dorsal/arxiv
View SchemaArtificial Neural Network Modeling of Forest Tree Growth
| Authors | Christopher Gordon |
|---|---|
| Categories | |
| ArXiv ID | physics/9906012 |
| URL | https://arxiv.org/abs/physics/9906012 |
Abstract
The problem of modeling forest tree growth curves with an artificial neural network (NN) is examined. The NN parametric form is shown to be a suitable model if each forest tree plot is assumed to consist of several differently growing sub-plots. The predictive Bayesian approach is used in estimating the NN output. Data from the correlated curve trend (CCT) experiments are used. The NN predictions are compared with those of one of the best parametric solutions, the Schnute model. Analysis of variance (ANOVA) methods are used to evaluate whether any observed differences are statistically significant. From a Frequentist perspective the differences between the Schnute and NN approach are found not to be significant. However, a Bayesian ANOVA indicates that there is a 93% probability of the NN approach producing better predictions on average.
{
"annotation_id": "5e350671-63b7-4e6f-9b35-81ef7634becc",
"date_created": "2026-03-02T18:01:25.421000Z",
"date_modified": "2026-03-02T18:01:25.421000Z",
"file_hash": "8b35c18a4291f4132fde2af3d33ed4ced67a544651b9d338a3d06c663b7439cb",
"private": false,
"record": {
"abstract": "The problem of modeling forest tree growth curves with an artificial neural\nnetwork (NN) is examined. The NN parametric form is shown to be a suitable\nmodel if each forest tree plot is assumed to consist of several differently\ngrowing sub-plots. The predictive Bayesian approach is used in estimating the\nNN output.\n Data from the correlated curve trend (CCT) experiments are used. The NN\npredictions are compared with those of one of the best parametric solutions,\nthe Schnute model. Analysis of variance (ANOVA) methods are used to evaluate\nwhether any observed differences are statistically significant. From a\nFrequentist perspective the differences between the Schnute and NN approach are\nfound not to be significant. However, a Bayesian ANOVA indicates that there is\na 93% probability of the NN approach producing better predictions on average.",
"arxiv_id": "physics/9906012",
"authors": [
"Christopher Gordon"
],
"categories": [
"physics.data-an"
],
"title": "Artificial Neural Network Modeling of Forest Tree Growth",
"url": "https://arxiv.org/abs/physics/9906012"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "386ad5e1-667b-4852-a57e-12f6277d12f5",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}