Format

Send to

Choose Destination
Sci Total Environ. 2018 Dec 15;645:655-661. doi: 10.1016/j.scitotenv.2018.07.123. Epub 2018 Jul 18.

Artificial neural networks: Modeling tree survival and mortality in the Atlantic Forest biome in Brazil.

Author information

1
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: samuel.rocha@ufv.br.
2
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: carlos.eleto@ufv.br.
3
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: jacovine@ufv.br.
4
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: hgleite@ufv.br.
5
Ensoag LLC, Gainesville, 32607, Florida, United States of America. Electronic address: eduardo@ensoag.com.
6
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: karina.neves@ufv.br.
7
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: bruno.schettini@ufv.br.
8
Departamento de Engenharia Florestal, Universidade Federal de Viçosa, 36.570-900 Viçosa, Minas Gerais, Brazil. Electronic address: paulo.villanova@ufv.br.
9
Departamento de Engenharia Florestal, Universidade Federal do Recôncavo da Bahia, 44380-000, Cruz das Almas, Bahia, Brazil. Electronic address: liniker@ufrb.edu.br.
10
Instituto de Desenvolvimento Sustentável Mamirauá, 69.553-225 Tefé, Amazonas, Brazil. Electronic address: leonardo.reis@mamiraua.org.br.
11
Departamento de Entomologia/BIOAGRO, Universidade Federal de Viçosa, 36570-900 Viçosa, Minas Gerais, Brazil. Electronic address: zanuncio@ufv.br.

Abstract

Models to predict tree survival and mortality can help to understand vegetation dynamics and to predict effects of climate change on native forests. The objective of the present study was to use Artificial Neural Networks, based on the competition index and climatic and categorical variables, to predict tree survival and mortality in Semideciduous Seasonal Forests in the Atlantic Forest biome. Numerical and categorical trees variables, in permanent plots, were used. The Agricultural Reference Index for Drought (ARID) and the distance-dependent competition index were the variables used. The overall efficiency of classification by ANNs was higher than 92% and 93% in the training and test, respectively. The accuracy for classification and number of surviving trees was above 99% in the test and in training for all ANNs. The classification accuracy of the number of dead trees was low. The mortality accuracy rate (10.96% for training and 13.76% for the test) was higher with the ANN 4, which considers the climatic variable and the competition index. The individual tree-level model integrates dendrometric and meteorological variables, representing a new step for modeling tree survival in the Atlantic Forest biome.

KEYWORDS:

Artificial intelligence; Prognosis; Tropical forests

PMID:
30029140
DOI:
10.1016/j.scitotenv.2018.07.123
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center