Cannot see the random forest for the decision trees: selecting predictive models for restoration ecology

Improving predictions of restoration outcomes is increasingly important to resource managers for accountability and adaptive management, yet there is limited guidance for selecting a predictive model from the multitude available. The goal of this article was to identify an optimal predictive framewo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Restoration ecology Jg. 27; H. 5; S. 1053 - 1063
Hauptverfasser: Barnard, David M., Germino, Matthew J., Pilliod, David S., Arkle, Robert S., Applestein, Cara, Davidson, Bill E., Fisk, Matthew R.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Malden, USA Wiley Periodicals, Inc 01.09.2019
Blackwell Publishing Ltd
Schlagworte:
ISSN:1061-2971, 1526-100X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Improving predictions of restoration outcomes is increasingly important to resource managers for accountability and adaptive management, yet there is limited guidance for selecting a predictive model from the multitude available. The goal of this article was to identify an optimal predictive framework for restoration ecology using 11 modeling frameworks (including machine learning, inferential, and ensemble approaches) and three data groups (field data, geographic data [GIS], and a combination thereof). We test this approach with a dataset from a large postfire sagebrush reestablishment project in the Great Basin, U.S.A. Predictive power varied among models and data groups, ranging from 58% to 79% accuracy. Finer‐scale field data generally had the greatest predictive power, although GIS data were present in the best models overall. An ensemble prediction computed from the 10 models parameterized to field data was well above average for accuracy but was outperformed by others that prioritized model parsimony by selecting predictor variables based on rankings of their importance among all candidate models. The variation in predictive power among a suite of modeling frameworks underscores the importance of a model comparison and refinement approach that evaluates multiple models and data groups, and selects variables based on their contribution to predictive power. The enhanced understanding of factors influencing restoration outcomes accomplished by this framework has the potential to aid the adaptive management process for improving future restoration outcomes.
AbstractList Improving predictions of restoration outcomes is increasingly important to resource managers for accountability and adaptive management, yet there is limited guidance for selecting a predictive model from the multitude available. The goal of this article was to identify an optimal predictive framework for restoration ecology using 11 modeling frameworks (including machine learning, inferential, and ensemble approaches) and three data groups (field data, geographic data [GIS], and a combination thereof). We test this approach with a dataset from a large postfire sagebrush reestablishment project in the Great Basin, U.S.A. Predictive power varied among models and data groups, ranging from 58% to 79% accuracy. Finer‐scale field data generally had the greatest predictive power, although GIS data were present in the best models overall. An ensemble prediction computed from the 10 models parameterized to field data was well above average for accuracy but was outperformed by others that prioritized model parsimony by selecting predictor variables based on rankings of their importance among all candidate models. The variation in predictive power among a suite of modeling frameworks underscores the importance of a model comparison and refinement approach that evaluates multiple models and data groups, and selects variables based on their contribution to predictive power. The enhanced understanding of factors influencing restoration outcomes accomplished by this framework has the potential to aid the adaptive management process for improving future restoration outcomes.
Author Pilliod, David S.
Applestein, Cara
Arkle, Robert S.
Germino, Matthew J.
Davidson, Bill E.
Fisk, Matthew R.
Barnard, David M.
Author_xml – sequence: 1
  givenname: David M.
  orcidid: 0000-0003-1877-3151
  surname: Barnard
  fullname: Barnard, David M.
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 2
  givenname: Matthew J.
  orcidid: 0000-0001-6326-7579
  surname: Germino
  fullname: Germino, Matthew J.
  email: mgermino@usgs.gov
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 3
  givenname: David S.
  orcidid: 0000-0003-4207-3518
  surname: Pilliod
  fullname: Pilliod, David S.
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 4
  givenname: Robert S.
  orcidid: 0000-0003-3021-1389
  surname: Arkle
  fullname: Arkle, Robert S.
