Bayesian Deep Learning for Spatial Interpolation in the Presence of Auxiliary Information

Earth scientists increasingly deal with ‘big data’. For spatial interpolation tasks, variants of kriging have long been regarded as the established geostatistical methods. However, kriging and its variants (such as regression kriging, in which auxiliary variables or derivatives of these are included...

Full description

Saved in:

Bibliographic Details
Published in:	Mathematical geosciences Vol. 54; no. 3; pp. 507 - 531
Main Authors:	Kirkwood, Charlie, Economou, Theo, Pugeault, Nicolas, Odbert, Henry
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2022 Springer Nature B.V
Subjects:	Approximation Artificial neural networks Bayesian analysis Bayesian theory Big Data Chemistry and Earth Sciences Computer Science Deep learning Earth and Environmental Science Earth Sciences Elevation Geostatistics Geotechnical Engineering & Applied Earth Sciences Hydrogeology Interpolation Machine learning Mathematical models Neural networks Pattern recognition Physics Probability theory Remote sensing Spatial data Spatial discrimination learning Special Issue Statistical analysis Statistical methods Statistics for Engineering Terrain Uncertainty Feature learning Uncertainty quantification Mapping Neural networks Geostatistics Machine learning
ISSN:	1874-8961, 1874-8953
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Earth scientists increasingly deal with ‘big data’. For spatial interpolation tasks, variants of kriging have long been regarded as the established geostatistical methods. However, kriging and its variants (such as regression kriging, in which auxiliary variables or derivatives of these are included as covariates) are relatively restrictive models and lack capabilities provided by deep neural networks. Principal among these is feature learning: the ability to learn filters to recognise task-relevant patterns in gridded data such as images. Here, we demonstrate the power of feature learning in a geostatistical context by showing how deep neural networks can automatically learn the complex high-order patterns by which point-sampled target variables relate to gridded auxiliary variables (such as those provided by remote sensing) and in doing so produce detailed maps. In order to cater for the needs of decision makers who require well-calibrated probabilities, we also demonstrate how both aleatoric and epistemic uncertainty can be quantified in our deep learning approach via a Bayesian approximation known as Monte Carlo dropout. In our example, we produce a national-scale probabilistic geochemical map from point-sampled observations with auxiliary data provided by a terrain elevation grid. By combining location information with automatically learned terrain derivatives, our deep learning approach achieves an excellent coefficient of determination ( R 2 = 0.74 ) and near-perfect probabilistic calibration on held-out test data. Our results indicate the suitability of Bayesian deep learning and its feature-learning capabilities for large-scale geostatistical applications where uncertainty matters. Graphic Abstract
AbstractList	Earth scientists increasingly deal with ‘big data’. For spatial interpolation tasks, variants of kriging have long been regarded as the established geostatistical methods. However, kriging and its variants (such as regression kriging, in which auxiliary variables or derivatives of these are included as covariates) are relatively restrictive models and lack capabilities provided by deep neural networks. Principal among these is feature learning: the ability to learn filters to recognise task-relevant patterns in gridded data such as images. Here, we demonstrate the power of feature learning in a geostatistical context by showing how deep neural networks can automatically learn the complex high-order patterns by which point-sampled target variables relate to gridded auxiliary variables (such as those provided by remote sensing) and in doing so produce detailed maps. In order to cater for the needs of decision makers who require well-calibrated probabilities, we also demonstrate how both aleatoric and epistemic uncertainty can be quantified in our deep learning approach via a Bayesian approximation known as Monte Carlo dropout. In our example, we produce a national-scale probabilistic geochemical map from point-sampled observations with auxiliary data provided by a terrain elevation grid. By combining location information with automatically learned terrain derivatives, our deep learning approach achieves an excellent coefficient of determination (R2=0.74) and near-perfect probabilistic calibration on held-out test data. Our results indicate the suitability of Bayesian deep learning and its feature-learning capabilities for large-scale geostatistical applications where uncertainty matters.Graphic Abstract Earth scientists increasingly deal with ‘big data’. For spatial interpolation tasks, variants of kriging have long been regarded as the established geostatistical methods. However, kriging and its variants (such as regression kriging, in which auxiliary variables or derivatives of these are included as covariates) are relatively restrictive models and lack capabilities provided by deep neural networks. Principal among these is feature learning: the ability to learn filters to recognise task-relevant patterns in gridded data such as images. Here, we demonstrate the power of feature learning in a geostatistical context by showing how deep neural networks can automatically learn the complex high-order patterns by which point-sampled target variables relate to gridded auxiliary variables (such as those provided by remote sensing) and in doing so produce detailed maps. In order to cater for the needs of decision makers who require well-calibrated probabilities, we also demonstrate how both aleatoric and epistemic uncertainty can be quantified in our deep learning approach via a Bayesian approximation known as Monte Carlo dropout. In our example, we produce a national-scale probabilistic geochemical map from point-sampled observations with auxiliary data provided by a terrain elevation grid. By combining location information with automatically learned terrain derivatives, our deep learning approach achieves an excellent coefficient of determination ( R 2 = 0.74 ) and near-perfect probabilistic calibration on held-out test data. Our results indicate the suitability of Bayesian deep learning and its feature-learning capabilities for large-scale geostatistical applications where uncertainty matters. Graphic Abstract
