Abstract
In forestry, many fundamental spatial processes cannot be measured directly and data on spatial patterns are used as a surrogate for studying processes. To characterize the outcomes of a dynamic process in terms of a spatial pattern, we often consider the probability of certain outcomes over a large area rather than on the scale of the particular process. In this chapter we demonstrate data mining approaches that leverage the growing availability of forestry-related spatial data sets for understanding spatial processes. We present classification and regression trees (CART) and associated methods, including boosted regression trees (BRT) and random forests (RT). We demonstrate how data mining or machine learning approaches are useful for relating spatial patterns and processes. Methods are applied to a wildfire data and covariate data are used to contextualize the quantified patterns. Results indicate that fire patterns are mostly related to processes influenced by people. Given the growing number of multi-temporal and large area datasets on forests and ecology machine learning and data mining approaches should be leveraged to quantify dynamic space-time relationships.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Amman G (1977) Role of the mountain pine beetle in lodgepole pine ecosystems: impact on succession. In: Mattson WJ (ed) The role of arthropods in forest ecosystems. New York, Springer-Verlag, pp 3–18
Anderson NM, Germain H, Bevilacqua E (2011) Geographic information system-based spatial analysis of sawmill wood procurement. J For 109:34–42
Aukema BH, Carroll AL, Zhu J, Raffa KF, Sickley TA, Taylor SW (2006) Landscape level analysis of mountain pine beetle in British Columbia, Canada: spatiotemporal development and spatial synchrony within the present outbreak. Ecography 29:427–441
Axelson JN, Alfaro RI, Hawkes BC (2010) Changes in stand structure in uneven-aged lodgepole pine stands impacted by mountain pine beetle epidemics and fires in central British Columbia. For Chron 86:87–99
Bailey TC, Gatrell AC (1995) Interactive spatial data analysis, vol 413. Longman Scientific & Technical, Essex
Berk RA (2008) Statistical learning from a regression perspective, vol 14. Springer, New York
Bessie A, Johnson E (1995) The relative importance of fuels and weather on fire behaviour in subalpine forests. Ecology 76:747–762
Bigler C, Kulawkowski D, Veblen TT (2005) Multiple disturbance interactions and drought influence fire severity in rocky mountain subalpine forests. Ecology 86:3018–3029
Bone C, Wulder MA, White J, Robertson C, Nelson TA (2013) A GIS-based risk rating of forest insect outbreaks using aerial overview surveys and the local Moran's I statistic. Appl Geogr 40:161–170
Bourbonnais ML, Nelson TA, Cattet MRL, Darimont CT, Stenhouse GB (2013b) Spatial analysis of factors influencing long-term stress in the grizzly bear (Ursus arctos) population of Alberta, Canada. PLoS One 8(12):e83768. doi:10.1371/journal.pone.0083768
Bourbonnais ML, Nelson TA, Wulder MA (2013a) Geographic analysis of the impacts of mountain pine beetle infestation on forest fire ignition. Can Geogr/Le Géographe Canadien 58(2):188–202. doi:10.1111/j.1541-0064.2013.12057.x
Breiman L (2001) Random forests. Mach Learn 45:5–32. Retrieved from http://www.springerlink.com/index/U0P06167N6173512.pdf
Breiman L, Friedman J, Olsen R, Stone C (1984) Classification and regression trees. Chapman and Hall/CRC, Boca Raton, p 368
Brunsdon C, Fotheringham AS, Charlton ME (1996) Geographically weighted regression: a method for exploring spatial nonstationarity. Geogr Anal 28(4):281–298