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 5
  givenname: Cara
  surname: Applestein
  fullname: Applestein, Cara
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 6
  givenname: Bill E.
  surname: Davidson
  fullname: Davidson, Bill E.
  organization: Forest and Rangeland Ecosystem Science Center
– sequence: 7
  givenname: Matthew R.
  surname: Fisk
  fullname: Fisk, Matthew R.
  organization: Forest and Rangeland Ecosystem Science Center
BookMark eNp9kE1LAzEQhoNUsK0e_AcLXvSwbT66u4k3WeoHFARR8BbS7Gybsk1qslX6781uPQk6lxmG5x2GZ4QG1llA6JLgCYk19aAnhArGT9CQZDRPCcbvgzjjnKRUFOQMjULYYEwyztkQrUtlrWuTAJC0a0i8spXbJrXzENqu9dsKtAnG2aT1AOE20g3o1thVsvNQmTh-QrJ1FTShz3Rh51XbRUC7xq0O5-i0Vk2Ai58-Rm_389fyMV08PzyVd4tUM4Z5yjmvhWZLyHKRzaoih1zkXAhGa0wU1wzTnNSgSFUTwUHMal4pXGhGi4ItacbG6Pp4d-fdxz7-IbcmaGgaZcHtg6QsauFFTjr06he6cXtv43eSRgQTwiiL1M2R0t6F4KGWO2-2yh8kwbJzLqNz2TuP7PQXq03ba2i9Ms1_iS_TwOHv0_JlXh4T3_q4lMU
CitedBy_id crossref_primary_10_1016_j_jenvman_2025_125808
crossref_primary_10_1016_j_rala_2021_12_002
crossref_primary_10_1016_j_tube_2020_101944
crossref_primary_10_1016_j_ecolind_2021_108379
crossref_primary_10_1007_s10980_023_01621_1
crossref_primary_10_3390_agronomy15061304
crossref_primary_10_1016_j_quascirev_2024_108686
crossref_primary_10_1016_j_ecolind_2022_108935
crossref_primary_10_3390_s20071941
crossref_primary_10_1016_j_ecolmodel_2019_108855
crossref_primary_10_1002_2688_8319_12172
crossref_primary_10_3390_rs11242953
crossref_primary_10_1002_2688_8319_12280
crossref_primary_10_1007_s10669_023_09940_z
crossref_primary_10_1111_rec_14231
crossref_primary_10_1002_ecs2_3541
crossref_primary_10_1111_1365_2664_14325
crossref_primary_10_1002_ecs2_2780
crossref_primary_10_1111_cobi_13842
crossref_primary_10_1016_j_rama_2019_05_006
crossref_primary_10_1016_j_scitotenv_2024_173848
crossref_primary_10_1016_j_scitotenv_2020_142081
crossref_primary_10_3390_rs17050915
Cites_doi 10.1111/j.1365-2656.2008.01390.x
10.1111/1365-2664.12938
10.1890/ES13-00295.1
10.1007/978-3-540-39804-2_12
10.1007/978-1-4614-6849-3
10.1111/j.1365-2486.2009.02000.x
10.1080/02626667909491834
10.1007/978-1-4419-7390-0_8
10.1016/j.ecoinf.2010.06.003
10.3732/ajb.1000285
10.1016/j.rala.2016.02.002
10.1002/eap.1589
10.1007/s10980-018-0662-8
10.18637/jss.v017.i02
10.1214/09-SS054
10.1111/j.1472-4642.2010.00725.x
10.18637/jss.v028.i05
10.1111/1365-2664.12935
10.1007/s11004-008-9156-6
10.1071/WF08088
10.1080/01431160110040323
10.1111/j.1654-1103.2002.tb02087.x
10.1890/14-0661.1
10.1177/001316446002000104
10.1016/j.rama.2018.05.003
10.1111/oik.03726
10.1890/07-0539.1
10.1890/0012-9658(2000)081[3178:CARTAP]2.0.CO;2
10.1007/s10021-005-0054-1
10.2111/REM-D-11-00026.1
10.2478/v10208-011-0016-2
10.2478/v10208-011-0015-3
10.1086/587826
ContentType Journal Article
Copyright Published 2019. This article is a U.S. Government work and is in the public domain in the USA.