Author	Odbert, Henry Kirkwood, Charlie Economou, Theo Pugeault, Nicolas
Author_xml	– sequence: 1 givenname: Charlie orcidid: 0000-0003-3218-4097 surname: Kirkwood fullname: Kirkwood, Charlie email: c.kirkwood@exeter.ac.uk organization: Department of Mathematics, University of Exeter – sequence: 2 givenname: Theo surname: Economou fullname: Economou, Theo organization: Department of Mathematics, University of Exeter, Climate and Atmosphere Research Centre, The Cyprus Institute – sequence: 3 givenname: Nicolas surname: Pugeault fullname: Pugeault, Nicolas organization: School of Computing Science, University of Glasgow – sequence: 4 givenname: Henry surname: Odbert fullname: Odbert, Henry organization: Met Office
BookMark	eNp9kE9LwzAYh4NMcJt-AU8Bz9WkTdPkOOe_wUBBPXgKaft2ZnRJTTpw3964ioKHnX4JPE_yvr8JGllnAaFzSi4pIcVVoDFYQlKaECmFSMgRGlNRsETIPBv9njk9QZMQ1oRwmuV0jN6u9Q6C0RbfAHR4CdpbY1e4cR4_d7o3usUL24PvXBtvzmJjcf8O-MlDAFsBdg2ebT9Na7TfRTSKmz14io4b3QY4-8kper27fZk_JMvH-8V8tkx0JnifQJZCk4KQdR0zY4yyKqellEA1BQF1WTHKWaU5lwWvRVHmAFXD8pqTsiYsm6KL4d3Ou48thF6t3dbb-KVKOeOSS0FFpMRAVd6F4KFRlen3c_Zem1ZRor6LVEORKhap9kUqEtX0n9p5s4nbHpayQQoRtivwf1MdsL4A6PKIqA
CitedBy_id	crossref_primary_10_1002_esp_5678 crossref_primary_10_3390_rs16173327 crossref_primary_10_1007_s11004_023_10125_2 crossref_primary_10_3390_atmos13081233 crossref_primary_10_1007_s10489_024_05913_0 crossref_primary_10_1016_j_measurement_2023_113019 crossref_primary_10_1016_j_earscirev_2024_104941 crossref_primary_10_1007_s10489_024_05541_8 crossref_primary_10_1007_s11053_022_10144_6 crossref_primary_10_1144_jgs2022_136 crossref_primary_10_1007_s11004_023_10087_5 crossref_primary_10_1080_13658816_2024_2347316 crossref_primary_10_1002_esp_6032 crossref_primary_10_1016_j_eswa_2025_129336 crossref_primary_10_1016_j_spasta_2024_100825 crossref_primary_10_1080_01431161_2025_2492412 crossref_primary_10_1109_ACCESS_2024_3388292 crossref_primary_10_1016_j_cageo_2025_105964 crossref_primary_10_1016_j_gexplo_2023_107174 crossref_primary_10_1016_j_jenvman_2025_125035 crossref_primary_10_1016_j_atmosenv_2024_120834 crossref_primary_10_1016_j_marpolbul_2025_118464 crossref_primary_10_5194_soil_10_679_2024 crossref_primary_10_1038_s41598_025_08844_z crossref_primary_10_1007_s11004_024_10163_4 crossref_primary_10_1017_aer_2024_110
Cites_doi	10.5194/soil-5-79-2019 10.1016/j.geoderma.2010.12.018 10.1016/j.jappgeo.2014.09.013 10.1007/BF00889887 10.1016/j.gexplo.2016.05.003 10.1109/CVPRW.2016.90 10.1016/j.neunet.2007.04.024 10.1029/94JB03097 10.1016/S0094-5765(01)00020-0 10.5194/gmd-14-3899-2021 10.1016/j.geoderma.2019.05.012 10.2307/1400558 10.1016/j.geoderma.2019.05.031 10.1016/S0169-1368(99)00007-4 10.1007/s10346-015-0614-1 10.1080/00401706.1993.10485354 10.1190/INT-2015-0188.1 10.1016/j.agrformet.2011.07.021 10.1109/LGRS.2017.2764915 10.5194/soil-5-107-2019 10.1002/2017GL075710 10.1007/978-1-4612-1494-6 10.1016/j.earscirev.2019.02.023 10.1080/09208118908944041 10.1016/j.jsg.2018.11.010 10.2139/ssrn.3695311 10.1007/978-1-4612-0745-0_2 10.1007/s00477-007-0165-7 10.1111/j.1467-9868.2007.00587.x 10.21105/joss.00747 10.1007/978-3-319-69320-0_8 10.1201/b16018 10.1144/1467-7873/05-070 10.1098/rsta.2020.0099 10.1109/MGRS.2017.2762307 10.1002/hyp.9578 10.1126/sciadv.1700578 10.1016/j.gsf.2020.04.015 10.1144/SP453.12 10.1016/j.geoderma.2013.05.029 10.1109/MGRS.2016.2540798 10.1016/j.cageo.2007.05.001 10.1371/journal.pone.0202691 10.1007/978-1-4757-4286-2 10.1038/nature14539 10.1190/geo2018-0646.1 10.1016/j.isprsjprs.2014.02.013 10.1146/annurev-statistics-062713-085831 10.1007/BF00893318 10.3390/rs6098639 10.2113/gsecongeo.69.5.673 10.1029/2000RG000089 10.1198/016214506000001437 10.1016/j.petrol.2020.107933 10.1007/978-3-319-69320-0_9
ContentType	Journal Article
Copyright	The Author(s) 2022 The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2022 – notice: The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION 7SC 7TG 7UA 8FD C1K F1W FR3 H8D H96 JQ2 KL. KR7 L.G L7M L~C L~D
DOI	10.1007/s11004-021-09988-0
DatabaseName	Springer Nature OA Free Journals CrossRef Computer and Information Systems Abstracts Meteorological & Geoastrophysical Abstracts Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ProQuest Computer Science Collection Meteorological & Geoastrophysical Abstracts - Academic Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Water Resources Abstracts Environmental Sciences and Pollution Management Computer and Information Systems Abstracts Professional Aerospace Database Meteorological & Geoastrophysical Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Meteorological & Geoastrophysical Abstracts - Academic
DatabaseTitleList	Civil Engineering Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Geology Physics Computer Science
EISSN	1874-8953
EndPage	531
ExternalDocumentID	10_1007_s11004_021_09988_0
GrantInformation_xml	– fundername: Engineering and Physical Sciences Research Council grantid: 2071900 funderid: http://dx.doi.org/10.13039/501100000266 – fundername: Horizon 2020 grantid: 856612 funderid: http://dx.doi.org/10.13039/501100007601
GroupedDBID	-5A -5G -BR -EM -Y2 -~C .86 .VR 06D 0R~ 0VY 199 1N0 203 29M 2J2 2JN 2JY 2KG 2KM 2LR 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5VS 67M 67Z 6NX 78A 7XC 88I 8FE 8FG 8FH 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDBF ABDZT ABECU ABFTV ABHLI ABHQN ABJCF ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACZOJ ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEUYN AEVLU AEXYK AFBBN AFEXP AFGCZ AFKRA AFLOW AFQWF AFRAH AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AOCGG ARAPS ARMRJ ATCPS AXYYD AYJHY AZFZN AZQEC B-. BDATZ BENPR BGLVJ BGNMA BHPHI BKSAR BPHCQ BSONS C6C CAG CCPQU COF CSCUP DDRTE DNIVK DPUIP DU5 DWQXO EBLON EBS EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 H13 HCIFZ HF~ HG5 HG6 HLICF HMJXF HQYDN HRMNR HVGLF HZ~ I-F IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K6V K7- KOV L6V L8X LK5 LLZTM M0N M2P M4Y M7R M7S MA- N2Q N9A NB0 NPVJJ NQJWS NU0 O9- O93 O9G O9J OAM P2P P62 PATMY PCBAR PF0 PQQKQ PROAC PT4 PTHSS PYCSY Q2X QOS R89 R9I RIG ROL RPX RSV S16 S1Z S27 S3B SAP SCK SCLPG SDH SEV SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z5O Z7R Z7X Z7Y Z7Z Z83 Z86 Z88 Z8M Z8R Z8S Z8T Z8W Z8Z ZMTXR ~02 ~A9 AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP AMVHM ATHPR AYFIA CITATION PHGZM PHGZT PQGLB 7SC 7TG 7UA 8FD C1K F1W FR3 H8D H96 JQ2 KL. KR7 L.G L7M L~C L~D