Canadian Forest Service (2010) National Fire Database – agency fire data. Natural Resources Canada, Canadian Forest Service, Northern Forestry Centre (Edmonton, AB). http://cwfis.cfs.nrcan.gc.ca/ha/nfdb. Accessed 28 Apr 2014
Chuvieco E, Salas J (1996) Map** the spatial distribution of forest fire danger using GIS. Int J Geogr Inf Syst 10:333–345. doi:10.1080/02693799608902082
Coops NC, Gillanders SN, Wulder MA, Gergel SE, Nelson T, Goodwin NR (2010) Assessing changes in forest fragmentation following infestation using time series Landsat imagery. For Ecol Manag 259:2355–2365
Cressie NA, Chan NH (1989) Spatial modeling of regional variables. J Am Stat Assoc 84:393–401. doi:10.2307/2289922
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88(11):2783–2792
Dark SJ, Bram D (2007) The modifiable areal unit problem (MAUP) in physical geography. Prog Phys Geogr 31:471–479. doi:10.1177/0309133307083294
De’ath G (2007) Boosted trees for ecological modeling and prediction. Ecology 88(1):243–251. Retrieved from http://www.ncbi.nlm.nih.gov/pubmed/17489472
De’ath G, Fabricius K (2000) Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81(11):3178–3192. Retrieved from http://www.esajournals.org/doi/pdf/10.1890/0012-9658(2000)081[3178:CARTAP]2.0.CO;2
Demarchi, D. A. (2011) The British Columbia Ecoregion classification, third edition. Ecosystem information section, Ministry of Environment. (Victoria, BC)
DÃaz-Avalos C, Peterson DL, Alvarado E, Ferguson SA, Besag JE (2001) Space-time modelling of lightning-caused ignitions in the Blue Mountains, Oregon. Can J For Res 31:1579–1593
Elith J, Graham CH, Anderson RP, Dudık M, Ferrier S, Guisan A et al (2006) Novel methods improve prediction of species ’ distributions from occurrence data. Ecography 29(2):129–151
Elith J, Leathwick J, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77:802–813. doi:10.1111/j.1365-2656.2008.01390.x
Flannigan MD, Harrington JB (1989) A study of the relation of meteorological variables to monthly provincial area burned by wildfire in Canada (1953–80). J Appl Meteorol 27:441–452
Flannigan MD, Logan KA, Amiro BD, Skinner WR, Stocks BJ (2005) Future area burned in Canada. Clim Chang 72:1–16
Fortin M-J, Dale MRT (2005) Spatial analysis: a guide for ecologists. Cambridge University Press, Cambridge
Fortin MJ, Boots B, Csillag F, Remmel TK (2003) On the role of spatial stochastic models in understanding landscape indices in ecology. Oikos 102(1):203–212
Franklin J (1995) Predictive vegetation map**: geographic modelling of biospatial patterns in relation to environmental gradients. Prog Phys Geogr 19:474–499
Friedman J (2001) Greedy function approximation: a gradient boosting machine, 1999. Ann Statist 29(5):1189–1232. Retrieved from http://scholar.google.com/scholar?hl=en&btnG=Search&q=intitle:Greedy+Function+Approximation:+A+Gradient+Boosting+Machine#3
Friedman JH, Meulman JJ (2003) Multiple additive regression trees with application in epidemiology. Stat Med 22(9):1365–1381. doi:10.1002/sim.1501
Gelman A, Carlin JB, Stern HS, Rubin DB (2009) Bayesian data analysis, 2nd edn. Chapman and Hall/CRC, Boca Raton, FL
Getis A, Boots BN (1978) Models of spatial processes: an approach to the study of point, line, and area patterns. Cambridge University Press, Cambridge
Ghazoul J, McAllister M (2003) Communicating complexity and uncertainty in decision making contexts: Bayesian approaches to forest research. Int For Rev 5(1):9–19
Gómez C, White JC, Wulder MA (2011) Characterizing the state and processes of change in a dynamic forest environment using hierarchical spatio-temporal segmentation. Remote Sens Environ 115(7):1665–1679
