|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Amazônia Oriental. Para informações adicionais entre em contato com cpatu.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Amazônia Oriental. |
Data corrente: |
31/01/2018 |
Data da última atualização: |
02/05/2018 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
REIS, L. P.; SOUZA, A. L. de; REIS, P. C. M. dos; FREITAS, L. J. M. de; SOARES, C. P. B.; TORRES, C. M. M. E.; SILVA, L. F. da; RUSCHEL, A. R.; RÊGO, L. J. S.; LEITE, H. G. |
Afiliação: |
Leonardo Pequeno Reis, Instituto de Desenvolvimento Sustentável Mamirauá; Agostinho Lopes de Souza, UFV; Pamella Carolline Marques dos Reis, UFV; LUCAS JOSE MAZZEI DE FREITAS, CPATU; Carlos Pedro Boechat Soares, UFV; Carlos Moreira Miquelino Eleto Torres, UFV; Liniker Fernandes da Silva, Universidade Federal do Recôncavo da Bahia; ADEMIR ROBERTO RUSCHEL, CPATU; Lyvia Julienne Sousa Rêgo, UFV; Helio Garcia Leite, UFV. |
Título: |
Estimation of mortality and survival of individual trees after harvesting wood using artificial neural networks in the amazon rain forest. |
Ano de publicação: |
2018 |
Fonte/Imprenta: |
Ecological Engineering, v. 112, p. 140-147, Mar. 2018. |
DOI: |
https://doi.org/10.1016/j.ecoleng.2017.12.014 |
Idioma: |
Inglês |
Conteúdo: |
Modeling individual trees in tropical rain forests in the Amazon allows for the safe use of scarce resources in a sustainable way. Unfortunately, in the Brazilian Amazon, rain forest growth and production models are not yet used to estimate future forest stock. Thus, forest management plans do not present technical-scientific support that guarantees sustainable production of wood throughout the cutting cycle. Therefore, this work aims to estimate the survival and mortality of individual trees in a selectively harvested forest using Artificial Neural Networks (ANN) to support silvicultural decisions in forest management in the Amazon rain forest. In 1979, a selective harvest was carried out, with 72.5 m3 ha-1 in an area of 64 ha in Floresta Nacional do Tapajós, in the state of Pará, Brazil. In 1981, 36 permanent plots were installed at random and inventoried. Nine successive measurements were carried from 1982 to 2012. In the modeling, classification, survival, and mortality, training and ANN testing were performed, using input variables such as: different semi-distance-independent competition indices (DSICI), diameter measured (dbh), forest class (FC), trunk identification class (TIC), competition index (CI), growth groups (GG), liana infestation intensity (liana); and crown lighting (CL); Damage to tree (D) and tree rotting (R). The categorical output variables (Classification) were Dead or Surviving tree. Overall efficiency of the classification was above 89% in training and above 90% in the test for all ANNs. Survival classification hit rate was above 99% in the test and training for all ANNs but the mortality score was low, with hit rates below 6%. The overall Kappa coefficient was below 8% for all ANNs (ranked ?poor?) but all ANNs were above 55% in the survival classification (ranked ?good?). ANN estimates the individual survival of trees more accurately but this does not occur with mortality, which is a rarer event than survival. MenosModeling individual trees in tropical rain forests in the Amazon allows for the safe use of scarce resources in a sustainable way. Unfortunately, in the Brazilian Amazon, rain forest growth and production models are not yet used to estimate future forest stock. Thus, forest management plans do not present technical-scientific support that guarantees sustainable production of wood throughout the cutting cycle. Therefore, this work aims to estimate the survival and mortality of individual trees in a selectively harvested forest using Artificial Neural Networks (ANN) to support silvicultural decisions in forest management in the Amazon rain forest. In 1979, a selective harvest was carried out, with 72.5 m3 ha-1 in an area of 64 ha in Floresta Nacional do Tapajós, in the state of Pará, Brazil. In 1981, 36 permanent plots were installed at random and inventoried. Nine successive measurements were carried from 1982 to 2012. In the modeling, classification, survival, and mortality, training and ANN testing were performed, using input variables such as: different semi-distance-independent competition indices (DSICI), diameter measured (dbh), forest class (FC), trunk identification class (TIC), competition index (CI), growth groups (GG), liana infestation intensity (liana); and crown lighting (CL); Damage to tree (D) and tree rotting (R). The categorical output variables (Classification) were Dead or Surviving tree. Overall efficiency of the classification was above 89% i... Mostrar Tudo |
