Enhancing the accuracy of machine learning models using the super learner technique in digital soil mapping
•The super learner is promising approach for Digital Soil Mapping.•Super learner increased accuracy by up to ~46%, compared to base learners.•Permutation feature importance revealed the contribution of each covariate. Digital soil mapping approaches predict soil properties based on the relationships...
Saved in:
| Published in | Geoderma Vol. 399; p. 115108 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.10.2021
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •The super learner is promising approach for Digital Soil Mapping.•Super learner increased accuracy by up to ~46%, compared to base learners.•Permutation feature importance revealed the contribution of each covariate.
Digital soil mapping approaches predict soil properties based on the relationships between soil observations and related environmental covariates using techniques such as machine learning (ML) models. In this research, a wide range of ML models (12 base learners) were tested in predicting and mapping soil properties. Furthermore, a super learner approach was used to improve model accuracy by combining the predictions of the base learners. A major challenge of using super learner and complex models is that the exact contribution of individual covariates in the overall prediction is not always known. To address this issue, permutation feature importance (PFI) analysis was applied as a model-agnostic interpretation tool. The weights assigned to each ML base learner obtained from super learner, and feature importance values obtained from each ML base learner were used to quantify the contribution of individual covariates on the final prediction. The super learner and PFI techniques were tested by predicting a variety of soil physical and chemical properties of the Urmia Lake playa in Iran. As expected, the results indicated that the super learner had substantially higher accuracies for predicting soil properties in comparison to the individual base learners. For instance, the super learner showed an improved performance in comparison to linear regression by decreasing the root mean square error by an average of 46%. The PFI analysis revealed the important contribution of geomorphic and groundwater data in predicting soil properties. Overall, the proposed approach may be used for improving accuracy of ML models in digital soil mapping. |
|---|---|
| AbstractList | Digital soil mapping approaches predict soil properties based on the relationships between soil observations and related environmental covariates using techniques such as machine learning (ML) models. In this research, a wide range of ML models (12 base learners) were tested in predicting and mapping soil properties. Furthermore, a super learner approach was used to improve model accuracy by combining the predictions of the base learners. A major challenge of using super learner and complex models is that the exact contribution of individual covariates in the overall prediction is not always known. To address this issue, permutation feature importance (PFI) analysis was applied as a model-agnostic interpretation tool. The weights assigned to each ML base learner obtained from super learner, and feature importance values obtained from each ML base learner were used to quantify the contribution of individual covariates on the final prediction. The super learner and PFI techniques were tested by predicting a variety of soil physical and chemical properties of the Urmia Lake playa in Iran. As expected, the results indicated that the super learner had substantially higher accuracies for predicting soil properties in comparison to the individual base learners. For instance, the super learner showed an improved performance in comparison to linear regression by decreasing the root mean square error by an average of 46%. The PFI analysis revealed the important contribution of geomorphic and groundwater data in predicting soil properties. Overall, the proposed approach may be used for improving accuracy of ML models in digital soil mapping. •The super learner is promising approach for Digital Soil Mapping.•Super learner increased accuracy by up to ~46%, compared to base learners.•Permutation feature importance revealed the contribution of each covariate. Digital soil mapping approaches predict soil properties based on the relationships between soil observations and related environmental covariates using techniques such as machine learning (ML) models. In this research, a wide range of ML models (12 base learners) were tested in predicting and mapping soil properties. Furthermore, a super learner approach was used to improve model accuracy by combining the predictions of the base learners. A major challenge of using super learner and complex models is that the exact contribution of individual covariates in the overall prediction is not always known. To address this issue, permutation feature importance (PFI) analysis was applied as a model-agnostic interpretation tool. The weights assigned to each ML base learner obtained from super learner, and feature importance values obtained from each ML base learner were used to quantify the contribution of individual covariates on the final prediction. The super learner and PFI techniques were tested by predicting a variety of soil physical and chemical properties of the Urmia Lake playa in Iran. As expected, the results indicated that the super learner had substantially higher accuracies for predicting soil properties in comparison to the individual base learners. For instance, the super learner showed an improved performance in comparison to linear regression by decreasing the root mean square error by an average of 46%. The PFI analysis revealed the important contribution of geomorphic and groundwater data in predicting soil properties. Overall, the proposed approach may be used for improving accuracy of ML models in digital soil mapping. |
| ArticleNumber | 115108 |
| Author | Scholten, Thomas Taghizadeh-Mehrjardi, Ruhollah Hassanzadeh, Maryam Ghebleh Goydaragh, Maryam Heung, Brandon Hamzehpour, Nikou Schmidt, Karsten |