ID	FETCH-LOGICAL-a386t-e32ef2e89ddef234414c51b99e1a1e8edbc4164ca66976d87b5eecf45d60bd043
IEDL.DBID	RSV
ISICitedReferencesCount	36
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000743447700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1874-8961
IngestDate	Thu Sep 25 00:56:03 EDT 2025 Sat Nov 29 02:45:21 EST 2025 Tue Nov 18 22:28:07 EST 2025 Fri Feb 21 02:47:20 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	3
Keywords	Feature learning Uncertainty quantification Mapping Neural networks Geostatistics Machine learning
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-a386t-e32ef2e89ddef234414c51b99e1a1e8edbc4164ca66976d87b5eecf45d60bd043
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-3218-4097
OpenAccessLink	https://link.springer.com/10.1007/s11004-021-09988-0
PQID	2646969818
PQPubID	54390
PageCount	25
ParticipantIDs	proquest_journals_2646969818 crossref_citationtrail_10_1007_s11004_021_09988_0 crossref_primary_10_1007_s11004_021_09988_0 springer_journals_10_1007_s11004_021_09988_0
PublicationCentury	2000
PublicationDate	2022-04-01
PublicationDateYYYYMMDD	2022-04-01
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg – name: Dordrecht
PublicationTitle	Mathematical geosciences
PublicationTitleAbbrev	Math Geosci
PublicationYear	2022
Publisher	Springer Berlin Heidelberg Springer Nature B.V
Publisher_xml	– name: Springer Berlin Heidelberg – name: Springer Nature B.V
References	Hijmans RJ (2017) raster: Geographic Data Analysis and Modeling. R package version 2.6-7 PoggioLGimonaABrewerMJRegional scale mapping of soil properties and their uncertainty with a large number of satellite-derived covariatesGeoderma2013209114 Dimitrakopoulos R (2018) Stochastic mine planning-methods, examples and value in an uncertain world. In: Advances in applied strategic mine planning. Springer, pp 101–115 JournelAGGeostatistics for conditional simulation of ore bodiesEcon Geol1974695673687 Kirkwood C (2020) Deep covariate-learning: optimising information extraction from terrain texture for geostatistical modelling applications. arXiv preprint arXiv:2005.11194 LiTShenHYuanQZhangXZhangLEstimating ground-level PM2.5 by fusing satellite and station observations: a geo-intelligent deep learning approachGeophys Res Lett2017442311985 Kirkwood C (2016) A dropout-regularised neural network for mapping arsenic enrichment in SW England using MXNet. NERC open research archive Fox CR, Ülkümen G (2011) Distinguishing two dimensions of uncertainty. Perspectives on thinking, judging, and decision making 14 BergerJOStatistical decision theory and bayesian analysis1985BerlinSpringer YoeCPrinciples of risk analysis: decision making under uncertainty2011CambridgeCRC Press LaahaGSkøienJBlöschlGSpatial prediction on river networks: comparison of top-kriging with regional regressionHydrol Process2014282315324 GelmanACarlinJBSternHSDunsonDBVehtariARubinDBBayesian data analysis2013CambridgeCRC Press Vann J, Bertoli O, Jackson S (2002) An overview of geostatistical simulation for quantifying risk. In: Proceedings of geostatistical association of Australasia symposium” quantifying risk and error, vol 1, Citeseer, 1 Raftery AE, Lewis SM (1996) Implementing MCMC. Markov chain Monte Carlo in practice, pp 115–130 CressieNThe origins of krigingMath Geol1990223239252 MosegaardKTarantolaAMonte carlo sampling of solutions to inverse problemsJ Geophys Res Solid Earth1995100B71243112447 Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: International conference on machine learning, pp 1050–1059 British Geological Survey (2020) Geology of Britain Viewer. Accessed through online web interface at http://mapapps.bgs.ac.uk/geologyofbritain/home.html CawleyGCJanacekGJHaylockMRDorlingSRPredictive uncertainty in environmental modellingNeural Netw2007204537549 Wilson AG (2020) The case for Bayesian deep learning. arXiv preprint arXiv:2001.10995 SrivastavaNHintonGKrizhevskyASutskeverISalakhutdinovRDropout: a simple way to prevent neural networks from overfittingJ Mach Learn Res201415119291958 Tarantola A, Valette B (1982) Inverse problems = quest for information. J Geophys 50(1):159–170 LamichhaneSKumarLWilsonBDigital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: a reviewGeoderma2019352395413 R Core Team (2020) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna KrigeDGA statistical approach to some basic mine valuation problems on the witwatersrandJ South Afr Inst Min Metall1951526119139 WellmannJFDe La VargaMMurdieREGessnerKJessellMUncertainty estimation for a geological model of the sandstone greenstone belt, western Australia-insights from integrated geological and geophysical inversion in a Bayesian inference frameworkGeol Soc Spec Publ201845314156 Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265–283 Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 MulderVDe BruinSSchaepmanMEMayrTThe use of remote sensing in soil and terrain mapping-a reviewGeoderma20111621–2119 ShamsipourPSchetselaarEBellefleurGMarcotteD3D stochastic inversion of potential field data using structural geologic constraintsJ Appl Geophys2014111173182 AlzubaidiFMostaghimiPSwietojanskiPClarkSRArmstrongRTAutomated lithology classification from drill core images using convolutional neural networksJ Pet Sci Eng2021197107933 GneitingTRafteryAEStrictly proper scoring rules, prediction, and estimationJ Am Stat Assoc2007102477359378 Schaaf A, de la Varga M, Wellmann F, Bond CE (2021) Constraining stochastic 3-D structural geological models with topology information usingÚpproximate Bayesian computation in GemPy 2.1. Geoscientific