2019 Society for Ecological Restoration
Copyright_xml – notice: Published 2019. This article is a U.S. Government work and is in the public domain in the USA.
– notice: 2019 Society for Ecological Restoration
DBID AAYXX
CITATION
7SN
7ST
7U6
7UA
C1K
F1W
H97
L.G
7S9
L.6
DOI 10.1111/rec.12938
DatabaseName CrossRef
Ecology Abstracts
Environment Abstracts
Sustainability Science Abstracts
Water Resources Abstracts
Environmental Sciences and Pollution Management
ASFA: Aquatic Sciences and Fisheries Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality
Aquatic Science & Fisheries Abstracts (ASFA) Professional
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
Aquatic Science & Fisheries Abstracts (ASFA) Professional
Sustainability Science Abstracts
ASFA: Aquatic Sciences and Fisheries Abstracts
Ecology Abstracts
Environment Abstracts
Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality
Water Resources Abstracts
Environmental Sciences and Pollution Management
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA

Aquatic Science & Fisheries Abstracts (ASFA) Professional
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Ecology
Environmental Sciences
EISSN 1526-100X
EndPage 1063
ExternalDocumentID 10_1111_rec_12938
REC12938
Genre article
GeographicLocations United States
GeographicLocations_xml – name: United States
GrantInformation_xml – fundername: US Geological Survey (USGS) Fire Program
– fundername: BLM's Fire Rehabilitation Program
– fundername: Great Basin Landscape Conservation Cooperative
– fundername: Joint Fire Sciences Program
  funderid: 16‐1‐03‐13
– fundername: USGS/BLM SageSuccess Project
GroupedDBID .3N
.GA
.Y3
05W
0R~
10A
123
1OB
1OC
29P
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
53G
5HH
5LA
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A03
AAESR
AAEVG
AAHBH
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABEFU
ABEML
ABJNI
ABPVW
ABTAH
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACGFS
ACPOU
ACPRK
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFPM
AFGKR
AFPWT
AFRAH
AFWVQ
AFZJQ
AHBTC
AHEFC
AITYG
AIURR
AIWBW
AJBDE
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BIYOS
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
D-E
D-F
D0L
DC6
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EBS
ECGQY
EJD
ESX
F00
F01
F04
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
IHE
IX1
J0M
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2P
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
R.K
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
UB1
W8V
W99
WBKPD
WIH
WIK
WNSPC
WOHZO
WQJ
WRC
WXSBR
WYISQ
XG1
Y6R
YV5
ZO4
ZY4
ZZTAW
~02
~IA
~KM
~WT
AAMMB
AAYXX
AEFGJ
AETEA
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
7SN
7ST
7U6
7UA
C1K
F1W
H97
L.G
7S9
L.6
ID FETCH-LOGICAL-c3308-888f9c3be56954d76e69689932f01a8c30261fea1df198e94f8da07c32773b253
IEDL.DBID DRFUL
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000484997000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1061-2971
IngestDate Fri Jul 11 18:35:12 EDT 2025
Sun Jul 13 04:24:05 EDT 2025
Sat Nov 29 04:06:11 EST 2025
Tue Nov 18 22:29:39 EST 2025
Wed Jan 22 16:38:59 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3308-888f9c3be56954d76e69689932f01a8c30261fea1df198e94f8da07c32773b253
