Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is wel...

Full description

Saved in:

Bibliographic Details
Published in:	Forests Vol. 10; no. 12; p. 1073
Main Authors:	Li, Yingchang, Li, Chao, Li, Mingyang, Liu, Zhenzhen
Format:	Journal Article
Language:	English
Published:	Basel MDPI AG 01.12.2019
Subjects:	Algorithms Biodiversity Biomass Carbon Carbon cycle Decision trees Ecological monitoring Ecosystems Feature selection Forest biomass Forest ecosystems Landsat Landsat satellites Learning algorithms Machine learning Model accuracy Modelling National forests Regression analysis Remote sensing Remote sensing systems Satellites Terrestrial ecosystems Timber Variables China Hunan China
ISSN:	1999-4907, 1999-4907
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is well developed and extensively used, improving the accuracy of biomass estimation remains challenging. In this paper, we used China’s National Forest Continuous Inventory data and Landsat 8 Operational Land Imager data in combination with three algorithms, either the linear regression (LR), random forest (RF), or extreme gradient boosting (XGBoost), to establish biomass estimation models based on forest type. In the modeling process, two methods of variable selection, e.g., stepwise regression and variable importance-base method, were used to select optimal variable subsets for LR and machine learning algorithms (e.g., RF and XGBoost), respectively. Comfortingly, the accuracy of models was significantly improved, and thus the following conclusions were drawn: (1) Variable selection is very important for improving the performance of models, especially for machine learning algorithms, and the influence of variable selection on XGBoost is significantly greater than that of RF. (2) Machine learning algorithms have advantages in aboveground biomass (AGB) estimation, and the XGBoost and RF models significantly improved the estimation accuracy compared with the LR models. Despite that the problems of overestimation and underestimation were not fully eliminated, the XGBoost algorithm worked well and reduced these problems to a certain extent. (3) The approach of AGB modeling based on forest type is a very advantageous method for improving the performance at the lower and higher values of AGB. Some conclusions in this paper were probably different as the study area changed. The methods used in this paper provide an optional and useful approach for improving the accuracy of AGB estimation based on remote sensing data, and the estimation of AGB was a reference basis for monitoring the forest ecosystem of the study area.
AbstractList	Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is well developed and extensively used, improving the accuracy of biomass estimation remains challenging. In this paper, we used China’s National Forest Continuous Inventory data and Landsat 8 Operational Land Imager data in combination with three algorithms, either the linear regression (LR), random forest (RF), or extreme gradient boosting (XGBoost), to establish biomass estimation models based on forest type. In the modeling process, two methods of variable selection, e.g., stepwise regression and variable importance-base method, were used to select optimal variable subsets for LR and machine learning algorithms (e.g., RF and XGBoost), respectively. Comfortingly, the accuracy of models was significantly improved, and thus the following conclusions were drawn: (1) Variable selection is very important for improving the performance of models, especially for machine learning algorithms, and the influence of variable selection on XGBoost is significantly greater than that of RF. (2) Machine learning algorithms have advantages in aboveground biomass (AGB) estimation, and the XGBoost and RF models significantly improved the estimation accuracy compared with the LR models. Despite that the problems of overestimation and underestimation were not fully eliminated, the XGBoost algorithm worked well and reduced these problems to a certain extent. (3) The approach of AGB modeling based on forest type is a very advantageous method for improving the performance at the lower and higher values of AGB. Some conclusions in this paper were probably different as the study area changed. The methods used in this paper provide an optional and useful approach for improving the accuracy of AGB estimation based on remote sensing data, and the estimation of AGB was a reference basis for monitoring the forest ecosystem of the study area.
Author	Li, Yingchang Liu, Zhenzhen Li, Chao Li, Mingyang