Model Dev 14(6):3899–3913 HenglTHeuvelinkGBRossiterDGAbout regression-kriging: from equations to case studiesComput Geosci2007331013011315 Dillon JV, Langmore I, Tran D, Brevdo E, Vasudevan S, Moore D, Patton B, Alemi A, Hoffman M, Saurous RA (2017) Tensorflow distributions. arXiv preprint arXiv:1711.10604 GneitingTBalabdaouiFRafteryAEProbabilistic forecasts, calibration and sharpnessJ R Stat Soc B2007692243268 PerolTGharbiMDenolleMConvolutional neural network for earthquake detection and locationSci Adv201842e1700578 Ruiz-AriasJPozo-VázquezDSantos-AlamillosFLara-FanegoVTovar-PescadorJA topographic geostatistical approach for mapping monthly mean values of daily global solar radiation: a case study in southern spainAgric For Meteorol20111511218121822 KirkwoodCEconomouTOdbertHPugeaultNA framework for probabilistic weather forecast post-processing across models and lead times using machine learningPhilos Trans R Soc A2021379219420200099 LeCunYBengioYHintonGDeep learningNature20155217553436444 PilzJSpöckGWhy do we need and how should we implement bayesian kriging methodsStoch Environ Res Risk Assess2008225621632 de la Varga M, Wellmann JF (2016) Structural geologic modeling as an inference problem: a bayesian perspective. Interpretation 4(3):SM1–SM16 DimitrakopoulosRConditional simulation algorithms for modelling orebody uncertainty in open pit optimisationInt J Min Reclam Environ1998124173179 Sambridge M, Mosegaard K (2002) Monte Carlo methods in geophysical inverse problems. Rev Geophys 40(3):1–29 ColominaIMolinaPUnmanned aerial systems for photogrammetry and remote sensing: a reviewISPRS J Photogramm2014927997 Kampffmeyer M, Salberg AB, Jenssen R (2016) Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 1–9 LeNailANn-svg: Publication-ready neural network architecture schematicsJ. Open Source Softw.2019433747 Menabde M, Froyland G, Stone P, Yeates G (2018) Mining schedule optimisation for conditionally simulated orebodies. In: Advances in applied strategic mine planning. Springer, pp 91–100 Van ZylJJThe shuttle radar topography mission (SRTM): a breakthrough in remote sensing of topographyActa Astronaut2001485–12559565 KirkwoodCCaveMBeamishDGrebbySFerreiraAA machine learning approach to geochemical mappingJ Geochem Explor20161674961 ZuoRXiongYWangJCarranzaEJMDeep learning and its application in geochemical mappingEarth Sci Rev2019192114 ParmentierBMcGillBWilsonAMRegetzJJetzWGuralnickRPTuanmuMNRobinsonNSchildhauerMAn assessment of methods and remote-sensing derived covariates for regional predictions of 1 km daily maximum air temperatureRemote Sens20146986398670 WadouxAMJPadarianJMinasnyBMulti-source data integration for soil mapping using deep learningSoil201951107119 Li Y, Sun Y, Reich BJ (2020) Deepkriging: Spatially dependent deep neural networks for spatial prediction. arXiv preprint arXiv:2007.11972 GroseLAilleresLLaurentGArmitRJessellMInversion of geological knowledge for fold geometryJ Struct Geol2019119114 GneitingTKatzfussMProbabilistic forecastingAnnu Rev Stat Appl20141125151 Wu X, Liang L, Shi Y, Fomel S (2019) Faultseg3d: Using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation. Geophysics 84(3):IM35–IM45 WadouxAMCUsing deep learning for multivariate mapping of soil with quantified uncertaintyGeoderma20193515970 Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105 SabinsFFRemote sensing for mineral explorationOre Geol Rev1999143–4157183 Shwartz-Ziv R, Tishby N (2017) Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810 OlierookHKScalzoRKohnDChandraRFarahbakhshEClarkCReddySMMüllerRDBayesian geological and geophysical data fusion for the construction and uncertainty quantification of 3d geological modelsGeosci Front2021121479493 ClarkIStatistics or geostatistics? Sampling error or nugget effect?J South Afr Inst Min Metal20101106307312 YoussefAMPourghasemiHRPourtaghiZSAl-KatheeriMMLandslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi ArabiaLandslides2016135839856 ChenYZhuLGhamisiPJiaXLiGTangLHyperspectral images classification with gabor filtering and convolutional neural networkIEEE Geosci Remote Sens Lett2017141223552359 Young DM, Parry LE, Lee D, Ray S (2018) Spatial models with covariates improve estimates of peat depth in blanket peatlands. PLoS ONE 13(9):e0202691 PadarianJMinasnyBMcBratneyABUsing deep learning for digital soil mappingSoil2019517989 ZhuXXTuiaDMouLXiaGSZhangLXuFFraundorferFDeep learning in remote sensing: A comprehensive review and list of resourcesIEEE Trans Geosci Remote Sens201754836 JournelAGRossiMWhen do we need a trend model in kriging?Math Geol1989217715739 GotwayCAHartfordAHGeostatistical methods for incorporating auxiliary information in the prediction of spatial variablesJ Agric Biol Environ Stat199611739 JohnsonCBrewardNAnderEAultLG-base: baseline geochemical mapping of Great Britain and Northern IrelandGeochem T Gneiting (9988_CR17) 2007; 69 9988_CR67 B Parmentier (9988_CR51) 2014; 6 9988_CR65 9988_CR62 K Mosegaard (9988_CR46) 1995; 100 9988_CR60 I Clark (9988_CR7) 2010; 110 N Cressie (9988_CR9) 1990; 22 9988_CR28 9988_CR29 9988_CR24 F Alzubaidi (9988_CR2) 2021; 197 T Hengl (9988_CR23) 2007; 33 A Gelman (9988_CR16) 2013 MS Handcock (9988_CR22) 1993; 35 XX Zhu (9988_CR77) 2017; 5 J Padarian (9988_CR50) 2019; 5 A LeNail (9988_CR40) 2019; 4 T Perol (9988_CR52) 2018; 4 HK Olierook (9988_CR49) 2021; 12 9988_CR11 9988_CR55 9988_CR56 T Gneiting (9988_CR19) 2007; 102 9988_CR10 L Poggio (9988_CR54) 2013; 209 Y Chen (9988_CR6) 2017; 14 CA Gotway (9988_CR20) 1996; 1 AMC Wadoux (9988_CR68) 2019; 351 9988_CR4 L Zhang (9988_CR76) 2016; 4 9988_CR15 9988_CR59 9988_CR1 GC Cawley (9988_CR5) 2007; 20 C Johnson (9988_CR25) 2005; 5 AM Youssef (9988_CR75) 2016; 13 9988_CR13 9988_CR14 V Mulder (9988_CR47) 2011; 162 DG Krige (9988_CR35) 1951; 52 I Colomina (9988_CR8) 2014; 92 JJ Van Zyl (9988_CR66) 2001; 48 S Lamichhane (9988_CR38) 2019; 352 P Shamsipour (9988_CR61) 2014; 111 ML Stein (9988_CR64) 1999 9988_CR44 J Ruiz-Arias (9988_CR57) 2011; 151 9988_CR45 9988_CR42 9988_CR43 C Yoe (9988_CR73) 2011 9988_CR48 C Kirkwood (9988_CR33) 2016; 167 AG Journel (9988_CR27) 1989; 21 AG Journel (9988_CR26) 1974; 69 FF Sabins (9988_CR58) 1999; 14 C Kirkwood (9988_CR34) 2021; 379 T Li (9988_CR41) 2017; 44 R Zuo (9988_CR78) 2019; 192 L Grose (9988_CR21) 2019; 119 9988_CR31 9988_CR32 9988_CR30 9988_CR74 9988_CR71 JF Wellmann (9988_CR70) 2018; 453 9988_CR72 AMJ Wadoux (9988_CR69) 2019; 5 JO Berger (9988_CR3) 1985 T Gneiting (9988_CR18) 2014; 1 9988_CR36 Y LeCun (9988_CR39) 2015; 521 R Dimitrakopoulos (9988_CR12) 1998; 12 G Laaha (9988_CR37) 2014; 28 J Pilz (9988_CR53) 2008; 22 N Srivastava (9988_CR63) 2014; 15