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-1877-3151
0000-0003-4207-3518
0000-0001-6326-7579
0000-0003-3021-1389
PQID 2287011323
PQPubID 31740
PageCount 11
ParticipantIDs proquest_miscellaneous_2315287615
proquest_journals_2287011323
crossref_primary_10_1111_rec_12938
crossref_citationtrail_10_1111_rec_12938
wiley_primary_10_1111_rec_12938_REC12938
PublicationCentury 2000
PublicationDate September 2019
2019-09-00
20190901
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: September 2019
PublicationDecade 2010
PublicationPlace Malden, USA
PublicationPlace_xml – name: Malden, USA
– name: Oxford
PublicationTitle Restoration ecology
PublicationYear 2019
Publisher Wiley Periodicals, Inc
Blackwell Publishing Ltd
Publisher_xml – name: Wiley Periodicals, Inc
– name: Blackwell Publishing Ltd
References 2010; 16
2012
2011
2010
2017; 27
2006; 17
2002; 13
2006; 9
2009
2011; 98
2004
2008; 77
2003
1991
2011; 17
2007; 31
2012; 35
2016; 38
1957; 6
1979; 24
2014; 5
2013; 36
1960; 20
2002; 23
2017; 54
2015; 85
2008; 28
2000; 81
2017
2016
2018; 71
2013
2008; 83
2018; 33
2008; 40
2007; 88
2010; 5
2010; 4
2012; 65
2017; 126
2009; 18
e_1_2_8_28_1
Chen C (e_1_2_8_12_1) 2004
Therneau TM (e_1_2_8_48_1) 2010
e_1_2_8_24_1
e_1_2_8_26_1
e_1_2_8_49_1
Kotsiantis SB (e_1_2_8_32_1) 2007; 31
e_1_2_8_3_1
e_1_2_8_5_1
e_1_2_8_7_1
e_1_2_8_9_1
e_1_2_8_20_1
e_1_2_8_43_1
e_1_2_8_45_1
e_1_2_8_41_1
e_1_2_8_17_1
e_1_2_8_19_1
e_1_2_8_13_1
e_1_2_8_36_1
e_1_2_8_15_1
e_1_2_8_38_1
Gelman A (e_1_2_8_23_1) 2009
Friedman J (e_1_2_8_22_1) 2016
Schliep K (e_1_2_8_46_1) 2010
e_1_2_8_11_1
e_1_2_8_34_1
e_1_2_8_30_1
e_1_2_8_29_1
e_1_2_8_25_1
e_1_2_8_27_1
e_1_2_8_2_1
Bellman R (e_1_2_8_4_1) 1957; 6
Witten IH (e_1_2_8_50_1) 2016
e_1_2_8_6_1
Burkett LM (e_1_2_8_10_1) 2011
e_1_2_8_8_1
e_1_2_8_21_1
e_1_2_8_42_1
e_1_2_8_44_1
Soil Survey Staff (e_1_2_8_47_1) 2017
e_1_2_8_18_1
e_1_2_8_39_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_16_1
e_1_2_8_37_1
Peters RH (e_1_2_8_40_1) 1991
e_1_2_8_31_1
e_1_2_8_33_1
References_xml – year: 2011
– volume: 36
  start-page: 1
  year: 2013
  end-page: 132
  article-title: A strict maximum likelihood explanation of MaxEnt, and some implications for distribution modelling
  publication-title: Sommerfeltia
– volume: 81
  start-page: 3178
  year: 2000
  end-page: 3192
  article-title: Classification and regression trees: a powerful yet simple technique for ecological data analysis
  publication-title: Ecology
– year: 2009
– volume: 13
  start-page: 603
  year: 2002
  end-page: 606
  article-title: Equations for potential annual direct incident radiation and heat load
  publication-title: Journal of Vegetation Science
– volume: 54
  start-page: 1018
  year: 2017
  end-page: 1027
  article-title: Interpreting variation to advance predictive restoration science
  publication-title: Journal of Applied Ecology
– start-page: 107
  year: 2003
  end-page: 119
– volume: 9
  start-page: 181
  year: 2006
  end-page: 199
  article-title: Newer classification and regression tree techniques: bagging and random forests for ecological prediction
  publication-title: Ecosystems
– volume: 71
  start-page: 721
  year: 2018
  end-page: 726
  article-title: Appropriate sample sizes for monitoring burned pastures in sagebrush steppe: how many plots are enough, and can one size fit all?