Gralewicz NJ, Nelson TA, Wulder MA (2011) Spatial and temporal patterns of wildfire ignitions in Canada from 1980 to 2006. Int J Wildland Fire 21:230–242
Gralewicz NJ, Nelson TA, Wulder MA (2012) Factors influencing national scale wildfire susceptibility in Canada. For Ecol Manag 265:20–29
Grenouillet G, Buisson L, Casajus N, Lek S (2011) Ensemble modelling of species distribution: the effects of geographical and environmental ranges. Ecography 34(1):9–17
Guisan A, Zimmermann NE (2000) Predictive habitat distribution models in ecology. Ecol Model 135:147–186. doi:10.1016/S0304-3800(00)00354-9
Haining R (1990) Spatial data analysis in the social and environmental sciences. Cambridge University Press, Cambridge
Hall JP, Moody B (1994) Forest depletions caused by insects and diseases in Canada 1982–1987. Natural Resources Canada, Canadian Forest Service, Ottawa, ON
Hamann A, Wang TL (2005) Models of climatic normals for genecology and climate change studies in British Columbia. Agric For Meteorol 128:211–221
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, p 745
Hawkes B, Taylor SW, Stockdale C, Shore TL, Alfaro RI, Campbell R, Vera P (2004) Impact of mountain pine beetle on stand dynamics in BC. In: Shore TL, Brooks JE, Stone JE (eds) Mountain pine beetle symposium: challenges and solutions. October 30–31, Kelowna, British Columbia. Natural Resources Canada, Canadian Forest Service, Pacific Forestry Centre, Information Report BC-X-399, Victoria, BC
Hawkins BA (2012) Eight (and a half) deadly sins of spatial analysis. J Biogeogr 39(1):1–9. doi:10.1111/j.1365-2699.2011.02637.x
Hayes GL (1942) Differences in fire danger with altitude, aspect, and time of day. J For 40:318–323
Hély C, Flannigan M, Bergeron Y, McRae D (2000) Role of vegetation and weather on fire behavior in the Canadian mixedwood boreal forest using two fire behavior prediction systems. Can J For Res 31:430–441
Holmes K, Nelson T, Coops N, Wulder M (2013) Biodiversity indicators show climate change will alter vegetation in parks and protected areas. Diversity 5(2):352–373. doi:10.3390/d5020352
Jacquez GM (2000) Spatial analysis in epidemiology: nascent science or a failure of GIS? J Geogr Syst 2:91–97
Jenkins MJ, Hebertson E, Page W, Jorgensen A (2008) Bark beetles, fuels, fires and implications for forest management in the intermountain west. For Ecol Manag 254:16–34
Jenkins MJ, Page WG, Hebertson EG, Alexander ME (2012) Fuels and fire behavior dynamics in bark beetle-attacked forests in western North America and implications for fire management. For Ecol Manag 275:23–34
Jolly WM, Parsons RA, Hadlow AM, Cohn GM, McAllister SS, Popp JB, Hubbard RM, Negron JF (2012) Relationships between moisture, chemistry, and ignition of Pinus contorta needles during the early stages of mountain pine beetle attack. For Ecol Manag 269:52–59
Klutsch JG, Battaglia MA, West DR, Costello SL, Negrón JF (2011) Evaluating potential fire behavior in lodgepole pine-dominated forests after a mountain pine beetle epidemic in north-central Colorado. West J Appl For 26:101–109
Kumar L, Skidmore AK, Knowles E (1997) Modelling topographic variation in solar radiation in a GIS environment. Int J Geogr Inf Sci 11:475–497
Langford WT, Gergel SE, Dietterich TG, Cohen W (2006) Map misclassification can cause large errors in landscape pattern indices: examples from habitat fragmentation. Ecosystems 9(3):474–488
Leathwick JR, Elith J, Francis MP, Hastie T, Taylor P (2006) Variation in demersal fish species richness in the oceans surrounding New Zealand: an analysis using boosted regression trees. Ecol Prog Ser 321:267–281.