Author_xml	– sequence: 1 givenname: Yingchang surname: Li fullname: Li, Yingchang – sequence: 2 givenname: Chao surname: Li fullname: Li, Chao – sequence: 3 givenname: Mingyang surname: Li fullname: Li, Mingyang – sequence: 4 givenname: Zhenzhen surname: Liu fullname: Liu, Zhenzhen
BookMark	eNptkMtOwkAUhicGExFZ-AaTuHKBzK2ddokElATjQnDbTNtTGFJmcKY1wad3ADXGeDbnku8_t0vUMdYAQteU3HGekmFFCWWUSH6GujRN04FIiez8ii9Q3_sNCRbJJGWiiz5mpqpbMAVgW-FX5bTKa8AvUEPRaGuwMiWeWge-wYv9LlDmOx3l9h1WzraBuNd2q7zHE9_orToKl16bFX5SxVobwHNQzhwKo3plnW7WW3-FzitVe-h_-R5aTieL8eNg_vwwG4_mg4JHSTMQUcJLQiVQJkSR8DTneRnFCeQxU5KxCkQlOQgZx7wqhcyljEkpkriIcgaJ4j10c-q7c_atDZtnG9s6E0ZmLBKJiGMmaaCGJ6pw1nsHVVbo5nhJ45SuM0qyw4-znx8Hxe0fxc6F493-H_YTjR19pg
CitedBy_id	crossref_primary_10_1080_17583004_2025_2504937 crossref_primary_10_1109_JSTARS_2021_3103754 crossref_primary_10_1007_s00477_022_02359_z crossref_primary_10_3390_f11030302 crossref_primary_10_1016_j_scitotenv_2021_147335 crossref_primary_10_1109_ACCESS_2020_3008686 crossref_primary_10_3390_f14081688 crossref_primary_10_3390_su132111591 crossref_primary_10_3390_su142114222 crossref_primary_10_1016_j_ecoinf_2023_102404 crossref_primary_10_3390_f15010215 crossref_primary_10_1016_j_jhydrol_2024_131493 crossref_primary_10_1080_01431161_2023_2277162 crossref_primary_10_2989_20702620_2023_2251946 crossref_primary_10_1109_JSTARS_2025_3559233 crossref_primary_10_1016_j_ecoinf_2025_103052 crossref_primary_10_1007_s10661_021_09524_x crossref_primary_10_3390_fire6020076 crossref_primary_10_3390_f14030526 crossref_primary_10_1016_j_catena_2025_109282 crossref_primary_10_1080_17538947_2025_2525383 crossref_primary_10_3390_rs16122229 crossref_primary_10_3390_s20247248 crossref_primary_10_1016_j_engappai_2023_106135 crossref_primary_10_3390_rs12162534 crossref_primary_10_3390_f15091615 crossref_primary_10_1080_10095020_2024_2439399 crossref_primary_10_3390_f12060739 crossref_primary_10_1038_s41598_024_78615_9 crossref_primary_10_3390_agriculture13010098 crossref_primary_10_1016_j_scitotenv_2021_145292 crossref_primary_10_1016_j_jobe_2023_107187 crossref_primary_10_1016_j_resconrec_2025_108567 crossref_primary_10_3390_f15101734 crossref_primary_10_1007_s41748_025_00713_z crossref_primary_10_3390_rs12050777 crossref_primary_10_1155_ijfr_9355771 crossref_primary_10_1016_j_still_2025_106629 crossref_primary_10_1080_01431161_2023_2210724 crossref_primary_10_3390_f12020216 crossref_primary_10_3390_f16071130 crossref_primary_10_1109_JSTARS_2025_3567505 crossref_primary_10_1139_cjfas_2022_0212 crossref_primary_10_1016_j_compag_2023_108144 crossref_primary_10_3390_rs12213609 crossref_primary_10_3390_rs14225734 crossref_primary_10_3390_f11020125 crossref_primary_10_1016_j_ecolind_2024_111554 crossref_primary_10_1007_s12145_025_01864_3 crossref_primary_10_1109_TGRS_2025_3537324 crossref_primary_10_1016_j_rsase_2022_100868 crossref_primary_10_3390_rs16203794 crossref_primary_10_3390_app12178654 crossref_primary_10_1016_j_indic_2025_100680 crossref_primary_10_1016_j_envsoft_2022_105326 crossref_primary_10_1007_s10653_025_02507_8 crossref_primary_10_1080_14942119_2024_2380230 crossref_primary_10_1016_j_foreco_2024_121927 crossref_primary_10_3390_rs14225741 crossref_primary_10_3390_su16167232 crossref_primary_10_3390_rs17162849 crossref_primary_10_3390_f16030449 crossref_primary_10_1080_10106049_2021_1952314 crossref_primary_10_3390_s21175974 crossref_primary_10_3390_f11080842 crossref_primary_10_3390_rs17162842 crossref_primary_10_3390_rs17162843 crossref_primary_10_1007_s10708_025_11374_w crossref_primary_10_1080_01431161_2021_1975845 crossref_primary_10_1016_j_envsoft_2024_106071 crossref_primary_10_1111_btp_13348 crossref_primary_10_3390_f14061086 crossref_primary_10_3390_rs15082067 crossref_primary_10_3390_rs16122250 crossref_primary_10_1109_ACCESS_2020_3048416 crossref_primary_10_1080_10095020_2023_2169199 crossref_primary_10_3390_rs15143543 crossref_primary_10_1016_j_ecoinf_2024_102732 crossref_primary_10_1007_s12145_025_01744_w crossref_primary_10_3390_rs17071228 crossref_primary_10_1080_10106049_2022_2071475 crossref_primary_10_3390_f16030477 crossref_primary_10_1080_10106049_2023_2207550 crossref_primary_10_3390_rs13081595 crossref_primary_10_1111_sum_12900 crossref_primary_10_3390_rs14143330 crossref_primary_10_3390_f14030602 crossref_primary_10_1016_j_oregeorev_2023_105652 crossref_primary_10_3390_rs15010284 crossref_primary_10_3390_rs12244015 crossref_primary_10_3390_rs13152885 crossref_primary_10_3390_rs13163081 crossref_primary_10_1016_j_envsoft_2021_105094 crossref_primary_10_1139_cjfr_2024_0293 crossref_primary_10_3390_rs14184434 crossref_primary_10_1016_j_rsase_2023_101123 crossref_primary_10_3390_f14071345 crossref_primary_10_1007_s11119_022_09915_1 crossref_primary_10_3390_f16040663 crossref_primary_10_1038_s41598_020_67024_3 crossref_primary_10_1007_s10661_021_08882_w