  publication-title: Rangeland Ecology & Management
– start-page: 139
  year: 2011
  end-page: 159
– volume: 20
  start-page: 37
  year: 1960
  end-page: 46
  article-title: A coefficient of agreement for nominal scales
  publication-title: Educational and Psychological Measurement
– volume: 17
  start-page: 43
  year: 2011
  end-page: 57
  article-title: A statistical explanation of MaxEnt for ecologists
  publication-title: Diversity and Distributions
– volume: 38
  start-page: 120
  year: 2016
  end-page: 128
  article-title: Tapping soil survey information for rapid assessment of sagebrush ecosystem resilience and resistance
  publication-title: Rangelands
– volume: 27
  start-page: 2048
  year: 2017
  end-page: 2060
  article-title: Prediction in ecology: a first‐principles framework
  publication-title: Ecological Applications
– year: 2016
– volume: 126
  start-page: 1
  year: 2017
  end-page: 7
  article-title: The priority of prediction in ecological understanding
  publication-title: Oikos
– volume: 83
  start-page: 171
  year: 2008
  end-page: 193
  article-title: Machine learning methods without tears: a primer for ecologists
  publication-title: The Quarterly Review of Biology
– volume: 77
  start-page: 802
  year: 2008
  end-page: 813
  article-title: A working guide to boosted regression trees
  publication-title: Journal of Animal Ecology
– volume: 28
  start-page: 1
  year: 2008
  end-page: 26
  article-title: Caret package
  publication-title: Journal of Statistical Software
– volume: 16
  start-page: 1145
  year: 2010
  end-page: 1157
  article-title: Uncertainty in ensemble forecasting of species distribution
  publication-title: Global Change Biology
– volume: 17
  start-page: 9
  year: 2006
  end-page: 36
  article-title: ada: an r package for stochastic boosting
  publication-title: Journal of Statistical Software
– year: 2010
– volume: 31
  start-page: 249
  year: 2007
  end-page: 268
  article-title: Supervised machine learning: a review of classification techniques
  publication-title: Informatics
– year: 2012
– volume: 18
  start-page: 235
  year: 2009
  end-page: 249
  article-title: LANDFIRE: a nationally consistent vegetation, wildland fire, and fuel assessment
  publication-title: International Journal of Wildland Fire
– volume: 5
  start-page: 1
  year: 2014
  end-page: 15
  article-title: Harnessing the power of big data: infusing the scientific method with machine learning to transform ecology
  publication-title: Ecosphere
– volume: 6
  start-page: 679
  year: 1957
  end-page: 684
  article-title: A Markovian decision process
  publication-title: Journal of Mathematics and Mechanics
– volume: 85
  start-page: 3
  year: 2015
  end-page: 28
  article-title: A guide to Bayesian model selection for ecologists
  publication-title: Ecological Monographs
– volume: 23
  start-page: 725
  year: 2002
  end-page: 749
  article-title: An assessment of support vector machines for land cover classification
  publication-title: International Journal of Remote Sensing
– volume: 54
  start-page: 1058
  year: 2017
  end-page: 1069
  article-title: The hierarchy of predictability in ecological restoration: are vegetation structure and functional diversity more predictable than community composition?
  publication-title: Journal of Applied Ecology
– volume: 88
  start-page: 2783
  year: 2007
  end-page: 2792
  article-title: Random forests for classification in ecology
  publication-title: Ecology
– volume: 4
  start-page: 40
  year: 2010
  end-page: 79
  article-title: A survey of cross‐validation procedures for model selection
  publication-title: Statistics Surveys
– volume: 65
  start-page: 160
  year: 2012
  end-page: 170
  article-title: A common‐garden study of resource‐island effects on a native and an exotic, annual grass after fire
  publication-title: Rangeland Ecology & Management
– year: 2004
– volume: 5
  start-page: 441
  year: 2010
  end-page: 450
  article-title: Classification in conservation biology: a comparison of five machine‐learning methods
  publication-title: Ecological Informatics
– volume: 40
  start-page: 409
  year: 2008
  end-page: 424
  article-title: An objective analysis of support vector machine based classification for remote sensing
  publication-title: Mathematical Geosciences
– volume: 98
  start-page: 549
  year: 2011
  end-page: 558
  article-title: The restoration of biodiversity: where has research been and where does it need to go?