References_xml	– reference: Vann J, Bertoli O, Jackson S (2002) An overview of geostatistical simulation for quantifying risk. In: Proceedings of geostatistical association of Australasia symposium” quantifying risk and error, vol 1, Citeseer, 1 – reference: BergerJOStatistical decision theory and bayesian analysis1985BerlinSpringer – reference: British Geological Survey (2020) Geology of Britain Viewer. Accessed through online web interface at http://mapapps.bgs.ac.uk/geologyofbritain/home.html – reference: GroseLAilleresLLaurentGArmitRJessellMInversion of geological knowledge for fold geometryJ Struct Geol2019119114 – reference: Raftery AE, Lewis SM (1996) Implementing MCMC. Markov chain Monte Carlo in practice, pp 115–130 – reference: Ruiz-AriasJPozo-VázquezDSantos-AlamillosFLara-FanegoVTovar-PescadorJA topographic geostatistical approach for mapping monthly mean values of daily global solar radiation: a case study in southern spainAgric For Meteorol20111511218121822 – reference: PadarianJMinasnyBMcBratneyABUsing deep learning for digital soil mappingSoil2019517989 – reference: MosegaardKTarantolaAMonte carlo sampling of solutions to inverse problemsJ Geophys Res Solid Earth1995100B71243112447 – reference: Van ZylJJThe shuttle radar topography mission (SRTM): a breakthrough in remote sensing of topographyActa Astronaut2001485–12559565 – reference: Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp 265–283 – reference: LeNailANn-svg: Publication-ready neural network architecture schematicsJ. Open Source Softw.2019433747 – reference: Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 – reference: Dillon JV, Langmore I, Tran D, Brevdo E, Vasudevan S, Moore D, Patton B, Alemi A, Hoffman M, Saurous RA (2017) Tensorflow distributions. arXiv preprint arXiv:1711.10604 – reference: ZhangLZhangLDuBDeep learning for remote sensing data: a technical tutorial on the state of the artIEEE Trans Geosci Remote Sens2016422240 – reference: ZhuXXTuiaDMouLXiaGSZhangLXuFFraundorferFDeep learning in remote sensing: A comprehensive review and list of resourcesIEEE Trans Geosci Remote Sens201754836 – reference: Menabde M, Froyland G, Stone P, Yeates G (2018) Mining schedule optimisation for conditionally simulated orebodies. In: Advances in applied strategic mine planning. Springer, pp 91–100 – reference: Wu X, Liang L, Shi Y, Fomel S (2019) Faultseg3d: Using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation. Geophysics 84(3):IM35–IM45 – reference: CressieNThe origins of krigingMath Geol1990223239252 – reference: PoggioLGimonaABrewerMJRegional scale mapping of soil properties and their uncertainty with a large number of satellite-derived covariatesGeoderma2013209114 – reference: LaahaGSkøienJBlöschlGSpatial prediction on river networks: comparison of top-kriging with regional regressionHydrol Process2014282315324 – reference: JohnsonCBrewardNAnderEAultLG-base: baseline geochemical mapping of Great Britain and Northern IrelandGeochem Explor Environ Anal200554347357 – reference: WadouxAMJPadarianJMinasnyBMulti-source data integration for soil mapping using deep learningSoil201951107119 – reference: Wilson AG (2020) The case for Bayesian deep learning. arXiv preprint arXiv:2001.10995 – reference: MulderVDe BruinSSchaepmanMEMayrTThe use of remote sensing in soil and terrain mapping-a reviewGeoderma20111621–2119 – reference: Neal RM (1996) Priors for infinite networks. In: Bayesian learning for neural networks. Springer, pp 29–53 – reference: Tarantola A, Valette B (1982) Inverse problems = quest for information. J Geophys 50(1):159–170 – reference: Fox CR, Ülkümen G (2011) Distinguishing two dimensions of uncertainty. Perspectives on thinking, judging, and decision making 14 – reference: JournelAGGeostatistics for conditional simulation of ore bodiesEcon Geol1974695673687 – reference: ClarkIStatistics or geostatistics? Sampling error or nugget effect?J South Afr Inst Min Metal20101106307312 – reference: Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Advances in neural information processing systems, pp 4898–4906 – reference: WellmannJFDe La VargaMMurdieREGessnerKJessellMUncertainty estimation for a geological model of the sandstone greenstone belt, western Australia-insights from integrated geological and geophysical inversion in a Bayesian inference frameworkGeol Soc Spec Publ201845314156 – reference: Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105 – reference: ZuoRXiongYWangJCarranzaEJMDeep learning and its application in geochemical mappingEarth Sci Rev2019192114 – reference: KirkwoodCEconomouTOdbertHPugeaultNA framework for probabilistic weather forecast post-processing across models and lead times using machine learningPhilos Trans R Soc A2021379219420200099 – reference: ChenYZhuLGhamisiPJiaXLiGTangLHyperspectral images classification with gabor filtering and convolutional neural networkIEEE Geosci Remote Sens Lett2017141223552359 – reference: Kampffmeyer M, Salberg AB, Jenssen R (2016) Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 1–9 – reference: Kirkwood C (2020) Deep covariate-learning: optimising information extraction from terrain texture for geostatistical modelling applications. arXiv preprint arXiv:2005.11194 – reference: KrigeDGA statistical approach to some basic mine valuation problems on the witwatersrandJ South Afr Inst Min Metall1951526119139 – reference: Li Y, Sun Y, Reich BJ (2020) Deepkriging: Spatially dependent deep neural networks for spatial prediction. arXiv preprint arXiv:2007.11972 – reference: SabinsFFRemote sensing for mineral explorationOre Geol Rev1999143–4157183 – reference: Dimitrakopoulos R (2018) Stochastic mine planning-methods, examples and value in an uncertain world. In: Advances in applied strategic