INVESTIGADORES
AMOROSO Mariano Martin
artículos
Título:
The Predicting Tree Growth App: an algorithmic approach to modelling individual tree growth
Autor/es:
MAGALHÃES, JULIANA; POLINK, A.; AMOROSO, M.M.; KOHLI, G.; LARSON, BRUCE
Revista:
ECOLOGICAL MODELLING
Editorial:
ELSEVIER SCIENCE BV
Referencias:
Lugar: Amsterdam; Año: 2022
ISSN:
0304-3800
Resumen:
PredictingTreeGrowth is free and open-source application software written in Python 3.7 that allows easy and fast development of predictive models using the Recurrent Neural Network (RNN)/Long Short-Term Memory (LSTM) framework. RNNs have an upgraded architecture able to capture tree growth mechanisms related to time ordering and size dependence. The motivation for this App is to demystify the use of Machine Learning algorithms and allow accessibility of Machine Learning algorithms by the scientific community. Its simple graphical user interface (GUI) provides straightforward tools for building predictive models with the RNN algorithm.