  publication-title: American Journal of Botany
– volume: 24
  start-page: 43
  year: 1979
  end-page: 69
  article-title: A physically based, variable contributing area model of basin hydrology
  publication-title: Hydrological Sciences Journal
– volume: 33
  start-page: 1177
  year: 2018
  end-page: 1194
  article-title: Thresholds and hotspots for shrub restoration following a heterogeneous megafire
  publication-title: Landscape Ecology
– year: 1991
– year: 2017
– volume: 35
  start-page: 1
  year: 2012
  end-page: 165
  article-title: A gradient analytic perspective on distribution modelling
  publication-title: Sommerfeltia
– year: 2013
– ident: e_1_2_8_19_1
  doi: 10.1111/j.1365-2656.2008.01390.x
– ident: e_1_2_8_8_1
  doi: 10.1111/1365-2664.12938
– ident: e_1_2_8_41_1
  doi: 10.1890/ES13-00295.1
– ident: e_1_2_8_11_1
  doi: 10.1007/978-3-540-39804-2_12
– ident: e_1_2_8_34_1
  doi: 10.1007/978-1-4614-6849-3
– ident: e_1_2_8_9_1
  doi: 10.1111/j.1365-2486.2009.02000.x
– ident: e_1_2_8_5_1
  doi: 10.1080/02626667909491834
– ident: e_1_2_8_21_1
  doi: 10.1007/978-1-4419-7390-0_8
– ident: e_1_2_8_31_1
  doi: 10.1016/j.ecoinf.2010.06.003
– ident: e_1_2_8_7_1
  doi: 10.3732/ajb.1000285
– ident: e_1_2_8_36_1
  doi: 10.1016/j.rala.2016.02.002
– ident: e_1_2_8_44_1
– volume-title: kknn: weighted k‐nearest neighbors. R package version 1.0‐8
  year: 2010
  ident: e_1_2_8_46_1
– ident: e_1_2_8_17_1
  doi: 10.1002/eap.1589
– ident: e_1_2_8_24_1
  doi: 10.1007/s10980-018-0662-8
– ident: e_1_2_8_14_1
  doi: 10.18637/jss.v017.i02
– ident: e_1_2_8_3_1
  doi: 10.1214/09-SS054
– ident: e_1_2_8_20_1
  doi: 10.1111/j.1472-4642.2010.00725.x
– volume: 31
  start-page: 249
  year: 2007
  ident: e_1_2_8_32_1
  article-title: Supervised machine learning: a review of classification techniques
  publication-title: Informatics
– ident: e_1_2_8_18_1
– ident: e_1_2_8_33_1
  doi: 10.18637/jss.v028.i05
– ident: e_1_2_8_35_1
  doi: 10.1111/1365-2664.12935
– ident: e_1_2_8_39_1
  doi: 10.1007/s11004-008-9156-6
– ident: e_1_2_8_45_1
  doi: 10.1071/WF08088
– ident: e_1_2_8_30_1
  doi: 10.1080/01431160110040323
– volume: 6
  start-page: 679
  year: 1957
  ident: e_1_2_8_4_1
  article-title: A Markovian decision process
  publication-title: Journal of Mathematics and Mechanics
– ident: e_1_2_8_6_1
– volume-title: glmnet: Lasso and elastic‐net regularized generalized linear models. R package version 1.9–5
  year: 2016
  ident: e_1_2_8_22_1
– ident: e_1_2_8_37_1
  doi: 10.1111/j.1654-1103.2002.tb02087.x
– volume-title: The rpart package
  year: 2010
  ident: e_1_2_8_48_1
– ident: e_1_2_8_27_1