mine planning. Springer, pp 101–115 – reference: KirkwoodCCaveMBeamishDGrebbySFerreiraAA machine learning approach to geochemical mappingJ Geochem Explor20161674961 – reference: LeCunYBengioYHintonGDeep learningNature20155217553436444 – reference: OlierookHKScalzoRKohnDChandraRFarahbakhshEClarkCReddySMMüllerRDBayesian geological and geophysical data fusion for the construction and uncertainty quantification of 3d geological modelsGeosci Front2021121479493 – reference: Sambridge M, Mosegaard K (2002) Monte Carlo methods in geophysical inverse problems. Rev Geophys 40(3):1–29 – reference: HandcockMSSteinMLA bayesian analysis of krigingTechnometrics1993354403410 – reference: Matheron G (1962) Traité de géostatistique appliquée. Mémoires du Bureau de Recherches Géologiques et Minières, Éditions Technip – reference: SrivastavaNHintonGKrizhevskyASutskeverISalakhutdinovRDropout: a simple way to prevent neural networks from overfittingJ Mach Learn Res201415119291958 – reference: Schaaf A, de la Varga M, Wellmann F, Bond CE (2021) Constraining stochastic 3-D structural geological models with topology information usingÚpproximate Bayesian computation in GemPy 2.1. Geoscientific Model Dev 14(6):3899–3913 – reference: R Core Team (2020) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna – reference: ParmentierBMcGillBWilsonAMRegetzJJetzWGuralnickRPTuanmuMNRobinsonNSchildhauerMAn assessment of methods and remote-sensing derived covariates for regional predictions of 1 km daily maximum air temperatureRemote Sens20146986398670 – reference: PerolTGharbiMDenolleMConvolutional neural network for earthquake detection and locationSci Adv201842e1700578 – reference: YoeCPrinciples of risk analysis: decision making under uncertainty2011CambridgeCRC Press – reference: WadouxAMCUsing deep learning for multivariate mapping of soil with quantified uncertaintyGeoderma20193515970 – reference: GneitingTRafteryAEStrictly proper scoring rules, prediction, and estimationJ Am Stat Assoc2007102477359378 – reference: ColominaIMolinaPUnmanned aerial systems for photogrammetry and remote sensing: a reviewISPRS J Photogramm2014927997 – reference: JournelAGRossiMWhen do we need a trend model in kriging?Math Geol1989217715739 – reference: GneitingTBalabdaouiFRafteryAEProbabilistic forecasts, calibration and sharpnessJ R Stat Soc B2007692243268 – reference: GelmanACarlinJBSternHSDunsonDBVehtariARubinDBBayesian data analysis2013CambridgeCRC Press – reference: ShamsipourPSchetselaarEBellefleurGMarcotteD3D stochastic inversion of potential field data using structural geologic constraintsJ Appl Geophys2014111173182 – reference: HenglTHeuvelinkGBRossiterDGAbout regression-kriging: from equations to case studiesComput Geosci2007331013011315 – reference: YoussefAMPourghasemiHRPourtaghiZSAl-KatheeriMMLandslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi ArabiaLandslides2016135839856 – reference: AlzubaidiFMostaghimiPSwietojanskiPClarkSRArmstrongRTAutomated lithology classification from drill core images using convolutional neural networksJ Pet Sci Eng2021197107933 – reference: Hijmans RJ (2017) raster: Geographic Data Analysis and Modeling. R package version 2.6-7 – reference: Kirkwood C (2016) A dropout-regularised neural network for mapping arsenic enrichment in SW England using MXNet. NERC open research archive – reference: SteinMLInterpolation of spatial data: some theory for kriging1999BerlinSpringer – reference: GneitingTKatzfussMProbabilistic forecastingAnnu Rev Stat Appl20141125151 – reference: Young DM, Parry LE, Lee D, Ray S (2018) Spatial models with covariates improve estimates of peat depth in blanket peatlands. PLoS ONE 13(9):e0202691 – reference: Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: International conference on machine learning, pp 1050–1059 – reference: DimitrakopoulosRConditional simulation algorithms for modelling orebody uncertainty in open pit optimisationInt J Min Reclam Environ1998124173179 – reference: Shwartz-Ziv R, Tishby N (2017) Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810 – reference: Kendall A, Gal Y (2017) What uncertainties do we need in bayesian deep learning for computer vision? In: Advances in neural information processing systems, pp 5574–5584 – reference: de la Varga M, Wellmann JF (2016) Structural geologic modeling as an inference problem: a bayesian perspective. Interpretation 4(3):SM1–SM16 – reference: PilzJSpöckGWhy do we need and how should we implement bayesian kriging methodsStoch Environ Res Risk Assess2008225621632 – reference: LiTShenHYuanQZhangXZhangLEstimating ground-level PM2.5 by fusing satellite and station observations: a geo-intelligent deep learning approachGeophys Res Lett2017442311985 – reference: GotwayCAHartfordAHGeostatistical methods for incorporating auxiliary information in the prediction of spatial variablesJ Agric Biol Environ Stat199611739 – reference: LamichhaneSKumarLWilsonBDigital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: a reviewGeoderma2019352395413 – reference: CawleyGCJanacekGJHaylockMRDorlingSRPredictive uncertainty in environmental modellingNeural Netw2007204537549 – volume: 5 start-page: 79 issue: 1 year: 2019 ident: 9988_CR50 publication-title: Soil doi: 10.5194/soil-5-79-2019 – ident: 9988_CR29 – ident: 9988_CR31 – volume: 162 start-page: 1 issue: 1–2 year: 2011 ident: 9988_CR47 publication-title: Geoderma doi: 10.1016/j.geoderma.2010.12.018 – volume: 111 start-page: 173 year: 2014 ident: 9988_CR61 publication-title: J Appl Geophys doi: 10.1016/j.jappgeo.2014.09.013 – volume: 22 start-page: 239 issue: 3 year: 1990 ident: 9988_CR9 publication-title: Math Geol doi: 10.1007/BF00889887 – volume: 167 start-page: 49 year: 2016 ident: 9988_CR33 publication-title: J Geochem Explor doi: 10.1016/j.gexplo.2016.05.003 – ident: 9988_CR28 doi: 10.1109/CVPRW.2016.90 – volume: 20 start-page: 537 issue: 4 year: 2007 ident: 9988_CR5 publication-title: Neural Netw doi: 10.1016/j.neunet.2007.04.024 – volume: 100 start-page: 12431 issue: B7 year: 1995 ident: 9988_CR46 publication-title: J Geophys Res Solid Earth doi: 10.1029/94JB03097 – volume: 48 start-page: 559 issue: 5–12 year: 2001 ident: 9988_CR66 publication-title: Acta Astronaut