{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:18:32Z","timestamp":1770329912241,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014051","name":"Cold Regions Research and Engineering Laboratory","doi-asserted-by":"publisher","award":["Contract No.W913E522C0001"],"award-info":[{"award-number":["Contract No.W913E522C0001"]}],"id":[{"id":"10.13039\/100014051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014051","name":"Cold Regions Research and Engineering Laboratory","doi-asserted-by":"publisher","award":["Contract No.W913E522C0001"],"award-info":[{"award-number":["Contract No.W913E522C0001"]}],"id":[{"id":"10.13039\/100014051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014051","name":"Cold Regions Research and Engineering Laboratory","doi-asserted-by":"publisher","award":["Contract No.W913E522C0001"],"award-info":[{"award-number":["Contract No.W913E522C0001"]}],"id":[{"id":"10.13039\/100014051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014051","name":"Cold Regions Research and Engineering Laboratory","doi-asserted-by":"publisher","award":["Contract No.W913E522C0001"],"award-info":[{"award-number":["Contract No.W913E522C0001"]}],"id":[{"id":"10.13039\/100014051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Climate change in Arctic regions poses a threat to permafrost stability, potentially leading to issues such as infrastructure damage, altered ecosystems, and increased greenhouse gas emissions. The challenge of monitoring permafrost temperatures and identifying critical environmental factors is accentuated by the scarcity of subsurface thermal data in remote Arctic locales. To alleviate this lack of soil thermal data we set out to combine in situ observed soil temperatures with MERRA-2 reanalysis data and Machine Learning (ML) to develop local and season-specific subsurface soil temperature predictions in Alaska. First, reanalysis features are selected based on surface energy budget physics. Coupled with Julian calendar dates, reanalysis features are preprocessed and then fed to the ML prediction model. We conducted a series of computational experiments and tested the results against performance benchmarks to determine the optimal prediction models, length of look-back period of model inputs, and the training set size. Six conventional ML models (e.g., GBDT, RF, SVR) and five statistical baselines (e.g. ARIMA) using in situ time series of soil temperature data ranging from 0 - 1 m depth are considered for the prediction task. The models are trained using in situ soil temperatures at depths between 0 and 1 m, spanning 16+ years, from field sites at Deadhorse and Toolik Lake, Alaska. All prediction performances are assessed using root mean squared error (RMSE) and mean absolute error (MAE). Results show that locally trained ML models can estimate shallow soil temperatures with an average error of <jats:inline-formula><jats:alternatives><jats:tex-math>$$RMSE=1.308^{\\circ }$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mi>R<\/mml:mi>\n                    <mml:mi>M<\/mml:mi>\n                    <mml:mi>S<\/mml:mi>\n                    <mml:mi>E<\/mml:mi>\n                    <mml:mo>=<\/mml:mo>\n                    <mml:mn>1<\/mml:mn>\n                    <mml:mo>.<\/mml:mo>\n                    <mml:msup>\n                      <mml:mn>308<\/mml:mn>\n                      <mml:mo>\u2218<\/mml:mo>\n                    <\/mml:msup>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>C.