| Author_xml | – sequence: 1 givenname: Ruhollah orcidid: 0000-0002-4620-6624 surname: Taghizadeh-Mehrjardi fullname: Taghizadeh-Mehrjardi, Ruhollah email: taghizadeh-mehrjardi@mnf.uni-tuebingen.de organization: Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tübingen, Germany – sequence: 2 givenname: Nikou surname: Hamzehpour fullname: Hamzehpour, Nikou email: nhamzehpour@maragheh.ac.ir organization: Soil Science Department, Faculty of Agriculture, University of Maragheh, Maragheh, Iran – sequence: 3 givenname: Maryam surname: Hassanzadeh fullname: Hassanzadeh, Maryam email: m.hasanzadeh@maragheh.ac.ir organization: Soil Science Department, Faculty of Agriculture, University of Maragheh, Maragheh, Iran – sequence: 4 givenname: Brandon surname: Heung fullname: Heung, Brandon email: brandon.heung@dal.ca organization: Department of Plant, Food, and Environmental Sciences, Faculty of Agriculture, Dalhousie University, Canada – sequence: 5 givenname: Maryam surname: Ghebleh Goydaragh fullname: Ghebleh Goydaragh, Maryam email: maryam.ghebleh@tabrizu.ac.ir organization: Department of Soil Science, Faculty of Agriculture, University of Tabriz, Tabriz, Iran – sequence: 6 givenname: Karsten surname: Schmidt fullname: Schmidt, Karsten email: karsten.schmidt@uni-tuebingen.de organization: eScience Center, University of Tübingen, 72070 Tübingen, Germany – sequence: 7 givenname: Thomas orcidid: 0000-0002-4875-2602 surname: Scholten fullname: Scholten, Thomas email: thomas.scholten@uni-tuebingen.de organization: Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tübingen, Germany |
| BookMark | eNqFkM1O3DAUhS1EJYafV0BedpOpf7A9kbooQtAiIbGBtXVr38x4SOzUTpB4ezwKbLphdWX5O8fX3yk5jikiIZecrTnj-sd-vcXkMQ-wFkzwNeeKs80RWfGNEY0Wqj0mK1bJxjDNT8hpKft6NEywFXm5jTuILsQtnXZIwbk5g3ujqaMDuF2ISHuEHA_AUF_pC53LJ13mEfNyX-eEbhfDvxlpiNSHbZigpyWFvjaNY82ck28d9AUvPuYZeb67fbr50zw8_r6_uX5oQOrN1AiDigmFXjFpPEqQeNVp403nlYTOeNZpzTSAcL6VV95hy__6Dgxy5Vum5Bn5vvSOOdV1ymSHUBz2PURMc7FCKd5KIdtNRfWCupxKydjZMYcB8pvlzB7s2r39tGsPdu1itwZ__hd09b9TSHHKEPqv47-WeBWKrwGzLS5gdOhDRjdZn8JXFe9Cnp6v |
| CitedBy_id | crossref_primary_10_1007_s42729_024_02182_1 crossref_primary_10_1016_j_compag_2022_107512 crossref_primary_10_1016_j_ecolind_2024_112654 crossref_primary_10_1016_j_geoderma_2024_116873 crossref_primary_10_3390_land12020494 crossref_primary_10_1016_j_catena_2023_106915 crossref_primary_10_1071_SR22042 crossref_primary_10_1007_s10661_023_11145_5 crossref_primary_10_2139_ssrn_3980079 crossref_primary_10_3390_land11122279 crossref_primary_10_1016_j_jhazmat_2024_136689 crossref_primary_10_1002_ece3_10090 crossref_primary_10_1111_ejss_13323 crossref_primary_10_1111_ejss_13368 crossref_primary_10_1016_j_compgeo_2022_105014 crossref_primary_10_1093_jrsssc_qlae070 crossref_primary_10_1016_j_pce_2024_103561 crossref_primary_10_34133_remotesensing_0130 crossref_primary_10_1109_JSTARS_2022_3164140 crossref_primary_10_1016_j_geoderma_2023_116383 crossref_primary_10_1016_j_envpol_2022_120931 crossref_primary_10_1139_cjss_2021_0091 crossref_primary_10_3390_agronomy14112707 crossref_primary_10_1007_s44353_024_00012_0 crossref_primary_10_3390_s22166153 crossref_primary_10_1016_j_isprsjprs_2023_04_018 crossref_primary_10_3390_rs14215571 crossref_primary_10_2139_ssrn_4181497 crossref_primary_10_3390_bdcc7020113 crossref_primary_10_1016_j_geodrs_2021_e00440 crossref_primary_10_3390_en14217367 crossref_primary_10_1016_j_jenvman_2024_123339 crossref_primary_10_1016_j_geoderma_2024_116850 crossref_primary_10_1007_s12145_025_01748_6 crossref_primary_10_1016_j_ijsrc_2024_04_003 crossref_primary_10_1016_j_still_2024_106220 crossref_primary_10_1016_j_ecoinf_2022_101933 crossref_primary_10_3390_rs14030472 crossref_primary_10_3390_land13030365 crossref_primary_10_1002_jpln_202200239 crossref_primary_10_1016_j_jag_2022_102969 crossref_primary_10_1097_HEP_0000000000000908 crossref_primary_10_1109_TGRS_2024_3446042 crossref_primary_10_1016_j_scitotenv_2023_167488 crossref_primary_10_1007_s13762_024_06183_6 crossref_primary_10_3390_rs15071751 crossref_primary_10_1016_j_catena_2023_107799 crossref_primary_10_1007_s13369_024_08961_3 crossref_primary_10_1016_j_compag_2022_106965 crossref_primary_10_1007_s40808_024_02127_8 crossref_primary_10_1016_j_geoderma_2025_117257 crossref_primary_10_1002_ird_3037 crossref_primary_10_1007_s12665_024_11834_5 crossref_primary_10_1016_j_cmpb_2023_107737 crossref_primary_10_1016_j_geoderma_2023_116446 crossref_primary_10_1007_s12672_024_01337_x crossref_primary_10_1016_j_ecolind_2022_108545 crossref_primary_10_1016_j_geoderma_2022_116265 crossref_primary_10_1016_j_still_2023_105684 crossref_primary_10_3390_land12091769 crossref_primary_10_3390_agronomy12030628 crossref_primary_10_1016_j_atmosenv_2022_119274 crossref_primary_10_1016_j_atmosres_2022_106406 crossref_primary_10_3389_feart_2024_1488504 crossref_primary_10_1016_j_geoderma_2024_116824 crossref_primary_10_1016_j_aiia_2024_08_001 crossref_primary_10_1016_j_geoderma_2023_116604 crossref_primary_10_1016_j_geodrs_2022_e00563 crossref_primary_10_1007_s10661_022_10678_5 |
| Cites_doi | 10.3390/rs12071095 10.1016/j.earscirev.2011.01.005 10.1016/j.geoderma.2018.12.037 10.2202/1544-6115.1309 10.1016/j.geoderma.2015.11.014 10.2136/sssabookser5.4.c14 10.1371/journal.pone.0125814 10.1007/978-0-387-21606-5_1 10.2136/sssabookser5.4.c12 10.1016/j.geomorph.2017.02.015 10.1016/j.geoderma.2015.12.003 10.1080/17583004.2017.1330593 10.2202/1544-6115.1240 10.1097/EDE.0000000000000762 10.1007/s00254-008-1245-9 10.1007/s10654-018-0390-z 10.1016/j.geoderma.2013.07.020 10.1111/j.2517-6161.1996.tb02080.x 10.1016/j.earscirev.2020.103359 10.3390/rs12010085 10.1016/j.scitotenv.2020.137703 10.2136/sssaj1950.036159950014000C0005x 10.1016/j.geoderma.2018.09.006 10.1111/j.1365-2389.2009.01205.x 10.2136/sssabookser5.3.c14 10.1007/s10994-006-6226-1 10.1016/j.geoderma.2019.114145 10.1016/j.cageo.2007.05.001 10.1016/j.apm.2019.12.016 10.1016/j.geoderma.2016.02.026 10.1016/j.geodrs.2020.e00256 10.1016/j.catena.2019.104424 10.1016/j.scitotenv.2016.11.078 10.1016/j.geoderma.2020.114237 10.1109/21.256541 10.5194/soil-4-1-2018 10.1016/j.jpsychires.2017.09.010 10.1016/S0016-7061(03)00223-4 10.1007/BF00117832 10.1002/eap.1557 10.1023/A:1010933404324 10.1007/s10040-018-1830-2 10.1016/j.geoderma.2004.06.007 10.1016/j.catena.2020.104675 10.1080/02664763.2010.505956 10.1515/ijb-2014-0060 10.1016/j.catena.2018.07.019 10.1016/j.ecolind.2018.01.049 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier B.V. |
| Copyright_xml | – notice: 2021 Elsevier B.V. |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.geoderma.2021.115108 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Agriculture |
| EISSN | 1872-6259 |