  doi: 10.1890/14-0661.1
– ident: e_1_2_8_43_1
– volume-title: Using random forest to learn imbalanced data
  year: 2004
  ident: e_1_2_8_12_1
– ident: e_1_2_8_13_1
  doi: 10.1177/001316446002000104
– volume-title: Soil survey geographic (SSURGO) database
  year: 2017
  ident: e_1_2_8_47_1
– ident: e_1_2_8_2_1
  doi: 10.1016/j.rama.2018.05.003
– ident: e_1_2_8_29_1
  doi: 10.1111/oik.03726
– ident: e_1_2_8_15_1
  doi: 10.1890/07-0539.1
– volume-title: arm: data analysis using regression and multilevel/hierarchical models. R package version 9.01
  year: 2009
  ident: e_1_2_8_23_1
– ident: e_1_2_8_16_1
  doi: 10.1890/0012-9658(2000)081[3178:CARTAP]2.0.CO;2
– volume-title: A critique for ecology
  year: 1991
  ident: e_1_2_8_40_1
– ident: e_1_2_8_42_1
  doi: 10.1007/s10021-005-0054-1
– ident: e_1_2_8_28_1
  doi: 10.2111/REM-D-11-00026.1
– ident: e_1_2_8_26_1
  doi: 10.2478/v10208-011-0016-2
– ident: e_1_2_8_25_1
  doi: 10.2478/v10208-011-0015-3
– ident: e_1_2_8_38_1
  doi: 10.1086/587826
– ident: e_1_2_8_49_1
– volume-title: Data mining: practical machine learning tools and techniques
  year: 2016
  ident: e_1_2_8_50_1
– volume-title: A field guide to pedoderm and pattern classes
  year: 2011
  ident: e_1_2_8_10_1
SSID ssj0015883
Score 2.3512514
Snippet Improving predictions of restoration outcomes is increasingly important to resource managers for accountability and adaptive management, yet there is limited...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1053
SubjectTerms Accuracy
Adaptive management
Artemisia
artificial intelligence
basins
Data
data collection
decision support systems
Decision trees
ecological prediction
ecological restoration
Ecology
ensemble modeling
Geographic information systems
Geographical information systems
Learning algorithms
Machine learning
model comparison
Modelling
postfire restoration
prediction
Prediction models
predictive framework
Resource management
Restoration
United States
Title Cannot see the random forest for the decision trees: selecting predictive models for restoration ecology
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Frec.12938
https://www.proquest.com/docview/2287011323
https://www.proquest.com/docview/2315287615
Volume 27
WOSCitedRecordID wos000484997000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library - Journals
  customDbUrl:
  eissn: 1526-100X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0015883
  issn: 1061-2971