<\/jats:p>","DOI":"10.1007\/s12145-024-01486-1","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T04:02:03Z","timestamp":1729051323000},"page":"6055-6073","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Artificial intelligence for predicting arctic permafrost and active layer temperatures along the Alaskan North Slope"],"prefix":"10.1007","volume":"17","author":[{"given":"Robert","family":"Chance","sequence":"first","affiliation":[]},{"given":"Aymane","family":"Ahajjam","sequence":"additional","affiliation":[]},{"given":"Jaakko","family":"Putkonen","sequence":"additional","affiliation":[]},{"given":"Timothy","family":"Pasch","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"1486_CR1","unstructured":"Ahajjam A, Chance R, Putkonen J, Pasch T (2024) Moredataset\/soiltemperatureprediction: initial release (0.1.0)"},{"issue":"3","key":"1486_CR2","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/S0304-3800(02)00016-9","volume":"153","author":"O Anisimov","year":"2002","unstructured":"Anisimov O, Shiklomanov N, Nelson F (2002) Variability of seasonal thaw depth in permafrost regions: a stochastic modeling approach. Ecol Model 153(3):217\u2013227","journal-title":"Ecol Model"},{"key":"1486_CR3","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s13280-011-0213-x","volume":"40","author":"TV Callaghan","year":"2011","unstructured":"Callaghan TV, Johansson M, Brown RD, Groisman PY, Labba N, Radionov V et al (2011) Multiple effects of changes in arctic snow cover. Ambio 40:32\u201345","journal-title":"Ambio"},{"key":"1486_CR4","doi-asserted-by":"publisher","unstructured":"Chen TC, Penny SG, Whitaker JS, Frolov S, Pincus R, Tulich S (2022) Correcting systematic and state-dependent errors in the noaa fv3-gfs using neural networks. J Adv Model Earth Syst. https:\/\/doi.org\/10.1002\/essoar.10511972.1","DOI":"10.1002\/essoar.10511972.1"},{"key":"1486_CR5","first-page":"C21C","volume":"2017","author":"MV Debolskiy","year":"2017","unstructured":"Debolskiy MV, Nicolsky D, Romanovsky VE, Muskett RR, Panda SK (2017) Modeling soil temperature change in Seward Peninsula, Alaska. Agu fall Meet abstr 2017:C21C-1126","journal-title":"Agu fall Meet abstr"},{"issue":"8","key":"1486_CR6","doi-asserted-by":"publisher","first-page":"3555","DOI":"10.5194\/tc-15-3555-2021","volume":"15","author":"TA Douglas","year":"2021","unstructured":"Douglas TA, Hiemstra CA, Anderson JE, Barbato RA, Bjella KL, Deeb EJ et al (2021) Recent degradation of interior alaska permafrost mapped with ground surveys, geophysics, deep drilling, and repeat airborne lidar. Cryosphere 15(8):3555\u20133575. https:\/\/doi.org\/10.5194\/tc-15-3555-2021","journal-title":"Cryosphere"},{"issue":"10","key":"1486_CR7","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/11\/10\/105003","volume":"11","author":"ES Euskirchen","year":"2016","unstructured":"Euskirchen ES, Bennett A, Breen AL, Genet H, Lindgren MA, Kurkowski TA, Rupp TS (2016) Consequences of changes in vegetation and snow cover for climate feedbacks in alaska and northwest canada. Environ Res Lett 11(10):105003","journal-title":"Environ Res Lett"},{"key":"1486_CR8","unstructured":"Global Modeling and Assimilation Office (2015a) MERRA-2 statD2dslvNx: 2d,Daily, Aggregated Statistics, Single-Level, Assimilation, Single-Level Diagnostics V5.12.4. Goddard Earth Sciences Data and Information Services"},{"key":"1486_CR9","unstructured":"Global Modeling and Assimilation Office (2015b) MERRA-2 tavg12dradNx: 2d, 1-Hourly, Time-Averaged, Single-Level, Assimilation, Radiation Diagnostics V5.12.4. Goddard Earth Sciences Data and Information Services"},{"key":"1486_CR10","unstructured":"Global Modeling and Assimilation Office (2015c) MERRA- tavg32dglcNx: 2d,3-Hourly,Time-Averaged,Single-Level,Assimilation,Land Ice Surface Diagnostics V5.12.4. Goddard Earth Sciences Data and Information Services"},{"key":"1486_CR11","unstructured":"Global Modeling and Assimilation Office (2015d) Modern-Era Retrospective Analysis for Research and Applications, Version 2. https:\/\/gmao.gsfc.nasa.gov\/reanalysis\/MERRA-2. NASA. (Accessed: 10 January 2024 )"},{"issue":"16","key":"1486_CR12","doi-asserted-by":"publisher","first-page":"4261","DOI":"10.5194\/bg-17-4261-2020","volume":"17","author":"I Gr\u00fcnberg","year":"2020","unstructured":"Gr\u00fcnberg I, Wilcox EJ, Zwieback S, Marsh P, Boike J (2020) Linking tundra vegetation, snow, soil temperature, and permafrost. Biogeosciences 