The localization of permafrost areas that are susceptible to thermokarst processes is a significant goal, given the current trend of increasing average surface temperatures in Arctic regions. The mapping of thermokarst landscapes is a significant research topic due to its relevance in understanding climate change, monitoring biodiversity, assessing carbon emissions, and informing sustainable land and water management strategies in vulnerable areas. This task can be accomplished through land cover mapping, utilizing supervised classification using machine learning techniques. In this study, we focused on comparing a range of machine learning algorithms available on the Google Earth Engine (GEE) cloud platform. We compared the performance of various models in the classification of land cover types, which relates to the degree of thermokarst process intensity. We identified that the random forest and K-nearest neighbor methods are the most effective in the classification of thermokarst landscapes, based on a visual analysis and accuracy assessment. Furthermore, we conducted the study on Arga Island (the Lena Delta). The Arga Island presents a unique opportunity for evaluating various methods of land cover mapping due to its uniformity in terms of landscape features, the monotony of deposits that make up the island, and the active thermokarst and neotectonic processes occurring there. The results obtained could be utilized in selecting the optimal model for multidisciplinary research involving various classification tasks. Additionally, the findings may be applied in future studies on landscape changes within the Lena Delta region. Furthermore, the comparison of machine learning techniques, which was conducted, may: Enhance the accuracy and efficiency of thermokarst detection; provide insights into the strengths and limitations of various algorithms; and foster the development of standardized approaches in remote sensing, which can be replicated in other studies.
Citation: Andrei Kartoziia. Comparison of machine learning techniques for thermokarst landscape mapping using Google Earth Engine[J]. AIMS Geosciences, 2025, 11(3): 704-724. doi: 10.3934/geosci.2025030
The localization of permafrost areas that are susceptible to thermokarst processes is a significant goal, given the current trend of increasing average surface temperatures in Arctic regions. The mapping of thermokarst landscapes is a significant research topic due to its relevance in understanding climate change, monitoring biodiversity, assessing carbon emissions, and informing sustainable land and water management strategies in vulnerable areas. This task can be accomplished through land cover mapping, utilizing supervised classification using machine learning techniques. In this study, we focused on comparing a range of machine learning algorithms available on the Google Earth Engine (GEE) cloud platform. We compared the performance of various models in the classification of land cover types, which relates to the degree of thermokarst process intensity. We identified that the random forest and K-nearest neighbor methods are the most effective in the classification of thermokarst landscapes, based on a visual analysis and accuracy assessment. Furthermore, we conducted the study on Arga Island (the Lena Delta). The Arga Island presents a unique opportunity for evaluating various methods of land cover mapping due to its uniformity in terms of landscape features, the monotony of deposits that make up the island, and the active thermokarst and neotectonic processes occurring there. The results obtained could be utilized in selecting the optimal model for multidisciplinary research involving various classification tasks. Additionally, the findings may be applied in future studies on landscape changes within the Lena Delta region. Furthermore, the comparison of machine learning techniques, which was conducted, may: Enhance the accuracy and efficiency of thermokarst detection; provide insights into the strengths and limitations of various algorithms; and foster the development of standardized approaches in remote sensing, which can be replicated in other studies.