| ExternalDocumentID | 10_1016_j_geoderma_2021_115108 S0016706121001889 |
| GeographicLocations | Iran |
| GeographicLocations_xml | – name: Iran |
| GroupedDBID | --K --M -DZ -~X .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JM 9JN AABNK AABVA AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AATLK AAXUO ABFRF ABGRD ABJNI ABMAC ABQEM ABQYD ABYKQ ACDAQ ACGFO ACGFS ACIUM ACLVX ACRLP ACSBN ADBBV ADEZE ADQTV AEBSH AEFWE AEKER AENEX AEQOU AFKWA AFTJW AFXIZ AGHFR AGUBO AGYEJ AHHHB AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ATOGT AXJTR BKOJK BLXMC CBWCG CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IHE IMUCA J1W KOM LW9 LY3 LY9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SAB SDF SDG SES SPC SPCBC SSA SSE SSZ T5K ~02 ~G- 29H AAHBH AALCJ AAQXK AATTM AAXKI AAYWO AAYXX ABEFU ABFNM ABWVN ABXDB ACRPL ACVFH ADCNI ADMUD ADNMO ADVLN AEGFY AEIPS AEUPX AFFNX AFJKZ AFPUW AGCQF AGQPQ AGRNS AI. AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BNPGV CITATION EJD FEDTE FGOYB G-2 GROUPED_DOAJ HLV HMA HMC HVGLF HZ~ H~9 K-O OHT R2- RIG SEN SEP SEW SSH VH1 WUQ XPP Y6R ZMT 7S9 L.6 |
| ID | FETCH-LOGICAL-a368t-27e5025ed5037de3a3e4f67d7fd53af7d0f6606aa2cd934dce91bdfa7e15d9053 |
| IEDL.DBID | .~1 |
| ISSN | 0016-7061 |
| IngestDate | Thu Jul 10 18:34:04 EDT 2025 Thu Apr 24 22:51:33 EDT 2025 Tue Jul 01 04:04:55 EDT 2025 Fri Feb 23 02:43:32 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Saline soils Urmia Playa Lake Model-agnostic Digital soil mapping Iran Super learner |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a368t-27e5025ed5037de3a3e4f67d7fd53af7d0f6606aa2cd934dce91bdfa7e15d9053 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-4875-2602 0000-0002-4620-6624 |
| PQID | 2551932398 |
| PQPubID | 24069 |
| ParticipantIDs | proquest_miscellaneous_2551932398 crossref_primary_10_1016_j_geoderma_2021_115108 crossref_citationtrail_10_1016_j_geoderma_2021_115108 elsevier_sciencedirect_doi_10_1016_j_geoderma_2021_115108 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-10-01 2021-10-00 20211001 |
| PublicationDateYYYYMMDD | 2021-10-01 |
| PublicationDate_xml | – month: 10 year: 2021 text: 2021-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Geoderma |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Rudiyanto, Minasny, Setiawan, Arif, Saptomo, Chadirin (b0245) 2016; 272 Breiman (b0015) 2001; 45 McBratney, Mendonça Santos, Minasny (b0155) 2003; 117 Molnar, C., 2018. Interpretable Machine Learning-A Guide for Making Black Box Models Explainable, ebook. Leanpub, np. Tajik, Ayoubi, Zeraatpisheh (b0290) 2020; 20 Foster, Pulido-Bosch, Vallejos, Molina, Llop, MacDonald (b0055) 2018; 26 Wyss, Schneeweiss, van der Laan, Lendle, Ju, Franklin (b0335) 2018; 29 Koza, Koza (b0135) 1992 Taghizadeh-Mehrjardi, Minasny, Sarmadian, Malone (b0270) 2014; 213 Polley, E., LeDell, E., Kennedy, C., Lendle, S., van der Laan, M., 2019. Package ‘SuperLearner’. CRAN. Keskin, Grunwald, Harris (b0125) 2019; 339 Taghizadeh-Mehrjardi, Neupane, Sood, Kumar (b0280) 2017; 8 Shapley (b0250) 1953; 2 RStudio, 2015. RStudio: integrated development for R. RStudio, Inc., Boston, MA URL http://www. rstudio. com 42, 14. Taghizadeh-Mehrjardi, Nabiollahi, Kerry (b0275) 2016; 266 Krinsley, D.B., 1970. A Geomorphological and Paleoclimatological Study of the Playas of Iran. Part II, GEOLOGICAL SURVEY RESTON VA. Wadoux, Minasny, McBratney (b0320) 2020; 210 Yegnanarayana (b0340) 2009 Jalali (b0110) 2009; 56 Jang (b0115) 1993; 23 Nimmo, J.R., Perkins, K.S., 2002. 2.6 Aggregate stability and size distribution. Methods of soil analysis: part 4 physical methods 5, 317-328. Zhou, Xue, Chen, Zhou, Liang, Wang, Shi (b0360) 2020; 12 Davies, Van Der Laan (b0040) 2016; 12 Chen, Mulder, Heuvelink, Poggio, Caubet, Román Dobarco, Walter, Arrouays (b0025) 2020; 366 Kuhn (b0145) 2013 Song, Wu, Ju, Liu, Yang, Li, Zhao, Yang, Zhang (b0265) 2020; 363 Friedman, J., Hastie, T., Tibshirani, R., 2001. The elements of statistical learning, 1. Springer series in statistics New York. Minasny, Hartemink (b0160) 2011; 106 Vapnik, Golowich, Smola (b0315) 1997 Hengl, Heuvelink, Rossiter (b0095) 2007; 33 Heung, Ho, Zhang, Knudby, Bulmer, Schmidt (b0100) 2016; 265 Rhoades, J., 1996. Salinity: Electrical conductivity and total dissolved solids. Methods of Soil Analysis: Part 3 Chemical Methods 5, 417-435. Behrens, Schmidt, Zhu, Scholten (b0005) 2010; 61 van Bavel (b0300) 1950; 14 Nelson, Sommers (b0185) 1996; 5 Geurts, Ernst, Wehenkel (b0075) 2006; 63 Page, Miller, Keeney (b0200) 1982 Rosellini, Dussaillant, Zubizarreta, Kessler, Rose (b0235) 2018; 96 Van der Laan, Rose (b0310) 2011 Wang, Waters, Orgill, Cowie, Clark, Li Liu, Simpson, McGowen, Sides (b0325) 2018; 88 Curto, Pinto (b0035) 2011; 38 Hengl, Heuvelink, Kempen, Leenaars, Walsh, Shepherd, Sila, MacMillan, Mendes de Jesus, Tamene, Tondoh (b0090) 2015; 10 R Core Team (b0225) 2015 (b0150) 2013 Quinlan (b0220) 1992 Tibshirani (b0295) 1996; 58 Alizadeh Motaghi, Hamzehpour, Mola Ali Abasiyan, Rahmati (b0170) 2020; 194 Fisher, A., Rudin, C., Dominici, F., 2018. All models are wrong but many are useful: Variable importance for black-box, proprietary, or misspecified prediction models, using model class reliance. arXiv preprint arXiv:1801.01489, 237-246. Geological Survey of Iran (b0070) 1995 Poggio, Gimona (b0205) 2017; 579 Sinisi, S.E., Polley, E.C., Petersen, M.L., Rhee, S. Y., Van Der Laan, M.J., 2007. Super learning: an application to the prediction of HIV-1 drug resistance. Statistical applications in genetics and molecular biology 6(1). Naimi, Balzer (b0180) 2018; 33 Gee, G.W., Or, D., 2002. 2.4 Particle‐size analysis. Methods of soil analysis: Part 4 physical methods 5, 255-293. Hamzehpour, Eghbal, Abasiyan, Dill (b0080) 2018; 171 Nussbaum, Spiess, Baltensweiler, Grob, Keller, Greiner, Schaepman, Papritz (b0195) 2018; 4 Iran Ministry of Energy, 2014. The National Water Master Plan Study in the Aras, Sefidrood, between Sefidrood and Haraz, Atrac and Urmia: agricultural water use study in Urmia Lake Basin, Tehran. Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., 2015. Xgboost: extreme gradient boosting. R package version 0.4-2, 1-4. Casalicchio, Molnar, Bischl (b0020) 2018 Khaledian, Miller (b0130) 2020; 81 Zeraatpisheh, Ayoubi, Jafari, Tajik, Finke (b0350) 2019; 338 Soil Survey Staff (b0260) 2014 Kemper, Chepil (b0120) 1965; 9 Zeraatpisheh, Jafari, Bagheri Bodaghabadi, Ayoubi, Taghizadeh-Mehrjardi, Toomanian, Kerry, Xu (b0355) 2020; 188 Muhammad, I.U., Muhammad, A., Muhammad, M.I.U., 2020. Package ‘mctest’. Van der Laan, Polley, Hubbard (b0305) 2007; 6 Breiman, L., 1996. Stacked regressions. Machine learning 24(1), 49-64. Wilson, Caughlin, Rifai, Boughton, Mack, Flory (b0330) 2017; 27 Fathololoumi, Vaezi, Alavipanah, Ghorbani, Saurette, Biswas (b0045) 2020; 721 Zeraatpisheh, Ayoubi, Jafari, Finke (b0345) 2017; 285 Henderson, Bui, Moran, Simon (b0085) 2005; 124 Taghizadeh-Mehrjardi, Schmidt, Amirian-Chakan, Rentschler, Zeraatpisheh, Sarmadian, Valavi, Davatgar, Behrens, Scholten (b0285) 2020; 12 Quinlan (10.1016/j.geoderma.2021.115108_b0220) 1992 R Core Team (10.1016/j.geoderma.2021.115108_b0225) 2015 Wadoux (10.1016/j.geoderma.2021.115108_b0320) 2020; 210 Khaledian (10.1016/j.geoderma.2021.115108_b0130) 2020; 81 Tibshirani (10.1016/j.geoderma.2021.115108_b0295) 1996; 58 Behrens (10.1016/j.geoderma.2021.115108_b0005) 2010; 61 Davies (10.1016/j.geoderma.2021.115108_b0040) 2016; 12 Breiman (10.1016/j.geoderma.2021.115108_b0015) 2001; 45 Van der Laan (10.1016/j.geoderma.2021.115108_b0310) 2011 Zeraatpisheh (10.1016/j.geoderma.2021.115108_b0355) 2020; 188 Kemper (10.1016/j.geoderma.2021.115108_b0120) 1965; 9 10.1016/j.geoderma.2021.115108_b0240 Zhou (10.1016/j.geoderma.2021.115108_b0360) 2020; 12 Casalicchio (10.1016/j.geoderma.2021.115108_b0020) 2018 10.1016/j.geoderma.2021.115108_b0165 Rudiyanto (10.1016/j.geoderma.2021.115108_b0245) 2016; 272 Poggio (10.1016/j.geoderma.2021.115108_b0205) 2017; 579 Wilson (10.1016/j.geoderma.2021.115108_b0330) 2017; 27 Nussbaum (10.1016/j.geoderma.2021.115108_b0195) 2018; 4 Jalali (10.1016/j.geoderma.2021.115108_b0110) 2009; 56 Alizadeh Motaghi (10.1016/j.geoderma.2021.115108_b0170) 2020; 194 Minasny (10.1016/j.geoderma.2021.115108_b0160) 2011; 106 Yegnanarayana (10.1016/j.geoderma.2021.115108_b0340) 2009 Wyss (10.1016/j.geoderma.2021.115108_b0335) 2018; 29 Koza (10.1016/j.geoderma.2021.115108_b0135) 1992 Page (10.1016/j.geoderma.2021.115108_b0200) 1982 Hengl (10.1016/j.geoderma.2021.115108_b0095) 2007; 33 Vapnik (10.1016/j.geoderma.2021.115108_b0315) 1997 Heung (10.1016/j.geoderma.2021.115108_b0100) 2016; 265 Curto (10.1016/j.geoderma.2021.115108_b0035) 2011; 38 10.1016/j.geoderma.2021.115108_b0050 Geological Survey of Iran (10.1016/j.geoderma.2021.115108_b0070) 1995 Chen (10.1016/j.geoderma.2021.115108_b0025) 2020; 366 Jang (10.1016/j.geoderma.2021.115108_b0115) 1993; 23 (10.1016/j.geoderma.2021.115108_b0150) 2013 10.1016/j.geoderma.2021.115108_b0010 10.1016/j.geoderma.2021.115108_b0175 Taghizadeh-Mehrjardi (10.1016/j.geoderma.2021.115108_b0285) 2020; 12 10.1016/j.geoderma.2021.115108_b0210 Hamzehpour (10.1016/j.geoderma.2021.115108_b0080) 2018; 171 Henderson (10.1016/j.geoderma.2021.115108_b0085) 2005; 124 Kuhn (10.1016/j.geoderma.2021.115108_b0145) 2013 10.1016/j.geoderma.2021.115108_b0255 Song (10.1016/j.geoderma.2021.115108_b0265) 2020; 363 Taghizadeh-Mehrjardi (10.1016/j.geoderma.2021.115108_b0280) 2017; 8 10.1016/j.geoderma.2021.115108_b0060 10.1016/j.geoderma.2021.115108_b0140 Van der Laan (10.1016/j.geoderma.2021.115108_b0305) 2007; 6 10.1016/j.geoderma.2021.115108_b0065 Soil Survey Staff (10.1016/j.geoderma.2021.115108_b0260) 2014 McBratney (10.1016/j.geoderma.2021.115108_b0155) 2003; 117 Fathololoumi (10.1016/j.geoderma.2021.115108_b0045) 2020; 721 Hengl (10.1016/j.geoderma.2021.115108_b0090) 2015; 10 Taghizadeh-Mehrjardi (10.1016/j.geoderma.2021.115108_b0275) 2016; 266 Naimi (10.1016/j.geoderma.2021.115108_b0180) 2018; 33 Shapley (10.1016/j.geoderma.2021.115108_b0250) 1953; 2 Foster (10.1016/j.geoderma.2021.115108_b0055) 2018; 26 Geurts (10.1016/j.geoderma.2021.115108_b0075) 2006; 63 Zeraatpisheh (10.1016/j.geoderma.2021.115108_b0345) 2017; 285 Nelson (10.1016/j.geoderma.2021.115108_b0185) 1996; 5 10.1016/j.geoderma.2021.115108_b0105 van Bavel (10.1016/j.geoderma.2021.115108_b0300) 1950; 14 10.1016/j.geoderma.2021.115108_b0030 10.1016/j.geoderma.2021.115108_b0230 Taghizadeh-Mehrjardi (10.1016/j.geoderma.2021.115108_b0270) 2014; 213 Tajik (10.1016/j.geoderma.2021.115108_b0290) 2020; 20 Zeraatpisheh (10.1016/j.geoderma.2021.115108_b0350) 2019; 338 Keskin (10.1016/j.geoderma.2021.115108_b0125) 2019; 339 Wang (10.1016/j.geoderma.2021.115108_b0325) 2018; 88 Rosellini (10.1016/j.geoderma.2021.115108_b0235) 2018; 96 10.1016/j.geoderma.2021.115108_b0190 |
| References_xml | – volume: 27 start-page: 1646 year: 2017 end-page: 1656 ident: b0330 article-title: Multi-decadal time series of remotely sensed vegetation improves prediction of soil carbon in a subtropical grassland publication-title: Ecol. Appl. – volume: 33 start-page: 459 year: 2018 end-page: 464 ident: b0180 article-title: Stacked generalization: an introduction to super learning publication-title: Eur. J. Epidemiol. – volume: 117 start-page: 3 year: 2003 end-page: 52 ident: b0155 article-title: On digital soil mapping publication-title: Geoderma – volume: 58 start-page: 267 year: 1996 end-page: 288 ident: b0295 article-title: Regression shrinkage and selection via the lasso publication-title: J. Roy. Stat. Soc.: Ser. B (Methodol.) – volume: 6 year: 2007 ident: b0305 article-title: Super learner publication-title: Statistical applications in genetics and molecular biology – volume: 96 start-page: 15 year: 2018 end-page: 22 ident: b0235 article-title: Predicting posttraumatic stress disorder following a natural disaster publication-title: J. Psychiatr. Res. – reference: RStudio, 2015. RStudio: integrated development for R. RStudio, Inc., Boston, MA URL http://www. rstudio. com 42, 14. – reference: Breiman, L., 1996. Stacked regressions. Machine learning 24(1), 49-64. – volume: 10 start-page: e0125814 year: 2015 ident: b0090 article-title: Mapping soil properties of Africa at 250 m resolution: Random forests significantly improve current predictions publication-title: PLoS ONE – volume: 8 start-page: 277 year: 2017 end-page: 291 ident: b0280 article-title: Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA publication-title: Carbon Manage. – volume: 210 start-page: 103359 year: 2020 ident: b0320 article-title: Machine learning for digital soil mapping: applications, challenges and suggested solutions publication-title: Earth Sci. Rev. – volume: 4 start-page: 1 year: 2018 end-page: 22 ident: b0195 article-title: Evaluation of digital soil mapping approaches with large sets of environmental covariates publication-title: Soil – volume: 20 start-page: e00256 year: 2020 ident: b0290 article-title: Digital mapping of soil organic carbon using ensemble learning model in Mollisols of Hyrcanian forests, northern Iran publication-title: Geoderma Regional – volume: 56 start-page: 1479 year: 2009 end-page: 1488 ident: b0110 article-title: Geochemistry characterization of groundwater in an agricultural area of Razan, Hamadan, Iran publication-title: Environ. Geol. – volume: 338 start-page: 445 year: 2019 end-page: 452 ident: b0350 article-title: Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran publication-title: Geoderma – volume: 26 start-page: 2781 year: 2018 end-page: 2791 ident: b0055 article-title: Impact of irrigated agriculture on groundwater-recharge salinity: a major sustainability concern in semi-arid regionsImpact de l’irrigation agricole sur la salinité de la recharge des eaux souterraines: une préoccupation majeure en matière de pérennité dans les régions semi-aridesImpacto de la agricultura de regadio en la salinidad de recarga de agua subterranea: una gran preocupacion para la sostenibilidad en las regiones semiaridas灌溉农业对地下水—补给盐度的影响:半干旱地区一个重要的、受到关注的可持续问题Impacto da agricultura irrigada na salinidade da recarga de águas subterrâneas: uma grande preocupação quanto à sustentabilidade em regiões semiáridas publication-title: Hydrogeol. J. – reference: Gee, G.W., Or, D., 2002. 2.4 Particle‐size analysis. Methods of soil analysis: Part 4 physical methods 5, 255-293. – year: 2014 ident: b0260 article-title: Keys to soil taxonomy – volume: 194 start-page: 104675 year: 2020 ident: b0170 article-title: The wind erodibility in the newly emerged surfaces of Urmia Playa Lake and adjacent agricultural lands and its determining factors publication-title: Catena – year: 1995 ident: b0070 article-title: Geological Quadrangle Map – reference: Rhoades, J., 1996. Salinity: Electrical conductivity and total dissolved solids. Methods of Soil Analysis: Part 3 Chemical Methods 5, 417-435. – reference: Polley, E., LeDell, E., Kennedy, C., Lendle, S., van der Laan, M., 2019. Package ‘SuperLearner’. CRAN. – volume: 171 start-page: 398 year: 2018 end-page: 415 ident: b0080 article-title: Pedogenic evidence of Urmia Lake's maximum expansion in the late Quaternary publication-title: Catena – volume: 266 start-page: 98 year: 2016 end-page: 110 ident: b0275 article-title: Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran publication-title: Geoderma – year: 2009 ident: b0340 article-title: Artificial neural networks – volume: 63 start-page: 3 year: 2006 end-page: 42 ident: b0075 article-title: Extremely randomized trees publication-title: Mach. Learn. – reference: Fisher, A., Rudin, C., Dominici, F., 2018. All models are wrong but many are useful: Variable importance for black-box, proprietary, or misspecified prediction models, using model class reliance. arXiv preprint arXiv:1801.01489, 237-246. – volume: 9 start-page: 499 year: 1965 end-page: 510 ident: b0120 article-title: Size distribution of aggregates. Methods of Soil Analysis: Part 1 Physical and Mineralogical Properties publication-title: Including Statistics of Measurement and Sampling – volume: 106 start-page: 52 year: 2011 end-page: 62 ident: b0160 article-title: Predicting soil properties in the tropics publication-title: Earth Sci. Rev. – year: 2013 ident: b0150 publication-title: Applied Predictive Modeling – reference: Friedman, J., Hastie, T., Tibshirani, R., 2001. The elements of statistical learning, 1. Springer series in statistics New York. – year: 2015 ident: b0225 article-title: R: A language and environment for statistical computing – volume: 23 start-page: 665 year: 1993 end-page: 685 ident: b0115 article-title: ANFIS: adaptive-network-based fuzzy inference system publication-title: IEEE Trans. Systems Man Cybernetics – volume: 339 start-page: 40 year: 2019 end-page: 58 ident: b0125 article-title: Digital mapping of soil carbon fractions with machine learning publication-title: Geoderma – reference: Muhammad, I.U., Muhammad, A., Muhammad, M.I.U., 2020. Package ‘mctest’. – volume: 45 start-page: 5 year: 2001 end-page: 32 ident: b0015 article-title: Random forests publication-title: Mach. Learn. – volume: 12 start-page: 179 year: 2016 end-page: 201 ident: b0040 article-title: Optimal spatial prediction using ensemble machine learning publication-title: Int. J. Biostatistics – year: 1982 ident: b0200 article-title: Methods of soil analysis – volume: 12 start-page: 1095 year: 2020 ident: b0285 article-title: Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space publication-title: Remote Sensing – volume: 285 start-page: 186 year: 2017 end-page: 204 ident: b0345 article-title: Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran publication-title: Geomorphology – year: 2011 ident: b0310 article-title: Targeted learning: causal inference for observational and experimental data – volume: 88 start-page: 425 year: 2018 end-page: 438 ident: b0325 article-title: Estimating soil organic carbon stocks using different modelling techniques in the semi-arid rangelands of eastern Australia publication-title: Ecol. Ind. – reference: Nimmo, J.R., Perkins, K.S., 2002. 2.6 Aggregate stability and size distribution. Methods of soil analysis: part 4 physical methods 5, 317-328. – reference: Krinsley, D.B., 1970. A Geomorphological and Paleoclimatological Study of the Playas of Iran. Part II, GEOLOGICAL SURVEY RESTON VA. – volume: 579 start-page: 1094 year: 2017 end-page: 1110 ident: b0205 article-title: Assimilation of optical and radar remote sensing data in 3D mapping of soil properties over large areas publication-title: Sci. Total Environ. – volume: 14 start-page: 20 year: 1950 end-page: 23 ident: b0300 article-title: Mean weight-diameter of soil aggregates as a statistical index of aggregation 1 publication-title: Soil Sci. Soc. Am. J. – reference: Iran Ministry of Energy, 2014. The National Water Master Plan Study in the Aras, Sefidrood, between Sefidrood and Haraz, Atrac and Urmia: agricultural water use study in Urmia Lake Basin, Tehran. – volume: 363 start-page: 114145 year: 2020 ident: b0265 article-title: Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China publication-title: Geoderma – reference: Sinisi, S.E., Polley, E.C., Petersen, M.L., Rhee, S. Y., Van Der Laan, M.J., 2007. Super learning: an application to the prediction of HIV-1 drug resistance. Statistical applications in genetics and molecular biology 