17(16):4261\u20134279","journal-title":"Biogeosciences"},{"key":"1486_CR13","doi-asserted-by":"crossref","unstructured":"James G, Witten D, Hastie T, Tibshirani R (2022) An introduction to statistical learning: With applications in r. Springer","DOI":"10.1007\/978-1-0716-1418-1"},{"issue":"2","key":"1486_CR14","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/0165-232x(91)90002-x","volume":"19","author":"DL Kane","year":"1991","unstructured":"Kane DL, Hinzman LD, Zarling JP (1991) Thermal response of the active layer to climatic warming in a permafrost environment. Cold Reg Sci Technol 19(2):111\u2013122. https:\/\/doi.org\/10.1016\/0165-232x(91)90002-x","journal-title":"Cold Reg Sci Technol"},{"issue":"4","key":"1486_CR15","doi-asserted-by":"publisher","first-page":"264","DOI":"10.3390\/e20040264","volume":"20","author":"Z Karevan","year":"2018","unstructured":"Karevan Z, Suykens JA (2018) Transductive feature selection using clustering-based sample entropy for temperature prediction in weather forecasting. Entropy 20(4):264","journal-title":"Entropy"},{"key":"1486_CR16","unstructured":"Lachenbruch AH (1962) Periodic heat flow in a stratified medium with application to permafrost problems. United States Geological Survey"},{"issue":"2","key":"1486_CR17","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1002\/ppp.445","volume":"14","author":"F Ling","year":"2003","unstructured":"Ling F, Zhang T (2003) Impact of the timing and duration of seasonal snow cover on the active layer and permafrost in the alaskan arctic. Permafr Periglac Process 14(2):141\u2013150","journal-title":"Permafr Periglac Process"},{"issue":"1","key":"1486_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/s0165-232x(03)00057-0","volume":"38","author":"F Ling","year":"2004","unstructured":"Ling F, Zhang T (2004) A numerical model for surface energy balance and thermal regime of the active layer and permafrost containing unfrozen water. Cold Reg Sci Technol 38(1):1\u201315. https:\/\/doi.org\/10.1016\/s0165-232x(03)00057-0","journal-title":"Cold Reg Sci Technol"},{"issue":"1","key":"1486_CR19","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/7\/1\/011005","volume":"7","author":"MM Loranty","year":"2012","unstructured":"Loranty MM, Goetz SJ (2012) Shrub expansion and climate feedbacks in arctic tundra. Environ Res Lett 7(1):011005","journal-title":"Environ Res Lett"},{"key":"1486_CR20","unstructured":"Muller SW (1947) Permafrost: Or, Permanently Frozen Ground and Related Engineering Problems. J.W, Edwards"},{"key":"1486_CR21","unstructured":"Mu\u00f1oz Sabater J (2024)"},{"issue":"1","key":"1486_CR22","doi-asserted-by":"publisher","first-page":"19","DOI":"10.2307\/1550211","volume":"4","author":"Y Nakano","year":"1972","unstructured":"Nakano Y, Brown J (1972) Mathematical modeling and validation of the thermal regimes in tundra soils, barrow, alaska. Arct Alp Res 4(1):19. https:\/\/doi.org\/10.2307\/1550211","journal-title":"Arct Alp Res"},{"key":"1486_CR23","unstructured":"Osterkamp TE (2009) Daily air And Active Layer Temperatures From Permafrost Observatories in Alaska. National Center for Atmospheric Research, ARCSS Data Archive, Boulder, CO, USA, pp 1986\u20132001"},{"issue":"7","key":"1486_CR24","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1029\/90wr00139","volume":"26","author":"SI Outcalt","year":"1990","unstructured":"Outcalt SI (1990) The zero-curtain effect: Heat and mass transfer across and isothermal region in freezing soil. Water Resour Res 26(7):1509\u20131516. https:\/\/doi.org\/10.1029\/90wr00139","journal-title":"Water Resour Res"},{"key":"1486_CR25","doi-asserted-by":"crossref","unstructured":"Pincus SM, Goldberger AL (1994) Physiological time-series analysis: what does regularityquantify? Am J Physiol Heart Circ Physiol 266(4):H1643\u2013H1656","DOI":"10.1152\/ajpheart.1994.266.4.H1643"},{"key":"1486_CR26","doi-asserted-by":"crossref","unstructured":"Pomeroy JW, Bewley D, Essery