crossref_primary_10_3390_su141912187 crossref_primary_10_1016_j_ecoinf_2024_102796 crossref_primary_10_1080_15481603_2025_2477869 crossref_primary_10_3390_rs15143489 crossref_primary_10_1007_s12665_025_12302_4 crossref_primary_10_1016_j_ecoinf_2023_101973 crossref_primary_10_3389_fpls_2025_1532138 crossref_primary_10_1016_j_rsase_2024_101291 crossref_primary_10_3390_f16091381 crossref_primary_10_1007_s12524_024_01901_6 crossref_primary_10_1016_j_rsase_2025_101458 crossref_primary_10_3390_drones9010032 crossref_primary_10_1016_j_catena_2022_106189 crossref_primary_10_3390_f15111861 crossref_primary_10_3390_f15060975 crossref_primary_10_3390_f13050787 crossref_primary_10_1007_s12145_024_01657_0 crossref_primary_10_3390_rs12111884 crossref_primary_10_3390_rs13081535 crossref_primary_10_3390_land13020213 crossref_primary_10_1155_2024_6619263 crossref_primary_10_1007_s11629_024_9266_8 crossref_primary_10_1016_j_foreco_2024_121729 crossref_primary_10_3390_app112110139 crossref_primary_10_3390_rs13245030 crossref_primary_10_3390_rs14112541 crossref_primary_10_3390_rs16071276 crossref_primary_10_3390_rs14051066 crossref_primary_10_1002_eco_70101 crossref_primary_10_3390_f15040731
Cites_doi	10.1016/j.rse.2016.01.015 10.1016/S0168-1699(02)00118-7 10.3808/jei.200600078 10.1080/07038992.1982.10855028 10.3233/IDA-1997-1302 10.3390/rs9030241 10.1016/S0269-7491(01)00212-3 10.3390/rs6097878 10.1016/j.patrec.2010.03.014 10.1080/01431160500142145 10.3390/rs10040627 10.1016/j.rse.2016.03.012 10.1007/s00267-011-9716-2 10.1080/07038992.2014.987376 10.1088/1748-9326/3/4/045011 10.1016/j.foreco.2005.10.014 10.1023/A:1007607513941 10.1146/annurev.energy.28.050302.105515 10.1111/j.1365-2656.2008.01390.x 10.1016/j.eswa.2018.01.012 10.1016/S0034-4257(02)00130-X 10.1109/TGRS.2002.804725 10.1016/j.rse.2017.07.018 10.1109/TSMC.1973.4309314 10.1021/acs.jcim.6b00591 10.1109/LGRS.2018.2803259 10.3390/rs6076407 10.1023/A:1010933404324 10.1145/2939672.2939785 10.1080/01431160110107806 10.1016/j.rse.2019.02.015 10.1016/j.agrformet.2018.04.005 10.1109/LGRS.2010.2094179 10.1111/j.1365-2486.2005.00955.x 10.5589/m08-066 10.1016/j.iref.2018.03.008 10.1080/014311698216152 10.1080/01431160310001654923 10.3390/f10020104 10.1016/S0167-9473(01)00065-2 10.1111/gcb.13139 10.1016/j.rse.2014.02.001 10.1126/science.1058629 10.1007/s13748-015-0080-y 10.1016/S0034-4257(01)00289-9 10.3390/rs71215841 10.1016/j.rse.2008.11.010 10.1186/s40663-015-0047-2 10.3390/rs70810017 10.3390/rs61010232 10.1080/01431160500486732 10.1080/014311697218593 10.1029/2009JG000935 10.1007/s11676-017-0530-4 10.1016/j.rse.2007.08.021 10.1007/s10310-008-0077-5 10.1080/17538947.2014.990526 10.1641/0006-3568(2004)054[0523:UISTSE]2.0.CO;2 10.1145/2821513 10.1139/cjfr-2014-0562 10.1016/j.jhydrol.2019.04.070 10.1016/j.rse.2016.07.033 10.14358/PERS.71.8.967 10.1007/978-3-319-14708-6 10.1590/S0044-59672005000200015 10.1109/JSTARS.2016.2597762 10.1016/j.rse.2012.02.012 10.1016/j.rse.2011.09.022
ContentType	Journal Article
Copyright	2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION 3V. 7SN 7SS 7X2 8FE 8FH 8FK ABUWG AEUYN AFKRA ATCPS AZQEC BENPR BHPHI BKSAR C1K CCPQU DWQXO GNUQQ HCIFZ M0K PATMY PCBAR PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PYCSY
DOI	10.3390/f10121073
DatabaseName	CrossRef ProQuest Central (Corporate) Ecology Abstracts Entomology Abstracts (Full archive) Agricultural Science Collection ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland ProQuest Agricultural & Environmental Science & Pollution Managment ProQuest Central Essentials ProQuest Central Natural Science Collection ProQuest Earth, Atmospheric & Aquatic Science Collection Environmental Sciences and Pollution Management ProQuest One Community College ProQuest Central Korea ProQuest Central Student SciTech Premium Collection Agricultural Science Database Environmental Science Database Earth, Atmospheric & Aquatic Science Database ProQuest Central Premium ProQuest One Academic ProQuest Publicly Available Content ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition Environmental Science Collection
DatabaseTitle	CrossRef Agricultural Science Database Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection Environmental Sciences and Pollution Management Earth, Atmospheric & Aquatic Science Collection ProQuest Central ProQuest One Sustainability Natural Science Collection ProQuest Central Korea Agricultural & Environmental Science Collection ProQuest Central (New) ProQuest One Academic Eastern Edition Earth, Atmospheric & Aquatic Science Database Agricultural Science Collection ProQuest SciTech Collection Ecology Abstracts Environmental Science Collection Entomology Abstracts ProQuest One Academic UKI Edition Environmental Science Database ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni)