doi: 10.1016/S0094-5765(01)00020-0 – ident: 9988_CR60 doi: 10.5194/gmd-14-3899-2021 – volume: 351 start-page: 59 year: 2019 ident: 9988_CR68 publication-title: Geoderma doi: 10.1016/j.geoderma.2019.05.012 – volume: 1 start-page: 17 year: 1996 ident: 9988_CR20 publication-title: J Agric Biol Environ Stat doi: 10.2307/1400558 – volume: 352 start-page: 395 year: 2019 ident: 9988_CR38 publication-title: Geoderma doi: 10.1016/j.geoderma.2019.05.031 – volume: 14 start-page: 157 issue: 3–4 year: 1999 ident: 9988_CR58 publication-title: Ore Geol Rev doi: 10.1016/S0169-1368(99)00007-4 – volume: 13 start-page: 839 issue: 5 year: 2016 ident: 9988_CR75 publication-title: Landslides doi: 10.1007/s10346-015-0614-1 – volume: 35 start-page: 403 issue: 4 year: 1993 ident: 9988_CR22 publication-title: Technometrics doi: 10.1080/00401706.1993.10485354 – ident: 9988_CR10 doi: 10.1190/INT-2015-0188.1 – volume: 151 start-page: 1812 issue: 12 year: 2011 ident: 9988_CR57 publication-title: Agric For Meteorol doi: 10.1016/j.agrformet.2011.07.021 – volume: 14 start-page: 2355 issue: 12 year: 2017 ident: 9988_CR6 publication-title: IEEE Geosci Remote Sens Lett doi: 10.1109/LGRS.2017.2764915 – volume: 5 start-page: 107 issue: 1 year: 2019 ident: 9988_CR69 publication-title: Soil doi: 10.5194/soil-5-107-2019 – volume: 44 start-page: 11 issue: 23 year: 2017 ident: 9988_CR41 publication-title: Geophys Res Lett doi: 10.1002/2017GL075710 – ident: 9988_CR32 – volume-title: Interpolation of spatial data: some theory for kriging year: 1999 ident: 9988_CR64 doi: 10.1007/978-1-4612-1494-6 – volume: 192 start-page: 1 year: 2019 ident: 9988_CR78 publication-title: Earth Sci Rev doi: 10.1016/j.earscirev.2019.02.023 – ident: 9988_CR11 – volume: 12 start-page: 173 issue: 4 year: 1998 ident: 9988_CR12 publication-title: Int J Min Reclam Environ doi: 10.1080/09208118908944041 – volume: 119 start-page: 1 year: 2019 ident: 9988_CR21 publication-title: J Struct Geol doi: 10.1016/j.jsg.2018.11.010 – ident: 9988_CR36 – ident: 9988_CR14 doi: 10.2139/ssrn.3695311 – ident: 9988_CR48 doi: 10.1007/978-1-4612-0745-0_2 – volume: 22 start-page: 621 issue: 5 year: 2008 ident: 9988_CR53 publication-title: Stoch Environ Res Risk Assess doi: 10.1007/s00477-007-0165-7 – ident: 9988_CR15 – volume: 69 start-page: 243 issue: 2 year: 2007 ident: 9988_CR17 publication-title: J R Stat Soc B doi: 10.1111/j.1467-9868.2007.00587.x – ident: 9988_CR42 – volume: 4 start-page: 747 issue: 33 year: 2019 ident: 9988_CR40 publication-title: J. Open Source Softw. doi: 10.21105/joss.00747 – ident: 9988_CR45 doi: 10.1007/978-3-319-69320-0_8 – volume-title: Bayesian data analysis year: 2013 ident: 9988_CR16 doi: 10.1201/b16018 – volume: 5 start-page: 347 issue: 4 year: 2005 ident: 9988_CR25 publication-title: Geochem Explor Environ Anal doi: 10.1144/1467-7873/05-070 – volume: 379 start-page: 20200099 issue: 2194 year: 2021 ident: 9988_CR34 publication-title: Philos Trans R Soc A doi: 10.1098/rsta.2020.0099 – ident: 9988_CR67 – volume-title: Principles of risk analysis: decision making under uncertainty year: 2011 ident: 9988_CR73 – volume: 5 start-page: 8 issue: 4 year: 2017 ident: 9988_CR77 publication-title: IEEE Trans Geosci Remote Sens doi: 10.1109/MGRS.2017.2762307 – volume: 110 start-page: 307 issue: 6 year: 2010 ident: 9988_CR7 publication-title: J South Afr Inst Min Metal – volume: 28 start-page: 315 issue: 2 year: 2014 ident: 9988_CR37 publication-title: Hydrol Process doi: 10.1002/hyp.9578 – ident: 9988_CR71 – volume: 4 start-page: e1700578 issue: 2 year: 2018 ident: 9988_CR52 publication-title: Sci Adv doi: 10.1126/sciadv.1700578 – ident: 9988_CR56 – ident: 9988_CR4 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 9988_CR63 publication-title: J Mach Learn Res – ident: 9988_CR43 – volume: 12 start-page: 479 issue: 1 year: 2021 ident: 9988_CR49 publication-title: Geosci Front doi: 10.1016/j.gsf.2020.04.015 – volume: 52 start-page: 119 issue: 6 year: 1951 ident: 9988_CR35 publication-title: J South Afr Inst Min Metall – volume: 453 start-page: 41 issue: 1 year: 2018 ident: 9988_CR70 publication-title: Geol Soc Spec Publ doi: 10.1144/SP453.12 – volume: 209 start-page: 1 year: 2013 ident: 9988_CR54 publication-title: Geoderma doi: 10.1016/j.geoderma.2013.05.029 – volume: 4 start-page: 22 issue: 2 year: 2016 ident: 9988_CR76 publication-title: IEEE Trans Geosci Remote Sens doi: 10.1109/MGRS.2016.2540798 – volume: 33 start-page: 1301 issue: 10 year: 2007 ident: 9988_CR23 publication-title: Comput Geosci doi: 10.1016/j.cageo.2007.05.001 – ident: 9988_CR24 – ident: 9988_CR74 doi: 10.1371/journal.pone.0202691 – volume-title: Statistical decision theory and bayesian analysis year: 1985 ident: 9988_CR3 doi: 10.1007/978-1-4757-4286-2 – ident: 9988_CR62 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 9988_CR39 publication-title: Nature doi: 10.1038/nature14539 – ident: 9988_CR30 – ident: 9988_CR72 doi: 10.1190/geo2018-0646.1 – ident: 9988_CR1 – volume: 92 start-page: 79 year: 2014 ident: 9988_CR8 publication-title: ISPRS J Photogramm doi: 10.1016/j.isprsjprs.2014.02.013 – volume: 1 start-page: 125 year: 2014 ident: 9988_CR18 publication-title: Annu Rev Stat Appl doi: 10.1146/annurev-statistics-062713-085831 – volume: 21 start-page: 715 issue: 7 year: 1989 ident: 9988_CR27 publication-title: Math Geol doi: 10.1007/BF00893318 – volume: 6 start-page: 8639 issue: 9 year: 2014 ident: 9988_CR51 publication-title: Remote Sens doi: 10.3390/rs6098639 – volume: 69 start-page: 673 issue: 5 year: 1974 ident: 9988_CR26 publication-title: Econ Geol doi: 10.2113/gsecongeo.69.5.673 – ident: 9988_CR55 – ident: 9988_CR59 doi: 10.1029/2000RG000089 – volume: 102 start-page: 359 issue: 477 year: 2007 ident: 9988_CR19 publication-title: J Am Stat Assoc doi: 10.1198/016214506000001437 – volume: 197 start-page: 107933 year: 2021 ident: 9988_CR2 publication-title: J Pet Sci Eng doi: 10.1016/j.petrol.2020.107933 – ident: 9988_CR44 – ident: 9988_CR13 doi: 10.1007/978-3-319-69320-0_9 – ident: 9988_CR65
SSID	ssj0061351
Score	2.4974022
Snippet	Earth scientists increasingly deal with ‘big data’. For spatial interpolation tasks, variants of kriging have long been regarded as the established...