| [1] | Lee H, Calvin K, Dasgupta D, et al. (2023) Climate Change 2023: Synthesis Report. Contribution of Working Groups Ⅰ, Ⅱ and Ⅲ to the Sixth Assessment Report of the Intergovernmental Panel on Climate Change. |
| [2] |
Wang L, Wang L, Li Y, et al. (2023) A century-long analysis of global warming and earth temperature using a random walk with drift approach. Decis Anal J 7: 100237. https://doi.org/10.1016/j.dajour.2023.100237 doi: 10.1016/j.dajour.2023.100237
|
| [3] |
Serreze M, Barrett A, Stroeve J, et al. (2009) The emergence of surface-based Arctic amplification. Cryosphere 3: 11–19. https://doi.org/10.5194/tc-3-11-2009 doi: 10.5194/tc-3-11-2009
|
| [4] |
Cohen J, Screen JA, Furtado J, et al. (2014) Recent Arctic amplification and extreme mid-latitude weather. Nat Geosci 7: 627–637. https://doi.org/10.1038/ngeo2234 doi: 10.1038/ngeo2234
|
| [5] |
Jansen E, Christensen J, Dokken T, et al. (2020) Past perspectives on the present era of abrupt Arctic climate change. Nat Clim Change 10: 714–721. https://doi.org/10.1038/s41558-020-0860-7 doi: 10.1038/s41558-020-0860-7
|
| [6] |
Obu J, Westermann S, Bartsch A, et al. (2019) Northern Hemisphere permafrost map based on TTOP modelling for 2000–2016 at 1 km2 scale. Earth-Sci Rev 193: 299–316. https://doi.org/10.1016/j.earscirev.2019.04.023 doi: 10.1016/j.earscirev.2019.04.023
|
| [7] | Streletskiy D, Anisimov O, Vasiliev A (2015) Chapter 10 - Permafrost Degradation, In: Shroder JF, Haeberli W, Whiteman C (Eds.), Snow and Ice-Related Hazards, Risks, and Disasters, Boston, Academic Press, 303–344. https://doi.org/10.1016/B978-0-12-394849-6.00010-X |
| [8] | French H (2017) The periglacial environment, Hoboken, NJ, Wiley, Blackwell, 560. |
| [9] | Jorgenson M (2013) 8.20 Thermokarst Terrains, In: Shroder JF (Ed.), Treatise on Geomorphology, San Diego: Academic Press, 313–324. https://doi.org/10.1016/B978-0-12-374739-6.00215-3 |
| [10] |
Jorgenson M, Grosse G (2016) Remote Sensing of Landscape Change in Permafrost Regions. Permafrost Periglacial Processes 27: 324–338. https://doi.org/10.1002/ppp.1914 doi: 10.1002/ppp.1914
|
| [11] |
Philipp M, Dietz A, Buchelt S, et al. (2021) Trends in Satellite Earth Observation for Permafrost Related Analyses—A Review. Remote Sens 13. https://doi.org/10.3390/rs13061217 doi: 10.3390/rs13061217
|
| [12] |
Chen Y, Liu A, Cheng X (2022) Landsat-Based Monitoring of Landscape Dynamics in Arctic Permafrost Region. J Remote Sens, 9765087. https://doi.org/10.34133/2022/9765087 doi: 10.34133/2022/9765087
|
| [13] |
Kizyakov AI, Wetterich S, Günther F, et al. (2023) Landforms and degradation pattern of the Batagay thaw slump, Northeastern Siberia. Geomorphology 420: 108501. https://doi.org/10.1016/j.geomorph.2022.108501 doi: 10.1016/j.geomorph.2022.108501
|
| [14] |
Zhu J, Luo J, Zhang H, et al. (2024) Distribution and changes of thermokarst lakes along the Qinghai-Tibet Railway from 1991 to 2022. Res Cold Arid Reg. https://doi.org/10.1016/j.rcar.2024.10.005 doi: 10.1016/j.rcar.2024.10.005
|
| [15] |
Zhou G, Liu W, Xie C, et al. (2024) Accelerating thermokarst lake changes on the Qinghai–Tibetan Plateau. Sci Rep 14: 2985. https://doi.org/10.1038/s41598-024-52558-7 doi: 10.1038/s41598-024-52558-7
|
| [16] |
Wei T, Wang H, Cui P, et al. (2024) Formation and evolution of thermokarst landslides in the Qinghai-Tibet Plateau, China. Sci Total Environ 954: 176557. https://doi.org/10.1016/j.scitotenv.2024.176557 doi: 10.1016/j.scitotenv.2024.176557
|
| [17] |