Levin SA (1992) The problem of pattern and scale in ecology: the Robert H. MacArthur award lecture. Ecology 73(6):1943–1967
Lynch HJ, Renkin RA, Crabtree RL, Moorcroft PR (2006) The influence of previous mountain pine beetle (Dendroctonus ponderosae) activity on the 1988 Yellowstone fires. Ecosystems 9:1318–1327
Masek, J. G., Cohen, W. B., Leckie, D., Wulder, M. A., Vargas, R., de Jong, B., Healy, S., et al. (2011) Recent rates of forest harvest and conversion in North America. J Geophys Res 116, G00K03, doi: 10.1029/2010JG001471
Michaud JS, Coops NC, Andrew ME, Wulder MA, Brown GS, Rickbeil GJM (2014) Estimating moose (Alces alces) occurrence and abundance from remotely derived environmental indicators. Remote Sens Environ 152:190–201. doi:10.1016/j.rse.2014.06.005
Miller C, Urban DL (2000) Connectivity of forest fuels and surface fire regimes. Landsc Ecol 15:145–154
Murthy S (1998) Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min Knowl Disc 2:345–389. Retrieved from http://springer.longhoe.net/article/10.1023/A:1009744630224
Nelson TA (2012) Trends in spatial analysis. Prof Geogr 64(1):1–12
Nelson TA, Boots B (2008) Detecting spatially explicit hot spots in landscape-scale ecology. Ecography 31(5):556–566
Nelson T, Boots B (2005) Identifying insect infestation hot spots: an approach using conditional spatial randomization. J Geogr Syst 7(3–4):291–311
Nelson T, Boots B, Wulder MA, Shore T, Safranyik L, Ebata T (2006) Rating the susceptibility of forests to mountain pine beetle infestations: the impact of data. Can J Forest Res 36(11):2815–2825.
Negrón JF, Bentz BJ, Fettig CJ, Gillette N, Hansen EM, Hayes JL, Kelsey RG et al (2008) US Forest Service bark beetle research in the western United States: looking toward the future. J For 106:325–331
Nijland W, Addink EA, De Jong SM, Van der Meer FD (2009) Optimizing spatial image support for quantitative map** of natural vegetation. Remote Sens Environ 113:771–780. doi:10.1016/j.rse.2008.12.002
Nijland W, Nielsen SE, Coops NC, Wulder M a, Stenhouse GB (2014) Fine-spatial scale predictions of understory species using climate- and LiDAR-derived terrain and canopy metrics. J Appl Remote Sens 8:083572. doi:10.1117/1.JRS.8.083572
Page W, Jenkins MJ (2007) Predicted fire behaviour in selected mountain pine beetle-infested lodgepole pine. For Sci 53:662–674
Parisien M-A, Moritz MA (2009) Environmental controls on the distribution of wildfire at multiple spatial scales. Ecol Monogr 79:127–154
Parisien M-A, Peters VS, Wang Y, Little JM, Bosch EM, Stocks BJ (2006) Spatial patterns of forest fires in Canada, 1980–1999. Int J Wildland Fire 15:361–374
Powers JS, Sollins P, Harmon ME, Jones JA (1999) Plant-pest interactions in time and space: Douglas-fir bark beetle outbreak as a case study. Landsc Ecol 14:105–120
Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9(2):181–199. doi:10.1007/s10021-005-0054-1
Reid RW (1961) Moisture changes in lodgepole pine before and after attack by the mountain pine beetle. For Chron 37:368–375
Robertson C, Nelson TA, Boots B (2007) Mountain pine beetle dispersal: the spatial-temporal interactions of infestation. For Sci 53(3):395–405
Robertson C, Wulder MA, Nelson TA, White JC (2008) Risk rating for mountain pine beetle infestation of lodgepole pine forests over large areas with ordinal regression modelling. For Ecol Manag 256:900–912
Robertson C, Farmer CJQ, Nelson TA, Mackenzie IK, Wulder MA, White JC (2009a) Determination of the compositional change (1999–2006) in the pine forests of British Columbia due to mountain pine beetle infestation. Environ Monit Assess 158:593–608
Robertson C, Nelson TA, Jelinski DE, Wulder MA, Boots B (2009b) Spatial–temporal analysis of species range expansion: the case of the mountain pine beetle, Dendroctonus ponderosae. J Biogeogr 36:1446–1458
Shekhar S, Zhang P, Huang Y, Vatsavai RR (2003) Trends in spatial data mining. In: Kargupta H, Joshi A, Sivakumar K, Yesha Y (eds) Data mining: next generation challenges and future directions. AAAI/MIT Press, Cambridge, MA, pp 357–380