DatabaseTitleList	CrossRef Agricultural Science Database
Database_xml	– sequence: 1 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Forestry
EISSN	1999-4907
ExternalDocumentID	10_3390_f10121073
GeographicLocations	China Hunan China
GeographicLocations_xml	– name: China – name: Hunan China
GroupedDBID	5VS 7X2 7XC 8FE 8FH AADQD AAFWJ AAHBH AAYXX ADBBV AENEX AEUYN AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ATCPS BANNL BCNDV BENPR BHPHI BKSAR CCPQU CITATION ECGQY EDH HCIFZ IAO ITG ITH KQ8 LK5 M0K M7R MODMG M~E OK1 PATMY PCBAR PHGZM PHGZT PIMPY PROAC PYCSY TR2 3V. 7SN 7SS 8FK ABUWG AZQEC C1K DWQXO GNUQQ PKEHL PQEST PQQKQ PQUKI
ID	FETCH-LOGICAL-c358t-4583d017e1244c839b3bd568eb62a722fe4f73e47663fd47b7760d486c5b2e8a3
IEDL.DBID	BENPR
ISICitedReferencesCount	121
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000507288400082&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1999-4907
IngestDate	Mon Jun 30 13:30:05 EDT 2025 Sat Nov 29 07:12:08 EST 2025 Tue Nov 18 22:22:19 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c358t-4583d017e1244c839b3bd568eb62a722fe4f73e47663fd47b7760d486c5b2e8a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
OpenAccessLink	https://www.proquest.com/docview/2548466271?pq-origsite=%requestingapplication%
PQID	2548466271
PQPubID	2032398
ParticipantIDs	proquest_journals_2548466271 crossref_citationtrail_10_3390_f10121073 crossref_primary_10_3390_f10121073
PublicationCentury	2000
PublicationDate	2019-12-01
PublicationDateYYYYMMDD	2019-12-01
PublicationDate_xml	– month: 12 year: 2019 text: 2019-12-01 day: 01
PublicationDecade	2010
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Forests
PublicationYear	2019
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	Loveland (ref_13) 2016; 185 ref_50 Shen (ref_25) 2018; 259 Baccini (ref_32) 2008; 3 Dietterich (ref_74) 2000; 40 ref_58 Nelson (ref_33) 2009; 113 Ali (ref_79) 2015; 7 Reese (ref_31) 2002; 37 ref_54 Loveland (ref_15) 2012; 122 Blackard (ref_35) 2008; 112 Lu (ref_64) 2016; 9 Wulder (ref_14) 2019; 225 Wulder (ref_17) 2008; 34 ref_59 Sheridan (ref_76) 2016; 56 Lu (ref_9) 2006; 27 Dash (ref_60) 1997; 1 Brown (ref_1) 2002; 116 Zald (ref_38) 2016; 176 Lei (ref_40) 2009; 11 ref_69 Barsi (ref_70) 2014; 6 Freeman (ref_65) 2016; 46 ref_66 Lu (ref_5) 2005; 71 Karlson (ref_37) 2015; 7 Kelsey (ref_73) 2014; 6 Banskota (ref_20) 2014; 40 ref_62 Kajisa (ref_67) 2008; 13 Deng (ref_11) 2014; 6 Zeng (ref_41) 2015; 2 Teillet (ref_48) 1982; 8 Houghton (ref_4) 2009; 114 ref_27 Yu (ref_52) 2018; 29 Tyralis (ref_53) 2019; 574 Cao (ref_12) 2016; 178 Chrysafis (ref_21) 2017; 199 Georganos (ref_77) 2018; 15 Carmona (ref_39) 2019; 61 Suganuma (ref_63) 2006; 222 He (ref_55) 2018; 98 Xie (ref_42) 2011; 48 Friedman (ref_56) 2002; 38 Haralick (ref_49) 1973; SMC-3 Gitelson (ref_72) 2002; 80 Lehmann (ref_18) 2013; 21 Ouma (ref_23) 2006; 8 Shimabukuro (ref_19) 1998; 19 Elith (ref_61) 2008; 77 Houghton (ref_3) 2005; 11 Breiman (ref_51) 2001; 45 Mutanga (ref_81) 2004; 25 ref_30 Crosby (ref_8) 2017; 10 Carreiras (ref_36) 2012; 121 Gitelson (ref_71) 2002; 23 Guyon (ref_57) 2003; 3 (ref_75) 2006; 7 Yu (ref_26) 2016; 11 Roy (ref_16) 2014; 145 Richter (ref_47) 1997; 18 Moghaddam (ref_80) 2002; 40 Ustin (ref_68) 2004; 54 Avitabile (ref_10) 2016; 22 Gower (ref_2) 2003; 28 Lu (ref_24) 2005; 35 Monnet (ref_34) 2011; 8 Dong (ref_78) 2003; 84 ref_46 ref_44 Zeng (ref_45) 2018; 7 Genuer (ref_28) 2010; 31 (ref_29) 2016; 5 Lu (ref_22) 2005; 26 Fang (ref_43) 2001; 292 ref_7 ref_6
References_xml	– volume: 7 start-page: 1 year: 2018 ident: ref_45 article-title: Developing one-variable individual tree biomass models based on wood density for 34 tree species in China publication-title: For. Res. Open Access – volume: 176 start-page: 188 year: 2016 ident: ref_38 article-title: Integrating landsat pixel composites and change metrics with lidar plots to predictively map forest structure and aboveground biomass in Saskatchewan, Canada publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2016.01.015 – volume: 37 start-page: 37 year: 2002 ident: ref_31 article-title: Applications using estimates of forest parameters derived from satellite and forest inventory data publication-title: Comput. Electron. Agric. doi: 10.1016/S0168-1699(02)00118-7 – volume: 3 start-page: 1157 year: 2003 ident: ref_57 article-title: An introduction to variable and feature selection publication-title: J. Mach. Learn. Res. – volume: 8 start-page: 70 year: 2006 ident: ref_23 article-title: Optimization of second-order grey-level texture in high-resolution imagery for statistical estimation of above-ground biomass