6(1). – volume: 29 start-page: 96 year: 2018 end-page: 106 ident: b0335 article-title: Using super learner prediction modeling to improve high-dimensional propensity score estimation publication-title: Epidemiology – start-page: 281 year: 1997 end-page: 287 ident: b0315 article-title: Support vector method for function approximation, regression estimation and signal processing publication-title: Adv. Neural Inform. Process. Syst. – volume: 213 start-page: 15 year: 2014 end-page: 28 ident: b0270 article-title: Digital mapping of soil salinity in Ardakan region, central Iran publication-title: Geoderma – start-page: 343 year: 1992 end-page: 348 ident: b0220 article-title: Learning with continuous classes, 5th Australian joint conference on artificial intelligence publication-title: World Scientific – volume: 272 start-page: 20 year: 2016 end-page: 31 ident: b0245 article-title: Digital mapping for cost-effective and accurate prediction of the depth and carbon stocks in Indonesian peatlands publication-title: Geoderma – volume: 124 start-page: 383 year: 2005 end-page: 398 ident: b0085 article-title: Australia-wide predictions of soil properties using decision trees publication-title: Geoderma – volume: 2 start-page: 307 year: 1953 end-page: 317 ident: b0250 article-title: A value for n-person games publication-title: Contrib. Theory Games – volume: 12 start-page: 85 year: 2020 ident: b0360 article-title: Fine-resolution mapping of soil total nitrogen across China based on weighted model averaging publication-title: Remote Sensing – volume: 721 start-page: 137703 year: 2020 ident: b0045 article-title: Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: a case study in Iran publication-title: Sci. Total Environ. – year: 2013 ident: b0145 article-title: Predictive Modeling with R and the caret Package – volume: 38 start-page: 1499 year: 2011 end-page: 1507 ident: b0035 article-title: The corrected vif (cvif) publication-title: J. Appl. Statistics – volume: 33 start-page: 1301 year: 2007 end-page: 1315 ident: b0095 article-title: About regression-kriging: from equations to case studies publication-title: Comput. Geosci. – volume: 265 start-page: 62 year: 2016 end-page: 77 ident: b0100 article-title: An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping publication-title: Geoderma – volume: 188 start-page: 104424 year: 2020 ident: b0355 article-title: Conventional and digital soil mapping in Iran: Past, present, and future publication-title: Catena – volume: 5 start-page: 961 year: 1996 end-page: 1010 ident: b0185 article-title: Total carbon, organic carbon, and organic matter. Methods of soil analysis publication-title: Part 3 Chemical methods – start-page: 1 year: 1992 ident: b0135 article-title: Genetic programming: on the programming of computers by means of natural selection – start-page: 655 year: 2018 end-page: 670 ident: b0020 article-title: Visualizing the feature importance for black box models publication-title: Joint European Conference on Machine Learning and Knowledge Discovery in Databases – volume: 81 start-page: 401 year: 2020 end-page: 418 ident: b0130 article-title: Selecting appropriate machine learning methods for digital soil mapping publication-title: Appl. Math. Model. – reference: Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., 2015. Xgboost: extreme gradient boosting. R package version 0.4-2, 1-4. – volume: 61 start-page: 133 year: 2010 end-page: 143 ident: b0005 article-title: The ConMap approach for terrain-based digital soil mapping publication-title: Eur. J. Soil Sci. – volume: 366 start-page: 114237 year: 2020 ident: b0025 article-title: Model averaging for mapping topsoil organic carbon in France publication-title: Geoderma – reference: Molnar, C., 2018. Interpretable Machine Learning-A Guide for Making Black Box Models Explainable, ebook. Leanpub, np. – ident: 10.1016/j.geoderma.2021.115108_b0175 – volume: 12 start-page: 1095 issue: 7 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0285 article-title: Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space publication-title: Remote Sensing doi: 10.3390/rs12071095 – volume: 106 start-page: 52 issue: 1-2 year: 2011 ident: 10.1016/j.geoderma.2021.115108_b0160 article-title: Predicting soil properties in the tropics publication-title: Earth Sci. Rev. doi: 10.1016/j.earscirev.2011.01.005 – volume: 339 start-page: 40 year: 2019 ident: 10.1016/j.geoderma.2021.115108_b0125 article-title: Digital mapping of soil carbon fractions with machine learning publication-title: Geoderma doi: 10.1016/j.geoderma.2018.12.037 – volume: 6 issue: 1 year: 2007 ident: 10.1016/j.geoderma.2021.115108_b0305 article-title: Super learner publication-title: Statistical applications in genetics and molecular biology doi: 10.2202/1544-6115.1309 – year: 2009 ident: 10.1016/j.geoderma.2021.115108_b0340 – ident: 10.1016/j.geoderma.2021.115108_b0165 – volume: 265 start-page: 62 year: 2016 ident: 10.1016/j.geoderma.2021.115108_b0100 article-title: An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping publication-title: Geoderma doi: 10.1016/j.geoderma.2015.11.014 – ident: 10.1016/j.geoderma.2021.115108_b0190 doi: 10.2136/sssabookser5.4.c14 – year: 1995 ident: 10.1016/j.geoderma.2021.115108_b0070 – volume: 10 start-page: e0125814 issue: 6 year: 2015 ident: 10.1016/j.geoderma.2021.115108_b0090 article-title: Mapping soil properties of Africa at 250 m resolution: Random forests significantly improve current predictions publication-title: PLoS ONE doi: 10.1371/journal.pone.0125814 – volume: 5 start-page: 961 year: 1996 ident: 10.1016/j.geoderma.2021.115108_b0185 article-title: Total carbon, organic carbon, and organic matter. Methods of soil analysis publication-title: Part 3 Chemical methods – start-page: 655 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0020 article-title: Visualizing the feature importance for black box models – ident: 10.1016/j.geoderma.2021.115108_b0060 doi: 10.1007/978-0-387-21606-5_1 – year: 1982 ident: 10.1016/j.geoderma.2021.115108_b0200 – ident: 10.1016/j.geoderma.2021.115108_b0065 doi: 10.2136/sssabookser5.4.c12 – volume: 285 start-page: 186 year: 2017 ident: 10.1016/j.geoderma.2021.115108_b0345 article-title: Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran publication-title: Geomorphology doi: 10.1016/j.geomorph.2017.02.015 – volume: 266 start-page: 98 year: 2016 ident: 10.1016/j.geoderma.2021.115108_b0275 