Technical notes

A spatial model for sporadic tree species distribution in support of tree oriented silviculture


Abstract


This technical note describes how a spatial model for sporadic tree species distribution in the territory of the Unione di Comuni Montana Colline Metallifere (UCMCM) was built using the Random Forest (RF) algorithm and 48 predictors, including reflectance values from ground cover - provided by satellite sensors - and ecological factors. The  P.Pro.SPO.T. project - Policy and Protection of Sporadic tree species in Tuscany forest (LIFE 09 ENV/IT/000087) is currently carried out in this area with the purpose of initiating the implementation of tree oriented silviculture in the Tuscany forests. Tree oriented silviculture aims at obtaining both forest biodiversity protection and local production of valuable timber. After creating a map showing the probability of presence of sporadic tree species, it was possible to identify the most suitable areas for sporadic tree species which are under protection according to the regulation of the Tuscany Region.Using data and software provided free of charge, and applying the RF algorithm, distribution models could be developed in order to identify the most suitable areas for the application of tree oriented silviculture. This can provide a support to forestry planning that includes tree oriented silviculture, thus reducing its implementation cost.

Keywords

sporadic tree species; distribution; tree oriented silviculture; forest biodiversity; random forests; GRASS GIS

Full Text:

PDF


DOI: http://dx.doi.org/10.12899/asr-751

References


Attorre F., Alfò M., De Sanctis M., Francesconi F., Bruno F. 2007 - Comparison of interpolation methods for mapping climatic and bioclimatic variables at regional scale. International Journal of Climatology 27 (13): 1825-1843.

Boslaugh S., Watters P.A. 2008 - Statistics in a Nutshell. O’ Reilly Media, Inc. 480 p.

Breiman L. 1996 - Technical report. Out-of-bag estimation. Department of Statistics, University of California, 13 p.

Breiman L. 2001 - Random forests. Machine Learning 45 (1): 5-32.

Catani F., Lagomarsino D., Segoni S., Tofani V. 2013 - Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues. Natural hazards and Earth System Sciences 13: 2815-2831

Cunningham P., Delaney S.J. 2007 - k-Nearest Neighbor Classifiers. Technical Report UCD-CSI-2007-4. School of Computer Science and Informatics, University College Dublin, 17 p.

Dunlap Brooks A. 2007 - Knnflex: a more flexible KNN. [Online]. Available: http://cran.cermin.lipi.go.id/web/packages/knnflex/index.htm [2013]

Emmert-Streib F., Dehmer M. 2010 - Medical biostatistics for complex diseases. Wiley-Blackwell Publishing, 30 p. GRASS Development Team 2012 - Geographic Resources Analysis Support System (GRASS) Software. Open Source Geospatial Foundation Project. [Online] Available: http://grass.osgeo.org [2013].

Jain A.K., Jianchang M., Mohiuddin K.M. 1996 - Artificial neural networks: A tutorial. IEEE Computer 29 (3): 31-44.

Liaw A., Wiener M. 2002 - Classification and regression by Random Forest. R News 2 (3): 18-22. [Online]. Available: http://CRAN.R-project.org/doc/Rnews/ [2013].

Lloyd D. 1990 - A phenological classification of terrestrial vegetation cover using shortwave vegetation index imagery. International Journal of Remote Sensing, 11: 2269 - 2279.

Mori P., Bruschini S., Buresti Lattes E., Giulietti V., Grifoni F., Pelleri F., Ravagni S., Berti S., Crivellaro A. 2007 - La selvicoltura delle specie sporadiche in Toscana. Manuale n. 3 “Supporti tecnici alla Legge Regionale Forestale della Toscana”. Editori ARSIA e Regione Toscana, 366 p.

Pebesma E., Edzer J. 2004 - Multivariable geostatistics in S: the gstat package. Computers & Geosciences 30: 683-691.

Pelleri F., Giulietti V., Sansone D., Samola A., Nitti D. 2010 - Valorizzazione delle rosacee arboree. Esperienze nei cedui delle Colline Metallifere (GR). Sherwood - Foreste ed Alberi Oggi 160 (2): 5-11.

R Development Core Team 2013 - R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0. [Online]. Available: http://www.R-project.org. [2013].

Regione Toscana 1998 - Boschi e macchie di Toscana, volume 3, Inventario Forestale. Edizioni Regione Toscana, 219 p.

Schliep K., Hechenbichler K. 2013 - Kknn: Weighted k-Nearest Neighbors Classification, Regression and Clustering. [Online]. Available: http://cran.r-project.org/web/packages/kknn/index.html [2013]

Strobl C., Boulesteix A.L., Kneib T., Augustin T., Zeileis A. 2008 - Conditional variable importance for random forests. BMC Bioinformatics 9: 307.

Strobl C., Malley J., Tutz G. 2009 - An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests. Psychological methods 14 (4): 323-348.




Copyright (c)



Creative Commons License

All texts reported in and all materials directly downloadable from this page are licensed under a Creative Commons Attribution 4.0 International License.