Turner B, Lambin E, Reenberg A (2007) The emergence of land change science for global environmental change and sustainability. Proc Natl Acad Sci 104: 20666–20671. https://doi.org/10.1073/pnas.0704119104 doi: 10.1073/pnas.0704119104
|
| [18] | Jansen L, Di Gregorio A (2000) Land Cover Classification System (LCCS): Classification Concepts and User Manual, Rome: Food and Agriculture Organization of the United Nations, 79. |
| [19] |
Nedd R, Light K, Owens M, et al. (2021) A Synthesis of Land Use/Land Cover Studies: Definitions, Classification Systems, Meta-Studies, Challenges and Knowledge Gaps on a Global Landscape. Land 10,994. https://doi.org/10.3390/land10090994 doi: 10.3390/land10090994
|
| [20] |
Zhao Q, Yu L, Li X, et al. (2021) Progress and Trends in the Application of Google Earth and Google Earth Engine. Remote Sens 13, 3778. https://doi.org/10.3390/rs13183778 doi: 10.3390/rs13183778
|
| [21] |
Beamish A, Raynolds M, Epstein H, et al. (2020) Recent trends and remaining challenges for optical remote sensing of Arctic tundra vegetation: A review and outlook. Remote Sens Environ 246: 111872. https://doi.org/10.1016/j.rse.2020.111872 doi: 10.1016/j.rse.2020.111872
|
| [22] |
Walker D, Gould W, Maier H, et al. (2002) The Circumpolar Arctic Vegetation Map: AVHRR-derived base maps, environmental controls, and integrated mapping procedures. Int J Remote Sens 23: 4551–4570. https://doi.org/10.1080/01431160110113854 doi: 10.1080/01431160110113854
|
| [23] |
Brown J, Tollerud H, Barber C, et al. (2020) Lessons learned implementing an operational continuous United States national land change monitoring capability: The Land Change Monitoring, Assessment, and Projection (LCMAP) approach. Remote Sens Environ 238: 111356. https://doi.org/10.1016/j.rse.2019.111356 doi: 10.1016/j.rse.2019.111356
|
| [24] |
Liu C, Xu X, Feng X, et al. (2023) CALC-2020: a new baseline land cover map at 10 m resolution for the circumpolar Arctic. Earth Syst Sci Data 15: 133–153. https://doi.org/10.5194/essd-15-133-2023 doi: 10.5194/essd-15-133-2023
|
| [25] |
Ulrich M, Matthes H, Schirrmeister L, et al. (2017) Differences in behavior and distribution of permafrost-related lakes in Central Yakutia and their response to climatic drivers. Water Resour Res 53: 1167–1188. https://doi.org/10.1002/2016WR019267 doi: 10.1002/2016WR019267
|
| [26] |
Nitze I, Grosse G, Jones B, et al. (2017) Landsat-Based Trend Analysis of Lake Dynamics across Northern Permafrost Regions. Remote Sens 9: 640. https://doi.org/10.3390/rs9070640 doi: 10.3390/rs9070640
|
| [27] |
Li L, Zhang X, Li X, et al. (2022) Thermokarst lake changes over the past 40 years in the Qinghai–Tibet Plateau, China. Front Env Sci 10: 1051086. https://doi.org/10.3389/fenvs.2022.1051086 doi: 10.3389/fenvs.2022.1051086
|
| [28] |
Yu Y, Hui F, Zhou Y, et al. (2024) The first 10 m resolution thermokarst lake and pond dataset for the Lena Basin in the 2020 thawing season. Big Earth Data 8: 302–332. https://doi.org/10.1080/20964471.2023.2280279 doi: 10.1080/20964471.2023.2280279
|
| [29] |
Qin Y, Zhang C, Lu P (2023) A fully automatic framework for sub-pixel mapping of thermokarst lakes using Sentinel-2 images. Sci Remote Sen 8: 100111. https://doi.org/10.1016/j.srs.2023.100111 doi: 10.1016/j.srs.2023.100111
|
| [30] |
Liu A, Chen Y, Cheng X (2023) Monitoring Thermokarst Lake Drainage Dynamics in Northeast Siberian Coastal Tundra. Remote Sens 15, 4396. https://doi.org/10.3390/rs15184396 doi: 10.3390/rs15184396
|
| [31] |
Beck I, Ludwig R, Bernier M, et al. (2015) Assessing Permafrost Degradation and Land Cover Changes (1986–2009) using Remote Sensing Data over Umiujaq, Sub-Arctic Québec. Permafrost Periglac 26: 129–141. https://doi.org/10.1002/ppp.1839 doi: 10.1002/ppp.1839