publication-title: J. Environ. Inf. doi: 10.3808/jei.200600078 – volume: 8 start-page: 84 year: 1982 ident: ref_48 article-title: On the slope-aspect correction of multispectral scanner data publication-title: Can. J. Remote Sens. doi: 10.1080/07038992.1982.10855028 – volume: 1 start-page: 131 year: 1997 ident: ref_60 article-title: Feature selection for classification publication-title: Intell. Data Anal. doi: 10.3233/IDA-1997-1302 – ident: ref_6 doi: 10.3390/rs9030241 – volume: 116 start-page: 363 year: 2002 ident: ref_1 article-title: Measuring carbon in forests: Current status and future challenges publication-title: Environ. Pollut. doi: 10.1016/S0269-7491(01)00212-3 – volume: 6 start-page: 7878 year: 2014 ident: ref_11 article-title: Estimating forest aboveground biomass by combining ALOS PALSAR and WorldView-2 data: A case study at Purple Mountain National Park, Nanjing, China publication-title: Remote Sens. doi: 10.3390/rs6097878 – volume: 31 start-page: 2225 year: 2010 ident: ref_28 article-title: Variable selection using random forests publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2010.03.014 – volume: 26 start-page: 2509 year: 2005 ident: ref_22 article-title: Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon publication-title: Int. J. Remote Sens. doi: 10.1080/01431160500142145 – ident: ref_66 doi: 10.3390/rs10040627 – volume: 178 start-page: 158 year: 2016 ident: ref_12 article-title: Estimation of forest biomass dynamics in subtropical forests using multi-temporal airborne LiDAR data publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2016.03.012 – volume: 48 start-page: 1095 year: 2011 ident: ref_42 article-title: Application of China’s National Forest Continuous Inventory Database publication-title: Environ. Manage. doi: 10.1007/s00267-011-9716-2 – ident: ref_58 – volume: 40 start-page: 362 year: 2014 ident: ref_20 article-title: Forest monitoring using landsat time series data: A review publication-title: Can. J. Remote Sens. doi: 10.1080/07038992.2014.987376 – volume: 3 start-page: 1 year: 2008 ident: ref_32 article-title: A first map of tropical Africa’s above-ground biomass derived from satellite imagery publication-title: Environ. Res. Lett. doi: 10.1088/1748-9326/3/4/045011 – volume: 222 start-page: 75 year: 2006 ident: ref_63 article-title: Stand biomass estimation method by canopy coverage for application to remote sensing in an arid area of Western Australia publication-title: For. Ecol. Manag. doi: 10.1016/j.foreco.2005.10.014 – volume: 40 start-page: 139 year: 2000 ident: ref_74 article-title: An experimental comparison of three methods for constructing ensembles of decision trees publication-title: Mach. Learn. doi: 10.1023/A:1007607513941 – volume: 28 start-page: 169 year: 2003 ident: ref_2 article-title: Patterns and mechanisms of the forest carbon cycle publication-title: Annu. Rev. Environ. Resour. doi: 10.1146/annurev.energy.28.050302.105515 – volume: 77 start-page: 802 year: 2008 ident: ref_61 article-title: A working guide to boosted regression trees publication-title: J. Anim. Ecol. doi: 10.1111/j.1365-2656.2008.01390.x – volume: 11 start-page: 52 year: 2009 ident: ref_40 article-title: Forest inventory in China: Status and challenges publication-title: Int. For. Rev. – ident: ref_27 – volume: 98 start-page: 105 year: 2018 ident: ref_55 article-title: A novel ensemble method for credit scoring: Adaption of different imbalance ratios publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2018.01.012 – volume: 84 start-page: 393 year: 2003 ident: ref_78 article-title: Remote sensing estimates of boreal and temperate forest woody biomass: Carbon pools, sources, and sinks publication-title: Remote Sens. Environ. doi: 10.1016/S0034-4257(02)00130-X – volume: 40 start-page: 2176 year: 2002 ident: ref_80 article-title: Forest variable estimation from fusion of SAR and multispectral optical data publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2002.804725 – volume: 199 start-page: 154 year: 2017 ident: ref_21 article-title: Estimating Mediterranean forest parameters using multi seasonal Landsat 8 OLI imagery and an ensemble learning method publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2017.07.018 – volume: SMC-3 start-page: 610 year: 1973 ident: ref_49 article-title: Textural features for image classification publication-title: IEEE Trans. Syst. Man. Cybern. doi: 10.1109/TSMC.1973.4309314 – ident: ref_69 – volume: 56 start-page: 2353 year: 2016 ident: ref_76 article-title: Extreme gradient boosting as a method for quantitative structure—Activity relationships publication-title: J. Chem. Inf. Model. doi: 10.1021/acs.jcim.6b00591 – volume: 15 start-page: 607 year: 2018 