article-title: Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran publication-title: Geoderma doi: 10.1016/j.geoderma.2015.12.003 – volume: 8 start-page: 277 issue: 3 year: 2017 ident: 10.1016/j.geoderma.2021.115108_b0280 article-title: Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA publication-title: Carbon Manage. doi: 10.1080/17583004.2017.1330593 – ident: 10.1016/j.geoderma.2021.115108_b0210 – ident: 10.1016/j.geoderma.2021.115108_b0255 doi: 10.2202/1544-6115.1240 – ident: 10.1016/j.geoderma.2021.115108_b0105 – volume: 29 start-page: 96 issue: 1 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0335 article-title: Using super learner prediction modeling to improve high-dimensional propensity score estimation publication-title: Epidemiology doi: 10.1097/EDE.0000000000000762 – volume: 56 start-page: 1479 issue: 7 year: 2009 ident: 10.1016/j.geoderma.2021.115108_b0110 article-title: Geochemistry characterization of groundwater in an agricultural area of Razan, Hamadan, Iran publication-title: Environ. Geol. doi: 10.1007/s00254-008-1245-9 – volume: 33 start-page: 459 issue: 5 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0180 article-title: Stacked generalization: an introduction to super learning publication-title: Eur. J. Epidemiol. doi: 10.1007/s10654-018-0390-z – start-page: 281 year: 1997 ident: 10.1016/j.geoderma.2021.115108_b0315 article-title: Support vector method for function approximation, regression estimation and signal processing publication-title: Adv. Neural Inform. Process. Syst. – ident: 10.1016/j.geoderma.2021.115108_b0050 – volume: 213 start-page: 15 year: 2014 ident: 10.1016/j.geoderma.2021.115108_b0270 article-title: Digital mapping of soil salinity in Ardakan region, central Iran publication-title: Geoderma doi: 10.1016/j.geoderma.2013.07.020 – volume: 58 start-page: 267 issue: 1 year: 1996 ident: 10.1016/j.geoderma.2021.115108_b0295 article-title: Regression shrinkage and selection via the lasso publication-title: J. Roy. Stat. Soc.: Ser. B (Methodol.) doi: 10.1111/j.2517-6161.1996.tb02080.x – volume: 210 start-page: 103359 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0320 article-title: Machine learning for digital soil mapping: applications, challenges and suggested solutions publication-title: Earth Sci. Rev. doi: 10.1016/j.earscirev.2020.103359 – volume: 12 start-page: 85 issue: 1 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0360 article-title: Fine-resolution mapping of soil total nitrogen across China based on weighted model averaging publication-title: Remote Sensing doi: 10.3390/rs12010085 – volume: 721 start-page: 137703 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0045 article-title: Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: a case study in Iran publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2020.137703 – volume: 14 start-page: 20 issue: C year: 1950 ident: 10.1016/j.geoderma.2021.115108_b0300 article-title: Mean weight-diameter of soil aggregates as a statistical index of aggregation 1 publication-title: Soil Sci. Soc. Am. J. doi: 10.2136/sssaj1950.036159950014000C0005x – ident: 10.1016/j.geoderma.2021.115108_b0030 – year: 2013 ident: 10.1016/j.geoderma.2021.115108_b0145 – volume: 338 start-page: 445 year: 2019 ident: 10.1016/j.geoderma.2021.115108_b0350 article-title: Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran publication-title: Geoderma doi: 10.1016/j.geoderma.2018.09.006 – volume: 61 start-page: 133 issue: 1 year: 2010 ident: 10.1016/j.geoderma.2021.115108_b0005 article-title: The ConMap approach for terrain-based digital soil mapping publication-title: Eur. J. Soil Sci. doi: 10.1111/j.1365-2389.2009.01205.x – ident: 10.1016/j.geoderma.2021.115108_b0230 doi: 10.2136/sssabookser5.3.c14 – volume: 63 start-page: 3 issue: 1 year: 2006 ident: 10.1016/j.geoderma.2021.115108_b0075 article-title: Extremely randomized trees publication-title: Mach. Learn. doi: 10.1007/s10994-006-6226-1 – volume: 9 start-page: 499 year: 1965 ident: 10.1016/j.geoderma.2021.115108_b0120 article-title: Size distribution of aggregates. Methods of Soil Analysis: Part 1 Physical and Mineralogical Properties publication-title: Including Statistics of Measurement and Sampling – volume: 363 start-page: 114145 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0265 article-title: Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China publication-title: Geoderma doi: 10.1016/j.geoderma.2019.114145 – year: 2015 ident: 10.1016/j.geoderma.2021.115108_b0225 – volume: 33 start-page: 1301 issue: 10 year: 2007 ident: 10.1016/j.geoderma.2021.115108_b0095 article-title: About regression-kriging: from equations to case studies publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2007.05.001 – volume: 81 start-page: 401 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0130 article-title: Selecting appropriate machine learning methods for digital soil mapping publication-title: Appl. Math. Model. doi: 10.1016/j.apm.2019.12.016 – ident: 10.1016/j.geoderma.2021.115108_b0240 – volume: 272 start-page: 20 year: 2016 ident: 10.1016/j.geoderma.2021.115108_b0245 article-title: Digital mapping for cost-effective and accurate prediction of the depth and carbon stocks in Indonesian peatlands publication-title: Geoderma doi: 10.1016/j.geoderma.2016.02.026 – volume: 20 start-page: e00256 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0290 article-title: Digital mapping of soil organic carbon using ensemble learning model in Mollisols of Hyrcanian forests, northern Iran publication-title: Geoderma Regional doi: 10.1016/j.geodrs.2020.e00256 – volume: 188 start-page: 104424 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0355 article-title: Conventional and digital soil mapping in Iran: Past, present, and future publication-title: Catena doi: 10.1016/j.catena.2019.104424 – ident: 10.1016/j.geoderma.2021.115108_b0140 – volume: 2 start-page: 307 issue: 28 year: 1953 ident: 10.1016/j.geoderma.2021.115108_b0250 article-title: A value for n-person games publication-title: Contrib. Theory Games – year: 2013 ident: 10.1016/j.geoderma.2021.115108_b0150 – year: 2011 ident: 10.1016/j.geoderma.2021.115108_b0310 – start-page: 343 year: 1992 ident: 10.1016/j.geoderma.2021.115108_b0220 article-title: Learning with continuous classes, 5th Australian joint conference on artificial intelligence publication-title: World Scientific – volume: 579 start-page: 1094 year: 2017 ident: 10.1016/j.geoderma.2021.115108_b0205 