|
| [32] |
Boike J, Grau T, Heim B, et al. (2016) Satellite-derived changes in the permafrost landscape of central Yakutia, 2000–2011: Wetting, drying, and fires. Global Planet Change 139: 116–127. https://doi.org/10.1016/j.gloplacha.2016.01.001 doi: 10.1016/j.gloplacha.2016.01.001
|
| [33] |
Lee Y, Kim S, Jung Y, et al. (2024) Monitoring Long-Term Land Cover Change in Central Yakutia Using Sparse Time Series Landsat Data. Remote Sens 16: 1868. https://doi.org/10.3390/rs16111868 doi: 10.3390/rs16111868
|
| [34] |
Nitze I, Grosse G, Jones B, et al. (2018) Remote sensing quantifies widespread abundance of permafrost region disturbances across the Arctic and Subarctic. Nat Commun 9: 5423. https://doi.org/10.1038/s41467-018-07663-3 doi: 10.1038/s41467-018-07663-3
|
| [35] |
Dubovik O, Schuster G, Xu F, et al. (2021) Grand Challenges in Satellite Remote Sensing. Front Remote Sens 2. https://doi.org/10.3389/frsen.2021.619818 doi: 10.3389/frsen.2021.619818
|
| [36] |
Gorelick N, Hancher M, Dixon M, et al. (2017) Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens Environ 202: 18–27. https://doi.org/10.1016/j.rse.2017.06.031 doi: 10.1016/j.rse.2017.06.031
|
| [37] |
Amani M, Brisco B, Afshar M, et al. (2019) A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing. Big Earth Data 3: 378–394. https://doi.org/10.1080/20964471.2019.1690404 doi: 10.1080/20964471.2019.1690404
|
| [38] | Jensen J (2016) Introductory Digital Image Processing: A Remote Sensing Perspective, Pearson Education, Incorporated, 623. |
| [39] |
Talukdar S, Singha P, Mahato S, et al. (2020) Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review. Remote Sens 12, 1135. https://doi.org/10.3390/rs12071135 doi: 10.3390/rs12071135
|
| [40] |
Zhao Z, Islam F, Waseem LA, et al. (2024) Comparison of Three Machine Learning Algorithms Using Google Earth Engine for Land Use Land Cover Classification. Rangeland Ecol Manag 92: 129–137. https://doi.org/10.1016/j.rama.2023.10.007 doi: 10.1016/j.rama.2023.10.007
|
| [41] |
Rawat K, Kumar S, Garg N (2024) Statistical comparison of simple and machine learning based land use and land cover classification algorithms: A case study. J Water Manag Modell 32. https://doi.org/10.14796/JWMM.H524 doi: 10.14796/JWMM.H524
|
| [42] |
Nigar A, Li Y, Jat Baloch M, et al. (2024) Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications. Front Environ Sci 12: 1378443. https://doi.org/10.3389/fenvs.2024.1378443 doi: 10.3389/fenvs.2024.1378443
|
| [43] |
Schwamborn G, Rachold V, Grigoriev M (2002) Late Quaternary sedimentation history of the Lena Delta. Quatern Int 89: 119–134. https://doi.org/10.1016/S1040-6182(01)00084-2 doi: 10.1016/S1040-6182(01)00084-2
|
| [44] |
Schwamborn G, Schirrmeister L, Mohammadi A, et al. (2023) Fluvial and permafrost history of the lower Lena River, north-eastern Siberia, over late Quaternary time. Sedimentology 70: 235–258. https://doi.org/10.1111/sed.13037 doi: 10.1111/sed.13037
|
| [45] |
Zaplavnova A, Deev E, Potapov V (2024) Structure of the Upper Part of the Earth's Crust in the Area of the Lena River Delta: The First Magnetotelluric Data. Dokl Earth Sci 514: 249–254. https://doi.org/10.1134/S1028334X23602833 doi: 10.1134/S1028334X23602833
|
| [46] | Grigoriev M (1993) Criomorphogenesis in the Lena Delta, Yakutsk, Russia: Permafrost Institute Press, 176. |
| [47] |