Palavras-Chave: |
Gestão florestal; Inteligência artificial; Modelagem. |
Thesagro: |
Floresta. |
Categoria do assunto: |
K Ciência Florestal e Produtos de Origem Vegetal |
Marc: |
LEADER 02910naa a2200289 a 4500 001 2086820 005 2018-05-02 008 2018 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.1016/j.ecoleng.2017.12.014$2DOI 100 1 $aREIS, L. P. 245 $aEstimation of mortality and survival of individual trees after harvesting wood using artificial neural networks in the amazon rain forest.$h[electronic resource] 260 $c2018 520 $aModeling individual trees in tropical rain forests in the Amazon allows for the safe use of scarce resources in a sustainable way. Unfortunately, in the Brazilian Amazon, rain forest growth and production models are not yet used to estimate future forest stock. Thus, forest management plans do not present technical-scientific support that guarantees sustainable production of wood throughout the cutting cycle. Therefore, this work aims to estimate the survival and mortality of individual trees in a selectively harvested forest using Artificial Neural Networks (ANN) to support silvicultural decisions in forest management in the Amazon rain forest. In 1979, a selective harvest was carried out, with 72.5 m3 ha-1 in an area of 64 ha in Floresta Nacional do Tapajós, in the state of Pará, Brazil. In 1981, 36 permanent plots were installed at random and inventoried. Nine successive measurements were carried from 1982 to 2012. In the modeling, classification, survival, and mortality, training and ANN testing were performed, using input variables such as: different semi-distance-independent competition indices (DSICI), diameter measured (dbh), forest class (FC), trunk identification class (TIC), competition index (CI), growth groups (GG), liana infestation intensity (liana); and crown lighting (CL); Damage to tree (D) and tree rotting (R). The categorical output variables (Classification) were Dead or Surviving tree. Overall efficiency of the classification was above 89% in training and above 90% in the test for all ANNs. Survival classification hit rate was above 99% in the test and training for all ANNs but the mortality score was low, with hit rates below 6%. The overall Kappa coefficient was below 8% for all ANNs (ranked ?poor?) but all ANNs were above 55% in the survival classification (ranked ?good?). ANN estimates the individual survival of trees more accurately but this does not occur with mortality, which is a rarer event than survival. 650 $aFloresta 653 $aGestão florestal 653 $aInteligência artificial 653 $aModelagem 700 1 $aSOUZA, A. L. de 700 1 $aREIS, P. C. M. dos 700 1 $aFREITAS, L. J. M. de 700 1 $aSOARES, C. P. B. 700 1 $aTORRES, C. M. M. E. 700 1 $aSILVA, L. F. da 700 1 $aRUSCHEL, A. R. 700 1 $aRÊGO, L. J. S. 700 1 $aLEITE, H. G. 773 $tEcological Engineering$gv. 112, p. 140-147, Mar. 2018.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Amazônia Oriental (CPATU) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Caprinos e Ovinos. |
Data corrente: |
24/11/2006 |
Data da última atualização: |
12/06/2024 |
Tipo da produção científica: |
Artigo em Anais de Congresso |
Autoria: |
ARAUJO FILHO, J. A.; FONTELES, F. de A.; CARVALHO, F. C. de; ARAUJO, M. R. A. de; PEREIRA, J. A. |
Afiliação: |
João Ambrósio de Araújo Filho, Embrapa Caprinos (CNPC); MARCELO RENATO ALVES DE ARAUJO, CNPC. |
Título: |
Desempenho produtivo de ovelhas crioulas em suplementação alimentar e sob três sistemas de acasalamento. |
Ano de publicação: |
2006 |
Fonte/Imprenta: |
In: REUNIÃO ANUAL DA SOCIEDADE BRASILEIRA DE ZOOTECNIA, 43., 2006, João Pessoa. Produção animal em biomas tropicais: anais dos simpósios. João Pessoa: Sociedade Brasileira de Zootecnia, 2006. 4 f. |
Idioma: |
Português |
Conteúdo: |