ident: ref_77 article-title: Very high resolution object-based land use–land cover urban classification using extreme gradient boosting publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2018.2803259 – volume: 6 start-page: 6407 year: 2014 ident: ref_73 article-title: Estimates of aboveground biomass from texture analysis of landsat imagery publication-title: Remote Sens. doi: 10.3390/rs6076407 – volume: 45 start-page: 5 year: 2001 ident: ref_51 article-title: Random forest publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – ident: ref_54 doi: 10.1145/2939672.2939785 – volume: 23 start-page: 2537 year: 2002 ident: ref_71 article-title: Vegetation and soil lines in visible spectral space: A concept and technique for remote estimation of vegetation fraction publication-title: Int. J. Remote Sens. doi: 10.1080/01431160110107806 – volume: 225 start-page: 127 year: 2019 ident: ref_14 article-title: Current status of Landsat program, science, and applications publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.02.015 – volume: 259 start-page: 23 year: 2018 ident: ref_25 article-title: Annual forest aboveground biomass changes mapped using ICESat/GLAS measurements, historical inventory data, and time-series optical and radar imagery for Guangdong province, China publication-title: Agric. For. Meteorol. doi: 10.1016/j.agrformet.2018.04.005 – volume: 8 start-page: 580 year: 2011 ident: ref_34 article-title: Support vector regression for the estimation of forest stand parameters using airborne laser scanning publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2010.2094179 – ident: ref_62 – volume: 11 start-page: 945 year: 2005 ident: ref_3 article-title: Aboveground forest biomass and the global carbon balance publication-title: Glob. Chang. Biol. doi: 10.1111/j.1365-2486.2005.00955.x – volume: 34 start-page: 549 year: 2008 ident: ref_17 article-title: Monitoring Canada’s forests. Part 1: Completion of the EOSD land cover project publication-title: Can. J. Remote Sens. doi: 10.5589/m08-066 – volume: 61 start-page: 304 year: 2019 ident: ref_39 article-title: Predicting failure in the U.S. banking sector: An extreme gradient boosting approach publication-title: Int. Rev. Econ. Financ. doi: 10.1016/j.iref.2018.03.008 – volume: 19 start-page: 535 year: 1998 ident: ref_19 article-title: Using shade fraction image segmentation to evaluate deforestation in landsat thematic mapper images of the Amazon Region publication-title: Int. J. Remote Sens. doi: 10.1080/014311698216152 – ident: ref_59 – volume: 25 start-page: 3999 year: 2004 ident: ref_81 article-title: Narrow band vegetation indices overcome the saturation problem in biomass estimation publication-title: Int. J. Remote Sens. doi: 10.1080/01431160310001654923 – ident: ref_30 doi: 10.3390/f10020104 – volume: 38 start-page: 367 year: 2002 ident: ref_56 article-title: Stochastic gradient boosting publication-title: Comput. Stat. Data Anal. doi: 10.1016/S0167-9473(01)00065-2 – volume: 22 start-page: 1406 year: 2016 ident: ref_10 article-title: An integrated pan-tropical biomass map using multiple reference datasets publication-title: Glob. Chang. Biol. doi: 10.1111/gcb.13139 – volume: 145 start-page: 154 year: 2014 ident: ref_16 article-title: Landsat-8: Science and product vision for terrestrial global change research publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2014.02.001 – volume: 292 start-page: 2320 year: 2001 ident: ref_43 article-title: Changes in forest biomass carbon storage in China between 1949 and 1998 publication-title: Science doi: 10.1126/science.1058629 – volume: 5 start-page: 65 year: 2016 ident: ref_29 article-title: Feature selection for high-dimensional data publication-title: Prog. Artif. Intell. doi: 10.1007/s13748-015-0080-y – volume: 80 start-page: 76 year: 2002 ident: ref_72 article-title: Novel algorithms for remote estimation of vegetation fraction publication-title: Remote Sens. Environ. doi: 10.1016/S0034-4257(01)00289-9 – volume: 7 start-page: 16398 year: 2015 ident: ref_79 article-title: Review of machine learning approaches for biomass and soil moisture retrievals from remote sensing data publication-title: Remote Sens. doi: 10.3390/rs71215841 – volume: 113 start-page: 691 year: 2009 ident: ref_33 article-title: Estimating Siberian timber volume using MODIS and ICESat/GLAS publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2008.11.010 – volume: 2 start-page: 23 year: 2015 ident: ref_41 article-title: The national forest inventory in China: History—Results—International context publication-title: For. Ecosyst. doi: 10.1186/s40663-015-0047-2 – volume: 7 start-page: 10017 year: 2015 ident: ref_37 article-title: Mapping tree