336/63298
http://suquia.ffyh.unc.edu.ar/handle/11336/63298
work_keys_str_mv AT burrylidiasusana ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
AT marconettomariabernarda ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
AT somozamariano ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
AT palaciopatriciairene ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
AT trivimatildeelena ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
AT dantonihector ecosystemmodelingusingartificialneuralnetworksanarchaeologicaltool
bdutipo_str Repositorios
_version_ 1764820398177779712