0 experimento foi conduzido na Embrapa Caprinos, Sobral, CE, Brasil com o objetivo de determinar os efeitos da suplementaçao alimentar e do sistema de acasalamento sobre 0 desempenho produtivo de matrizes ovinas crioulas criadas em caatinga manipulada, em urn delineamento experimental inteiramente casualizado, sob 0 sistema de pastoreio rotativo e com uma taxa de lotaçao medio de 3,6 ovinos/ha/ano. A suplementaçao alimentar, ministrada durante a estaçao seca, constou de 200 g de rolao de milho e 300 g de feno de leucena e os sistemas de acasalamento foram a manta continua, a manta anual e a manta a cada oito meses. Na fase de pre-manta, as matrizes nao suplementadas tiveram pesos vivos medias (PVM), na estaçao umida, superiores (P<0,05) aos da estaçao seca, enquanto que as suplementadas tiveram PVM semelhantes (P>0,05), mas, superiores (P<0,05) aos das nao suplementadas, somente na estacao seca. Ao pre-parto, pos-parto e a desmama, os PVM das matrizes suplementadas superaram (P<0,05) os das nao suplementadas, independentemente da estaçao do ano. A fertilidade ao parto na epoca das chuvas foi de 86,3% para as matrizes suplementadas e de 72,7% para as nao suplementadas, enquanto na epoca seca os valores foram de 75,8% e 60,0%, respectivamente. A taxa media de prolificidade foi de 1,64 crias/ano para as matrizes nao suplementadas e 1,77 para as suplementadas. As reprodutrizes suplementadas desmamaram anualmente 15,6 kg PVM de cordeiros e as nao suplementadas 10,6 kg. [Productive performance of Criolla sheep on feed supplementation and under three mating systems]. Abstract: The experiment was carried out at the Fazenda Crioula, Embrapa Caprinos, in Sobral, Ceará, Brazil, with the objective of determining the effects of the feed supplementation and of the mating system on the performance of ewes raised in manipulated caatinga on a complete randomized experimental design, under a rotation grazing system, with a stocking rate of 3.6 sheep/ha/year. The feed supplementation offered during the dry season, consisted of 200 g of ground whole corn ear and 300 g of leucaena hay and the mating systems were continuous mating, annual matting and eight month interval mating. Before mating, the non supplemented ewes had mean living weight (MLW) in the rainy season superior (P<0.05) to those of the dry season, while the supplemented ones presented similar MLW in both season (P>0.05), however, higher (P<0.05) to those of the supplemented ewes, only in the dry season. At before parturition, after parturition and at weaning, the MLW of the supplemented ewes were superior (P<0.05) to those of the non supplemented ewes, at any season of the year. The fertility rate at the rainy season was 86.3% for the supplemented mothers and 72.7% for the non supplemented ones, while, in the dry season, the values were 75.8% and 60.0%, respectively. The mean prolificity rate was 1.64 lamb/year, for the non supplemented ewes and 1.77 lamb/year for the supplemented ones. These produced 15.6 kg of MLW of weaned lamb/ewe/year and the non supplemented mothers born 10,6 kg. Menos0 experimento foi conduzido na Embrapa Caprinos, Sobral, CE, Brasil com o objetivo de determinar os efeitos da suplementaçao alimentar e do sistema de acasalamento sobre 0 desempenho produtivo de matrizes ovinas crioulas criadas em caatinga manipulada, em urn delineamento experimental inteiramente casualizado, sob 0 sistema de pastoreio rotativo e com uma taxa de lotaçao medio de 3,6 ovinos/ha/ano. A suplementaçao alimentar, ministrada durante a estaçao seca, constou de 200 g de rolao de milho e 300 g de feno de leucena e os sistemas de acasalamento foram a manta continua, a manta anual e a manta a cada oito meses. Na fase de pre-manta, as matrizes nao suplementadas tiveram pesos vivos medias (PVM), na estaçao umida, superiores (P<0,05) aos da estaçao seca, enquanto que as suplementadas tiveram PVM semelhantes (P>0,05), mas, superiores (P<0,05) aos das nao suplementadas, somente na estacao seca. Ao pre-parto, pos-parto e a desmama, os PVM das matrizes suplementadas superaram (P<0,05) os das nao suplementadas, independentemente da estaçao do ano. A fertilidade ao parto na epoca das chuvas foi de 86,3% para as matrizes suplementadas e de 72,7% para as nao suplementadas, enquanto na epoca seca os valores foram de 75,8% e 60,0%, respectivamente. A taxa media de prolificidade foi de 1,64 crias/ano para as matrizes nao suplementadas e 1,77 para as suplementadas. As reprodutrizes suplementadas desmamaram anualmente 15,6 kg PVM de cordeiros e as nao suplementadas 10,6 kg. [Productiv... Mostrar Tudo |
Palavras-Chave: |
Brasil; Ceará; Desempenho produtivo; Época seca; Peso vivo; Raça Crioula; Sobral. |
Thesagro: |