canopy cover and aboveground biomass in sudano-sahelian woodlands using landsat 8 and random forest publication-title: Remote Sens. doi: 10.3390/rs70810017 – volume: 6 start-page: 10232 year: 2014 ident: ref_70 article-title: The spectral response of the Landsat-8 operational land imager publication-title: Remote Sens. doi: 10.3390/rs61010232 – volume: 27 start-page: 1297 year: 2006 ident: ref_9 article-title: The potential and challenge of remote sensing-based biomass estimation publication-title: Int. J. Remote Sens. doi: 10.1080/01431160500486732 – ident: ref_44 – volume: 18 start-page: 1099 year: 1997 ident: ref_47 article-title: Correction of Atmospheric and Topographic Effects for High Spatial Resolution Satellite Imagery publication-title: Int. J. Remote Sens. doi: 10.1080/014311697218593 – volume: 114 start-page: 1 year: 2009 ident: ref_4 article-title: Importance of biomass in the global carbon cycle publication-title: J. Geophys. Res. Biogeosci. doi: 10.1029/2009JG000935 – volume: 29 start-page: 1407 year: 2018 ident: ref_52 article-title: Forest type identification by random forest classification combined with SPOT and multitemporal SAR data publication-title: J. For. Res. doi: 10.1007/s11676-017-0530-4 – volume: 112 start-page: 1658 year: 2008 ident: ref_35 article-title: Mapping U.S. forest biomass using nationwide forest inventory data and moderate resolution information publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2007.08.021 – volume: 13 start-page: 249 year: 2008 ident: ref_67 article-title: Estimation of stand volumes using the k-nearest neighbors method in Kyushu, Japan publication-title: J. For. Res. doi: 10.1007/s10310-008-0077-5 – volume: 21 start-page: 453 year: 2013 ident: ref_18 article-title: Forest cover trends from time series Landsat data for the Australian continent publication-title: Int. J. Appl. Earth Obs. Geoinf. – ident: ref_50 – volume: 9 start-page: 63 year: 2016 ident: ref_64 article-title: A survey of remote sensing-based aboveground biomass estimation methods in forest ecosystems publication-title: Int. J. Digit. Earth doi: 10.1080/17538947.2014.990526 – volume: 54 start-page: 523 year: 2004 ident: ref_68 article-title: Using imaging spectroscopy to study ecosystem processes and properties publication-title: Bioscience doi: 10.1641/0006-3568(2004)054[0523:UISTSE]2.0.CO;2 – volume: 11 start-page: 1 year: 2016 ident: ref_26 article-title: Scalable and accurate online feature selection for big data publication-title: ACM Trans. Knowl. Discov. Data doi: 10.1145/2821513 – volume: 46 start-page: 323 year: 2016 ident: ref_65 article-title: Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance publication-title: Can. J. For. Res. doi: 10.1139/cjfr-2014-0562 – ident: ref_46 – volume: 574 start-page: 628 year: 2019 ident: ref_53 article-title: How to explain and predict the shape parameter of the generalized extreme value distribution of streamflow extremes using a big dataset publication-title: J. Hydrol. doi: 10.1016/j.jhydrol.2019.04.070 – volume: 185 start-page: 1 year: 2016 ident: ref_13 article-title: Landsat 8: The plans, the reality, and the legacy publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2016.07.033 – volume: 7 start-page: 1 year: 2006 ident: ref_75 article-title: Gene selection and classification of microarray data using random forest publication-title: BMC Bioinf. – volume: 71 start-page: 967 year: 2005 ident: ref_5 article-title: Satellite estimation of aboveground biomass and impacts of forest stand structure publication-title: Photogramm. Eng. Remote Sens. doi: 10.14358/PERS.71.8.967 – ident: ref_7 doi: 10.1007/978-3-319-14708-6 – volume: 35 start-page: 249 year: 2005 ident: ref_24 article-title: Exploring TM image texture and its relationships with biomass estimation in Rondônia, Brazilian Amazon publication-title: Acta Amaz. doi: 10.1590/S0044-59672005000200015 – volume: 10 start-page: 243 year: 2017 ident: ref_8 article-title: Consequences of landsat image strata classification errors on bias and variance of inventory estimates: A forest inventory case study publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2016.2597762 – volume: 121 start-page: 426 year: 2012 ident: ref_36 article-title: Understanding the relationship between aboveground biomass and ALOS PALSAR data in the forests of Guinea-Bissau (West Africa) publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2012.02.012 – volume: 122 start-page: 22 year: 2012 ident: ref_15 article-title: Landsat: Building a strong future publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2011.09.022
SSID	ssj0000578924
Score	2.537153
Snippet	Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for...