SourceID	proquest crossref springer
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	507
SubjectTerms	Approximation Artificial neural networks Bayesian analysis Bayesian theory Big Data Chemistry and Earth Sciences Computer Science Deep learning Earth and Environmental Science Earth Sciences Elevation Geostatistics Geotechnical Engineering & Applied Earth Sciences Hydrogeology Interpolation Machine learning Mathematical models Neural networks Pattern recognition Physics Probability theory Remote sensing Spatial data Spatial discrimination learning Special Issue Statistical analysis Statistical methods Statistics for Engineering Terrain Uncertainty
Title	Bayesian Deep Learning for Spatial Interpolation in the Presence of Auxiliary Information
URI	https://link.springer.com/article/10.1007/s11004-021-09988-0 https://www.proquest.com/docview/2646969818
Volume	54
WOSCitedRecordID	wos000743447700001&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1874-8953 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0061351 issn: 1874-8961 databaseCode: RSV dateStart: 20080101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA7iA7z4FuuLHLzpwu5mm8exvg9SxBd6WpLsRArSSlvF_nsnadaiqKC3hU3CMpkk32zmm4-QPS0lomxjE5c6mxTKClxSoBInBNNNppwOP3PuLkS7Le_v1WUkhQ3qbPf6SjLs1BOyWxaSJnIMfzFGkAkG6jN43Ekv2HB1fVfvv9xrzvkwS4oikYpnkSrz_Rifj6MJxvxyLRpOm9PF_33nElmI6JK2xu6wTKagu0IWa-UGGhfyCpk7C4K-I3wKKaB2sEoeDvUIPKWSHgM801h49ZEiqqVeuBgdlY5TFHvj_Dna6VKEj_QyMJgs0J6jrZe3zlNH90c08px8wzVye3pyc3SeROGFRDPJhwmwHFwOUuHe53KGiKmwzcwoBZnOQEJlLOK4wmrOEc1UUpgmgHVFs-KpqdKCrZPpbq8LG4RW1hTCCGEYY4VylUS85hwYLnTKpLENktX2L22sSu7FMZ7KST1lb88S7VkGe5Zpg-x_9Hke1-T4tfV2Pa1lXJ-DEmEgV1whWmmQg3oaJ69_Hm3zb823yHzu-RIh1WebTA_7L7BDZu3rsDPo7wa_fQdKLeZj
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3faxQxEB5KreiLrdXitbXmwTdd2N3k8uOxVmtLz6NoLfVpSbITOSh35e4qvf_eSS7roaigbwubhGUyM_lmM98MwEurNaFs54tQBl8I4xWZFJoiKMVtn5tg08-cy4EaDvXVlTnPpLBZl-3eXUkmT70iu1UpaaKm8JdiBF1QoH5P0IkVK-Z__HTZ-V8Ze87FMEsrUWgjq0yV-f0aPx9HK4z5y7VoOm2ON__vO7fgUUaX7HCpDo9hDcfbsNl1bmDZkLfh_vvU0HdBTykF1M-ewJc3doGRUsneIt6wXHj1KyNUy2LjYlJUtkxRnCzz59hozAg-svPEYPLIJoEd3t6Nrkd2umCZ5xQHPoXPx-8ujk6K3HihsFzLeYG8xlCjNuT7Qs0JMQnfr5wxWNkKNbbOE44T3kpJaKbVyvURfRD9VpauLQXfgfXxZIzPgLXeCeWUcpxzYUKrCa-FgE4qW3LtfA-qTv6Nz1XJY3OM62ZVTznKsyF5NkmeTdmDVz_m3Cxrcvx19H63rU22z1lDMFAaaQit9OB1t42r139ebfffhr-ABycXHwbN4HR4tgcP68idSGk_-7A-n97ic9jw3-aj2fQg6fB3HxfpRw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwED6hDRAvGwwQHQP8wBtES2LXPx7HRgExVZWAaTxFtnOeKk1p1XZo_e85OwkdCJAQb5FiW9HZZ38Xf98dwEurNaFs57OQB58J4xW5FJosKMXtkJtg08-cs1M1HuvzczO5oeJPbPf-SrLVNMQsTc3qcF6Hw43wrUgEipJCYYoXdEZB-7aIRPoYr3866_diGevPxZBLK5FpI4tONvP7MX4-mjZ485cr0nTyjHb__5vvw06HOtlRu0wewC1s9mC3r-jAOgffgzvvUqHfNT0laqhfPoSvb-wao9SSnSDOWZeQ9YIR2mWxoDEtYNZSF2ctr45NG0awkk2SsskjmwV2dHU9vZzaxZp1-qfY8BF8Gb39fPw-6woyZJZrucqQlxhK1Ib2xFByQlLCDwtnDBa2QI2184TvhLdSEsqptXJDRB_EsJa5q3PBH8NWM2vwCbDaO6GcUo5zLkyoNeG4ENBJZXOunR9A0c9F5bts5bFoxmW1ybMc7VmRPatkzyofwKsffeZtro6_tj7op7jq_HZZETyURhpCMQN43U_p5vWfR9v_t-Yv4O7kZFSdfhh_fAr3yiipSGygA9haLa7wGdz231bT5eJ5Ws7fAY6V8is
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=Bayesian+Deep+Learning+for+Spatial+Interpolation+in+the+Presence+of+Auxiliary+Information&rft.jtitle=Mathematical+geosciences&rft.au=Kirkwood%2C+Charlie&rft.au=Economou%2C+Theo&rft.au=Pugeault%2C+Nicolas&rft.au=Odbert%2C+Henry&rft.date=2022-04-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=1874-8961&rft.eissn=1874-8953&rft.volume=54&rft.issue=3&rft.spage=507&rft.epage=531&rft_id=info:doi/10.1007%2Fs11004-021-09988-0&rft.externalDocID=10_1007_s11004_021_09988_0
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1874-8961&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1874-8961&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1874-8961&client=summon