Acasalamento; Caatinga; Nutrição Animal; Ovino; Performance; Suplemento Alimentar. |
Thesaurus NAL: |
Brazil; Dry season; Ewes; Liveweight gain; Ruminant nutrition; Semiarid zones; Sheep feeding. |
Categoria do assunto: |
-- |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/35203/1/AAC-Desempenho-produtivo.pdf
|
Marc: |
LEADER 04356nam a2200397 a 4500 001 1532412 005 2024-06-12 008 2006 bl uuuu u00u1 u #d 100 1 $aARAUJO FILHO, J. A. 245 $aDesempenho produtivo de ovelhas crioulas em suplementação alimentar e sob três sistemas de acasalamento.$h[electronic resource] 260 $aIn: REUNIÃO ANUAL DA SOCIEDADE BRASILEIRA DE ZOOTECNIA, 43., 2006, João Pessoa. Produção animal em biomas tropicais: anais dos simpósios. João Pessoa: Sociedade Brasileira de Zootecnia, 2006. 4 f.$c2006 520 $a0 experimento foi conduzido na Embrapa Caprinos, Sobral, CE, Brasil com o objetivo de determinar os efeitos da suplementaçao alimentar e do sistema de acasalamento sobre 0 desempenho produtivo de matrizes ovinas crioulas criadas em caatinga manipulada, em urn delineamento experimental inteiramente casualizado, sob 0 sistema de pastoreio rotativo e com uma taxa de lotaçao medio de 3,6 ovinos/ha/ano. A suplementaçao alimentar, ministrada durante a estaçao seca, constou de 200 g de rolao de milho e 300 g de feno de leucena e os sistemas de acasalamento foram a manta continua, a manta anual e a manta a cada oito meses. Na fase de pre-manta, as matrizes nao suplementadas tiveram pesos vivos medias (PVM), na estaçao umida, superiores (P<0,05) aos da estaçao seca, enquanto que as suplementadas tiveram PVM semelhantes (P>0,05), mas, superiores (P<0,05) aos das nao suplementadas, somente na estacao seca. Ao pre-parto, pos-parto e a desmama, os PVM das matrizes suplementadas superaram (P<0,05) os das nao suplementadas, independentemente da estaçao do ano. A fertilidade ao parto na epoca das chuvas foi de 86,3% para as matrizes suplementadas e de 72,7% para as nao suplementadas, enquanto na epoca seca os valores foram de 75,8% e 60,0%, respectivamente. A taxa media de prolificidade foi de 1,64 crias/ano para as matrizes nao suplementadas e 1,77 para as suplementadas. As reprodutrizes suplementadas desmamaram anualmente 15,6 kg PVM de cordeiros e as nao suplementadas 10,6 kg. [Productive performance of Criolla sheep on feed supplementation and under three mating systems]. Abstract: The experiment was carried out at the Fazenda Crioula, Embrapa Caprinos, in Sobral, Ceará, Brazil, with the objective of determining the effects of the feed supplementation and of the mating system on the performance of ewes raised in manipulated caatinga on a complete randomized experimental design, under a rotation grazing system, with a stocking rate of 3.6 sheep/ha/year. The feed supplementation offered during the dry season, consisted of 200 g of ground whole corn ear and 300 g of leucaena hay and the mating systems were continuous mating, annual matting and eight month interval mating. Before mating, the non supplemented ewes had mean living weight (MLW) in the rainy season superior (P<0.05) to those of the dry season, while the supplemented ones presented similar MLW in both season (P>0.05), however, higher (P<0.05) to those of the supplemented ewes, only in the dry season. At before parturition, after parturition and at weaning, the MLW of the supplemented ewes were superior (P<0.05) to those of the non supplemented ewes, at any season of the year. The fertility rate at the rainy season was 86.3% for the supplemented mothers and 72.7% for the non supplemented ones, while, in the dry season, the values were 75.8% and 60.0%, respectively. The mean prolificity rate was 1.64 lamb/year, for the non supplemented ewes and 1.77 lamb/year for the supplemented ones. These produced 15.6 kg of MLW of weaned lamb/ewe/year and the non supplemented mothers born 10,6 kg. 650 $aBrazil 650 $aDry season 650 $aEwes 650 $aLiveweight gain 650 $aRuminant nutrition 650 $aSemiarid zones 650 $aSheep feeding 650 $aAcasalamento 650 $aCaatinga 650 $aNutrição Animal 650 $aOvino 650 $aPerformance 650 $aSuplemento Alimentar 653 $aBrasil 653 $aCeará 653 $aDesempenho produtivo 653 $aÉpoca seca 653 $aPeso vivo 653 $aRaça Crioula 653 $aSobral 700 1 $aFONTELES, F. de A. 700 1 $aCARVALHO, F. C. de 700 1 $aARAUJO, M. R. A. de 700 1 $aPEREIRA, J. A.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Caprinos e Ovinos (CNPC) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|