Shore TL, Safranyik L, Hawkes BC, Taylor SW (2006) Effects of the mountain pine beetle on lodgepole pine stand structure and dynamics. In: Safranyik L, Wilson B (eds) The Mountain pine beetle: a synthesis of biology, management, and impacts on lodgepole pine. Natural Resources Canada, Canadian Forest Service, Pacific forestry Centre, Victoria, BC, pp 95–114
Simard M, Romme WH, Griffin JM, Turner MG (2011) Do mountain pine beetle outbreaks change the probability of active crown fire in lodgepole pine forests? Ecol Monogr 81:3–24
Sokal RR, Oden NL, Thomson BA (1998) Local spatial autocorrelation in biological variables. Biol J Linn Soc 65:41–62
Statistics Canada (2008) .Road Network File, Reference Guide 92-500-GWE Ottawa, On. Available at: www.statcan.ca/bsolc/english/bsolc?catno=92-500-x
Stocks BJ, Mason JA, Todd JB, Bosch EM, Wotton BM, Amiro BD, Flannigan MD, Hirsch KG, Logan KA, Martell DL, Skinner WR (2002) Large forest fires in Canada, 1959–1997. J Geophys Res Atmos 108:5.1–5.12
Turner MG (1989) Landscape ecology: the effect of pattern on process. Annu Rev Ecol Syst 20:171–197
Turner MG, Romme WH (1994) Landscape dynamics in crown fire ecosystems. Landsc Ecol 9:59–77
Turner MG, Romme WH, Gardner RH (1999) Prefire heterogeneity, fire severity, and early postfire plant reestablishment in subalpine forests of Yellowstone National Park, Wyoming. Int J Wildland Fire 9:21–36
van Oijen M, Thomson A (2010) Toward Bayesian uncertainty quantification for forestry models used in the United Kingdom greenhouse gas inventory for land use, land use change, and forestry. Clim Chang 103(1-2):55–67
van Oijen M, Rougier J, Smith R (2005) Bayesian calibration of process-based forest models: bridging the gap between models and data. Tree Physiol 25(7):915–927
van Wagner CE (1977) Conditions for the start and spread of crown fire. Can J For Res 7:23–33
Verbesselt J, Hyndman R, Newnham G, Culvenor D (2010) Detecting trend and seasonal changes in satellite image time series. Remote Sens Environ 114(1):106–115
Volney WJA, Fleming RA (2000) Climate change and impacts of boreal forest insects. Agric Ecosyst Environ 82:283–294
Walton, A. (2010). Provincial-level projection of the current mountain pine beetle outbreak: update of the infestation projection based on the 2009 provincial aerial overview of forest health and the BCMPB model (year 7). Research branch, BC Forest Service. (Victoria, BC)
Wang T, Hamann A, Spittlehouse DL, Murdock TQ (2011) ClimateWNA – high-resolution spatial climate data for western North America. Am Meteorol Soc 51:16–29. doi:10.1175/JAMC-D-11-043.1
Wang Q, Ni J, Tenhunen J (2005) Application of a geographically-weighted regression analysis to estimate net primary production of Chinese forest ecosystems. Glob Ecol Biogeogr 14(4):379–393
Waring RH, Coops NC, Mathys A, Hilker T, Latta G (2014) Process-based modeling to assess the effects of recent climatic variation on site productivity and forest function across western North America. Forests 5:518–534. doi:10.3390/f5030518
White JC, Wulder MA (2014) The Landsat observation record of Canada: 1972–2012. Can J Remote Sens 39(06):1–13
Wulder MA, Ortlepp SM, White JC, Nelson TA, Coops NC (2010) A provincial and regional assessment of the mountain pine beetle epidemic in British Columbia: 1999–2008. J Environ Inform 15:1–13
Wulder MA, White JC, Coops NC (2011) Fragmentation regimes of Canada’s forests. Can Geogr 55:288–230
Wulder MA, Masek JG, Cohen WB, Loveland TR, Woodcock CE (2012) Opening the archive: how free data has enabled the science and monitoring promise of Landsat. Remote Sens Environ 122:2–10
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media LLC
About this chapter
Cite this chapter
Nelson, T.A., Nijland, W., Bourbonnais, M.L., Wulder, M.A. (2017). Regression Tree Modeling of Spatial Pattern and Process Interactions. In: Remmel, T., Perera, A. (eds) Map** Forest Landscape Patterns. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-7331-6_5
Download citation
DOI: https://doi.org/10.1007/978-1-4939-7331-6_5
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4939-7329-3
Online ISBN: 978-1-4939-7331-6
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)