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3di9swDBddu8Fe9tFbWbdu-MYe7iVHHDuOsz2NrmUPoxxlhb4Fx7HZYEtL0w7uvz_ZcdMOdjDYU0IiE2FZ1k-RLAG8r0qelLEWkbCliHhiVITgiEZpVmmrMsOEqnyziWyxkOt1ftODj8ezMG19iO6Hm9MMv187BVdlc6bkuCFcO2MlH8AgwXWb9mHweTlffe2CCKmUbX69oFGSZzQUFnKJPN3gP83RCWOeI1VvauZP_4vJZ_AkIEzyqV0Sz6Fn6iE8mvnq1LdDGM1OR9uQLOh2cwHfp6quN3vSGEMQFRI0YtXmF0FQi6y6i39ahZ48xEWzmw-k8X100P6R7c7FfNzuSXx7ncaP2fnONV78xLQ8vIDVfPZt-iUKfRgizVgsI3SSba5ZaVKRp7zKhHEVdRDYJDamSmrm_DhrFK0szaXJuZWVijPNkixjZZKyEfTrTW1eAnHlS62QKtUx44KViP8sp1zZWJVcaT6Gq6M4Ch2KlLteGT-Lo7OCM1r4GR3Du45021bm-BvR5CjTIihnUyQuuEvRDWdjuOxeo1q5WImqzeaANAyBDVoKmiJLXsL3f6RYzqb-5tW_k76Gxwi9QrbaBPr73cG8gYf69_5Hs3sbVvId0EP3xQ
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9swED-yZKN72Ue30Gzdqo097MXDsmRbHn0ZmUPLsjBKCnkzsizRwuaUOB30v-9Jlp0WNhjsycY-40N3p_udTroD-FCVPCpDlQSJKZOAR1oGCI5oEKeVMjLVLJGVazaRLhZitcp-DOC4OwvT1ofoF9ysZbj52hq4XZC-Y-U4I3yy3ko8gBFHNUL9Hn09m53P-yxCLES7wT6hQZSl1FcWsjt5-o_v-6MdyLwLVZ2vmT39Py6fwROPMcmXVimew0DX-_Aod_Wpb_ZhnO8OtyGZt-7mBVxMZV2vt6TRmiAuJOjGqvUvgrAWebUX97TyXXmIzWc3n0njOumgByRXG5v1sfMncQ12GvfNxvWucQpAdMvDSzif5cvpSeA7MQSKsVAEGCabTLFSx0kW8ypNtK2pg9AmMiGVQjEbyRktaWVoJnTGjahkmCoWpSkro5iNYViva30AxBYwNYmQsQoZSq1EBGg45dKEsuRS8Ql87ORRKF-m3HbL-Fl04QqOaOFGdALve9KrtjbHn4gOO6EW3jybIrLpXYqBOJvAu_41GpbNlshar6-RhiG0QV9BY2TJifjvPynO8qm7efXvpEewd7L8Pi_mp4tvr-ExAjG_d-0QhtvNtX4DD9Xv7WWzeevV-hajhPu1
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9swED-6dCt92Ue30Kzdpo097MXFsmRZLnsZaULLSihlhb4ZWR9ssDohTgv973eSFbeDFQp7srFP-JB0ut_5pPsBfDY1z-pUi0S4WiQ8sypBcESTvDDaqcIyoUwgmyhmM3l5WZ5twNf1WZiuPkT_w81bRlivvYHbhXH3rBxXhAPvreQT2OSeRGYAm0fn04vTPouQS9ltsBc0ycqCxspCfidP3_hvf3QHMu9D1eBrpi_-T8uX8DxiTPKtmxSvYMM2O_BsEupT3-7AcHJ3uA3FonW3r-HnWDXNfEVaawniQoJuzMyvCMJa1NVfwlMTWXmIz2e3h6QNTDroAcli6bM-fv0kgWCnDW2WgbsmTABiOx3ewMV08mN8nEQmhkQzlsoEw2RXalbbXJQ5N4WwvqYOQpvMpVRJzXwk56yixtFS2pI7aVRaaJYVBauznA1h0MwbuwvEFzB1Qqpcp4wLViMCdJxy5VJVc6X5CL6sx6PSsUy5Z8v4Xa3DFezRKvToCD71oouuNse_hPbXg1pF82yrzKd3KQbibAQf-9doWD5boho7v0YZhtAGfQXNUaUwxA9_pDqfjMPN28eLfoCts6NpdXoy-74H24jD4ta1fRisltf2HTzVN6tf7fJ9nNV_ADUz-zA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Cannot+see+the+random+forest+for+the+decision+trees%3A+selecting+predictive+models+for+restoration+ecology&rft.jtitle=Restoration+ecology&rft.au=Barnard%2C+David+M&rft.au=Germino%2C+Matthew+J&rft.au=Pilliod%2C+David+S&rft.au=Arkle%2C+Robert+S&rft.date=2019-09-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=1061-2971&rft.eissn=1526-100X&rft.volume=27&rft.issue=5&rft.spage=1053&rft.epage=1063&rft_id=info:doi/10.1111%2Frec.12938&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1061-2971&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1061-2971&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1061-2971&client=summon