SourceID	proquest crossref
SourceType	Aggregation Database Enrichment Source Index Database
StartPage	1073
SubjectTerms	Algorithms Biodiversity Biomass Carbon Carbon cycle Decision trees Ecological monitoring Ecosystems Feature selection Forest biomass Forest ecosystems Landsat Landsat satellites Learning algorithms Machine learning Model accuracy Modelling National forests Regression analysis Remote sensing Remote sensing systems Satellites Terrestrial ecosystems Timber Variables
Title	Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms
URI	https://www.proquest.com/docview/2548466271
Volume	10
WOSCitedRecordID	wos000507288400082&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: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: M~E dateStart: 20100101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Agricultural Science Database customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: M0K dateStart: 20100301 isFulltext: true titleUrlDefault: https://search.proquest.com/agriculturejournals providerName: ProQuest – providerCode: PRVPQU databaseName: Earth, Atmospheric & Aquatic Science Database customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: PCBAR dateStart: 20100301 isFulltext: true titleUrlDefault: https://search.proquest.com/eaasdb providerName: ProQuest – providerCode: PRVPQU databaseName: Environmental Science Database customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: PATMY dateStart: 20100301 isFulltext: true titleUrlDefault: http://search.proquest.com/environmentalscience providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: BENPR dateStart: 20100301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1999-4907 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000578924 issn: 1999-4907 databaseCode: PIMPY dateStart: 20100301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8JAEN4IGOPFtxFFsjEevDRAX7s9GTAQiYE0voKnptvdIgkCUuTgwd_uTLvFkBgvXpq0ncMmszsz3-7s9xFyaaNOiF3nRmw3FAAUZRmCe7ZhuaEnhQtxU_BUbIL1-3ww8Hy94Zbotso8JqaBWk4j3COvAZCBVOmarHE9ezdQNQpPV7WERoGUkKkM5nmp1e7796tdFqhGOCCMjFLIAnxfi5HQCjCPtZ6I1uNwmlw6u_8d1h7Z0WUlbWbzYJ9sqMkB2ULdTRRzOySf3VyMhE5j-gwAGa9M0YdUBQdcQ8OJpJk5RWhK4ZN-bYrpUuHlD7BojbCdKKFtCAzZnUea9hzQXtqTqaimax3S5ngIw1y8viVH5KnTfry5NbTsghFZDl8YeJIqYaEqTP0RFFDCEtJxuRKuGTLTjJUdM0vZDIqVWNpMMObWpc3dyBGm4qF1TIqT6USdEBoyJ2TI0A8rHSo_J2xwT0IIcRuRdKC0KJOr3AdBpDnJURpjHAA2QXcFK3eVycXKdJYRcfxmVMm9FOi1mAQ_Ljr9-_cZ2YZyyMuaVSqkuJh_qHOyGS0Xo2Re1VOrSgq9-h0-v9rwze_2_JdvM-_byw
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9NAEB2VBEEvUKCohUJXFUhcrMTetXd9QFVaUiXKhyJRUDi5Xu86jZQmpQ5F8KP4jZ3xR1AkxC2HHm2PLHn3-c3M7uw8gHeCdEJEUzmpcC0mKJY7WoXC4UEcGh0gb2qVi03I4VCNx-FoC_5UZ2GorLLixJyozSKhNfIGJjLoKgNPusfX3x1SjaLd1UpCo4BFz_76iSlb9rH7Cef3veedtc9PO06pKuAk3FdLhzYKDeLQkmdLMD7QXBs_UFYHXiw9L7UildwKib44NUJqKYOmESpIfO1ZFXN87wOoCwJ7Deqj7mD0bbWqg9GPwoymaGHEedhspNRAC3Msvu741nk_d2ZnT-_bMOzAkzJsZq0C589gy86fwyPSFSWxuhfwu1uJrbBFyr7G-FvpmWWfc5UfhB6L54YV5oxSb4a3ysuWXtxaOtyCFidTKpfKWBuJrzjTyfKaCjbIa04tK9vRTlhrNsFhWV5eZbvwZSNf_hJq88Xc7gGLpR9LUiBAJsPI1o9dFRqkyMBNjI-h0z58qOY8Ssqe6yT9MYsw9yJ4RCt47MPRyvS6aDTyL6ODChVRyTVZ9BcSr_7_-BAed84H_ajfHfZewzaGfmFRmHMAteXND_sGHia3y2l287aENYOLTUPoDnldM3U
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LS8NAEB5qK-LFt_h2EQUvoW12k90cRKq1WKql4AM9xWx2U4XaqqmK_jR_nbN5VATx5sFjkiGQ3S8z8-3OzgewzYxOCKsIK2JVjQRFU0sKj1nUDTwlXfSbUiRiE7zdFldXXqcAH_lZGFNWmfvExFGrQWjWyMtIZDBUujavlqOsLKJTb-w_PFpGQcrstOZyGilEWvrtFelbvNes41zv2Hbj6Pzw2MoUBqyQOmJomU1DhZjUJsqFmCtIKpXjCi1dO-C2HWkWcaoZx7gcKcYl525FMeGGjrS1CCi-dwxKmJIzuwilTvO0cz1a4cFMSCC7SdsZUepVypFppoV8i34Pgt9jQBLYGtP_eUhmYCpLp0ktxf8sFHR_DiaM3qgRsZuH92YuwkIGEbkM8HeTPU3OEvUfhCQJ-oqk5sRQcoK3ssuaHLxoc-gFLQ7uTBlVTI7QIaZnPUlSa0FOk1pUTbI2tV1S63VxWIa39_ECXPzJly9CsT_o6yUgAXcCbpQJ0MNhxusEVeEpdJ1uNVQOplTLsJvPvx9mvdiNJEjPR05moOKPoLIMWyPTh7QByU9GazlC_MwHxf4XPFZ-f7wJE4gb_6TZbq3CJGaEXlqvswbF4dOzXofx8GV4Fz9tZAgncPPXCPoEfiI8NQ
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=Influence+of+Variable+Selection+and+Forest+Type+on+Forest+Aboveground+Biomass+Estimation+Using+Machine+Learning+Algorithms&rft.jtitle=Forests&rft.au=Li%2C+Yingchang&rft.au=Li%2C+Chao&rft.au=Li%2C+Mingyang&rft.au=Liu%2C+Zhenzhen&rft.date=2019-12-01&rft.pub=MDPI+AG&rft.eissn=1999-4907&rft.volume=10&rft.issue=12&rft.spage=1073&rft_id=info:doi/10.3390%2Ff10121073&rft.externalDBID=HAS_PDF_LINK
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1999-4907&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1999-4907&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1999-4907&client=summon