RL, Hedstrom N, Link T, Granger RJ, Janowicz J (2006) Shrub tundra snowmelt. Hydrol Process Int J 20(4):923\u2013941","DOI":"10.1002\/hyp.6124"},{"key":"1486_CR27","doi-asserted-by":"publisher","unstructured":"Pomeroy JW, Marsh P, Gray DM (1997) Application of a distributed blowing snow model to the arctic. Hydrol Process 11(11). https:\/\/doi.org\/10.1002\/(SICI)1099-1085(199709)11:11<1451::AID-HYP449>3.0.CO;2-Q","DOI":"10.1002\/(SICI)1099-1085(199709)11:11<1451::AID-HYP449>3.0.CO;2-Q"},{"key":"1486_CR28","doi-asserted-by":"publisher","unstructured":"Putkonen J (1998) Soil thermal properties and heat transfer processes near ny-alesund, northwestern spitsbergen, svalbard. Polar Res 17(2):165\u2013179. https:\/\/doi.org\/10.1111\/j.1751-8369.1998.tb00270.x","DOI":"10.1111\/j.1751-8369.1998.tb00270.x"},{"issue":"2","key":"1486_CR29","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1002\/ppp.449","volume":"14","author":"TS Sazonova","year":"2003","unstructured":"Sazonova TS, Romanovsky VE (2003) A model for regional-scale estimation of temporal and spatial variability of active layer thickness and mean annual ground temperatures. Permafr Periglac Process 14(2):125\u2013139. https:\/\/doi.org\/10.1002\/ppp.449","journal-title":"Permafr Periglac Process"},{"issue":"4","key":"1486_CR30","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1002\/(SICI)1099-1530(199610)7:4<301::AID-PPP231>3.0.CO;2-R","volume":"7","author":"M Smith","year":"1996","unstructured":"Smith M, Riseborough D (1996) Permafrost monitoring and detection of climate change. Permafr Periglac Process 7(4):301\u2013309","journal-title":"Permafr Periglac Process"},{"key":"1486_CR31","unstructured":"Staff, N (2022) Soil climate research station data, [toolik, alaska]. United States Department of Agriculture"},{"issue":"2","key":"1486_CR32","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1002\/ppp.452","volume":"14","author":"D Walker","year":"2003","unstructured":"Walker D, Jia G, Epstein H, Raynolds M, Chapin Iii F, Copass C et al (2003) Vegetation-soil-thaw-depth relationships along a low-arctic bioclimate gradient, alaska: Synthesis of information from the atlas studies. Permafr Periglac Process 14(2):103\u2013123","journal-title":"Permafr Periglac Process"},{"key":"1486_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.geoderma.2020.114583","volume":"377","author":"S Yang","year":"2020","unstructured":"Yang S, Li R, Wu T, Hu G, Xiao Y, Du Y et al (2020) Evaluation of reanalysis soil temperature and soil moisture products in permafrost regions on the qinghai-tibetan plateau. Geoderma 377:114583. https:\/\/doi.org\/10.1016\/j.geoderma.2020.114583","journal-title":"Geoderma"},{"issue":"4","key":"1486_CR34","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.3390\/earth3040060","volume":"3","author":"C Zhao","year":"2022","unstructured":"Zhao C, Gong C, Duan H, Yan P, Liu Y, Zhou G (2022) Evaluation of three reanalysis soil temperature datasets with observation data over china. Earth 3(4):1042\u20131058. https:\/\/doi.org\/10.3390\/earth3040060","journal-title":"Earth"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01486-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-024-01486-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01486-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:24:50Z","timestamp":1732091090000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-024-01486-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1486"],"URL":"https:\/\/doi.org\/10.1007\/s12145-024-01486-1","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"value":"1865-0473","type":"print"},{"value":"1865-0481","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"assertion":[{"value":"11 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing of interest"}},{"value":"Code and data for manuscript can be found at Ahajjam et\u00a0al. ()","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Open Research Section"}}]}}