article-title: Assimilation of optical and radar remote sensing data in 3D mapping of soil properties over large areas publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2016.11.078 – volume: 366 start-page: 114237 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0025 article-title: Model averaging for mapping topsoil organic carbon in France publication-title: Geoderma doi: 10.1016/j.geoderma.2020.114237 – volume: 23 start-page: 665 issue: 3 year: 1993 ident: 10.1016/j.geoderma.2021.115108_b0115 article-title: ANFIS: adaptive-network-based fuzzy inference system publication-title: IEEE Trans. Systems Man Cybernetics doi: 10.1109/21.256541 – volume: 4 start-page: 1 issue: 1 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0195 article-title: Evaluation of digital soil mapping approaches with large sets of environmental covariates publication-title: Soil doi: 10.5194/soil-4-1-2018 – volume: 96 start-page: 15 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0235 article-title: Predicting posttraumatic stress disorder following a natural disaster publication-title: J. Psychiatr. Res. doi: 10.1016/j.jpsychires.2017.09.010 – volume: 117 start-page: 3 issue: 1-2 year: 2003 ident: 10.1016/j.geoderma.2021.115108_b0155 article-title: On digital soil mapping publication-title: Geoderma doi: 10.1016/S0016-7061(03)00223-4 – ident: 10.1016/j.geoderma.2021.115108_b0010 doi: 10.1007/BF00117832 – volume: 27 start-page: 1646 issue: 5 year: 2017 ident: 10.1016/j.geoderma.2021.115108_b0330 article-title: Multi-decadal time series of remotely sensed vegetation improves prediction of soil carbon in a subtropical grassland publication-title: Ecol. Appl. doi: 10.1002/eap.1557 – volume: 45 start-page: 5 issue: 1 year: 2001 ident: 10.1016/j.geoderma.2021.115108_b0015 article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – start-page: 1 year: 1992 ident: 10.1016/j.geoderma.2021.115108_b0135 – volume: 26 start-page: 2781 issue: 8 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0055 publication-title: Hydrogeol. J. doi: 10.1007/s10040-018-1830-2 – volume: 124 start-page: 383 issue: 3-4 year: 2005 ident: 10.1016/j.geoderma.2021.115108_b0085 article-title: Australia-wide predictions of soil properties using decision trees publication-title: Geoderma doi: 10.1016/j.geoderma.2004.06.007 – volume: 194 start-page: 104675 year: 2020 ident: 10.1016/j.geoderma.2021.115108_b0170 article-title: The wind erodibility in the newly emerged surfaces of Urmia Playa Lake and adjacent agricultural lands and its determining factors publication-title: Catena doi: 10.1016/j.catena.2020.104675 – year: 2014 ident: 10.1016/j.geoderma.2021.115108_b0260 – volume: 38 start-page: 1499 issue: 7 year: 2011 ident: 10.1016/j.geoderma.2021.115108_b0035 article-title: The corrected vif (cvif) publication-title: J. Appl. Statistics doi: 10.1080/02664763.2010.505956 – volume: 12 start-page: 179 issue: 1 year: 2016 ident: 10.1016/j.geoderma.2021.115108_b0040 article-title: Optimal spatial prediction using ensemble machine learning publication-title: Int. J. Biostatistics doi: 10.1515/ijb-2014-0060 – volume: 171 start-page: 398 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0080 article-title: Pedogenic evidence of Urmia Lake's maximum expansion in the late Quaternary publication-title: Catena doi: 10.1016/j.catena.2018.07.019 – volume: 88 start-page: 425 year: 2018 ident: 10.1016/j.geoderma.2021.115108_b0325 article-title: Estimating soil organic carbon stocks using different modelling techniques in the semi-arid rangelands of eastern Australia publication-title: Ecol. Ind. doi: 10.1016/j.ecolind.2018.01.049 |
| SSID | ssj0017020 |
| Score | 2.5874457 |
| Snippet | •The super learner is promising approach for Digital Soil Mapping.•Super learner increased accuracy by up to ~46%, compared to base learners.•Permutation... Digital soil mapping approaches predict soil properties based on the relationships between soil observations and related environmental covariates using... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 115108 |
| SubjectTerms | Digital soil mapping groundwater Iran lakes Model-agnostic playas prediction regression analysis Saline soils Super learner Urmia Playa Lake |
| Title | Enhancing the accuracy of machine learning models using the super learner technique in digital soil mapping |
| URI | https://dx.doi.org/10.1016/j.geoderma.2021.115108 https://www.proquest.com/docview/2551932398 |
| Volume | 399 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07b9swECYCZ0mGomkS1H0YLJBVsWRSIjUaQQKnRTMlQDaC4kOR60qGH0OX_vbeSZSRBAg8dBIkkQRxPN59BO--I-SCMylk4ZMInIGPuDGw5xxzUVxwI3xmY6vxRvfnXTZ74N8f08cDctXnwmBYZbD9nU1vrXX4Mg7SHC-rCnN8k0zELQNWnEiJSXycC9Tyy7-7MI9ExIGaMckibP0sS3gOa4QFx1r-oUkC1gMUVL7loF6Z6tb_3Lwn7wJwpNNubifkwNUfyPG0XAXyDHdKfl3XT0ifUZcUYB3VxmxX2vyhjae_25hJR0ORiJK2FXDWFMPeu9br7dKtuv_w3FG70qqmtiqxtAhdN9UCRkJGh_KMPNxc31_NolBMIdIsk5toIlwK-MbZNGbCOqaZ4z4TVnibMu2FjX0GhxmtJ8bmjFvj8qSwXguXpDaHrXpOBnVTu4-EMg1GIEemfQn4K3W5tgWPvfe6AHQo7ZCkvQSVCUzjWPBiofqQsrnqJa9Q8qqT_JCMd_2WHdfG3h55v0DqhdYocAh7-37rV1TBlsJ7El27ZrtWcMpCWMty-ek_xv9MjvCtC_z7Qgab1dZ9BQCzKUatho7I4fT2x-zuHymp8kA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT-MwEB51y4HlgGAXxBsj7TVqUiexc6xQUXn1BBI3y_EjhEda9XHg3zNOnIpFQhw4RYozVjQznvksj78B-BdTznhuowCTgQ1ipXDNGWqCMI8Vs6kOtXQnurfjdHQfXz0kDx04b-_CuLJKH_ubmF5Ha_-m57XZm5alu-MbpSysGbDCiPPsF6w5dqqkC2uDy-vReHWYwELPzhilgRP4cFH4Cc3keo7VFET9CAMI-ij_Kkd9itZ1CrrYgk2PHcmg-b1t6JjqD2wMipnnzzB_4XlYPToGjaogiOyIVGo5k-qNTCx5rcsmDfF9IgpSN8GZE1f53nw9X07NrBnH54rdlZQV0WXhuouQ-aR8wZkcqUOxA_cXw7vzUeD7KQSSpnwR9JlJEOIYnYSUaUMlNbFNmWZWJ1RapkOb4n5Gyr7SGY21MlmUayuZiRKd4WrdhW41qcweECoxDmSObJ8jBEtMJnUeh9ZamSNA5HofklaDQnmycdfz4kW0VWVPotW8cJoXjeb3obeSmzZ0G99KZK2BxH-OIzAnfCt71lpU4KpyRyWyMpPlXOBGyyFbmvGDH8x_Cuuju9sbcXM5vj6E326kqQM8gu5itjTHiGcW-Yn313dzVPTx |
| 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=Enhancing+the+accuracy+of+machine+learning+models+using+the+super+learner+technique+in+digital+soil+mapping&rft.jtitle=Geoderma&rft.au=Taghizadeh-Mehrjardi%2C+Ruhollah&rft.au=Hamzehpour%2C+Nikou&rft.au=Hassanzadeh%2C+Maryam&rft.au=Heung%2C+Brandon&rft.date=2021-10-01&rft.issn=0016-7061&rft.volume=399+p.115108-&rft_id=info:doi/10.1016%2Fj.geoderma.2021.115108&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0016-7061&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0016-7061&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0016-7061&client=summon |