Boike J, Nitzbon J, Anders K, et al. (2019) A 16-year record (2002–2017) of permafrost, active-layer, and meteorological conditions at the Samoylov Island Arctic permafrost research site, Lena River delta, northern Siberia: an opportunity to validate remote-sensing data and land surface, snow, and permafrost models. Earth Syst Sci Data 11: 261–299. https://doi.org/10.5194/essd-11-261-2019 doi: 10.5194/essd-11-261-2019
|
| [48] |
Chalov S, Prokopeva K, Magritsky D, et al. (2023) Climate change impacts on streamflow, sediment load and carbon fluxes in the Lena River delta. Ecol Indic 157: 111252. https://doi.org/10.1016/j.ecolind.2023.111252 doi: 10.1016/j.ecolind.2023.111252
|
| [49] |
Yurkevich N, Kartoziia A, Tsibizova E (2022) Permafrost degradation impact on water bodies in the Siberian tundra (Samoylov and Kurungnakh Islands, Lena Delta) using GIS analysis of remote sensing data and a geochemical approach. Water 14: 2322. https://doi.org/10.3390/w14152322 doi: 10.3390/w14152322
|
| [50] | Schwamborn G, Andreev A, Rachold V, et al. (2002) Evolution of Lake Nikolay, Arga Island, Western Lena River Delta, during Late Pleistocene and Holocene Time. Polarforschung 70: 69–82. https://doi.org/10013/epic.29859.d001 |
| [51] |
Schirrmeister L, Grosse G, Schwamborn G, et al. (2003) Late Quaternary History of the Accumulation Plain North of the Chekanovsky Ridge (Lena Delta, Russia): A Multidisciplinary Approach. Polar Geogr 27: 277–319. https://doi.org/10.1080/789610225 doi: 10.1080/789610225
|
| [52] | Feliks Are, Reimnitz E (2000) An Overview of the Lena River Delta Setting: Geology, Tectonics, Geomorphology, and Hydrology. J Coastal Res 16: 1083–1093. |
| [53] |
Imaeva L, Gusev G, Imaev V (2019) Dynamics of the relief and seismotectonic activity of the modern structures in the delta of the river Lena. Geotectonics 5: 62–77. https://doi.org/10.31857/S0016-853X2019562-77 doi: 10.31857/S0016-853X2019562-77
|
| [54] |
Dergach P, Eponeshnikova L, Ponasenko S, et al. (2022) Building a tomographic velocity model for Samoylov Island area (Lena Delta) from local seismological data for the period of 2019–2021. Geodin tektonofiz 13: 0627. https://doi.org/10.5800/GT-2022-13-2s-0627 doi: 10.5800/GT-2022-13-2s-0627
|
| [55] |
Zolnikov I, Glushkova N, Kartoziya A, et al. (2023) The geomorphological zonation of the Lena river delta east part by using GIS-analysis. Geology and Mineral Resources of Siberia 1: 3–11. https://doi.org/10.20403/2078-0575-2023-1-3-11 doi: 10.20403/2078-0575-2023-1-3-11
|
| [56] | Harmonized Sentinel-2 MSI: MultiSpectral Instrument, Level-2A Available from: https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_SR_HARMONIZED (accessed on 13 December 2024). |
| [57] | Rouse J, Haas R, Deering D, et al. (1973) Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. Texas: Remote Sens. Centre, TEXAS A & M Univ., 8. |
| [58] |
Gao B (1996) NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens Environ 58: 257–266. https://doi.org/10.1016/S0034-4257(96)00067-3 doi: 10.1016/S0034-4257(96)00067-3
|
| [59] |
Huete A, Didan K, Miura T, et al. (2002) Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ 83: 195–213. https://doi.org/10.1016/S0034-4257(02)00096-2 doi: 10.1016/S0034-4257(02)00096-2
|
| [60] | Kauth R (1976) ThomasG. S., 1976: The tasseled cap – A graphic description of the spectral-temporal development of agricultural crops as seen by Landsat, Proceedings on the Symposium on Machine Processing of Remotely Sensed Data, New York: The Institute of Electrical and Electronics Engineers, Inc., 41–51. |
| [61] |
Shi T, Xu H (2019) Derivation of Tasseled Cap Transformation Coefficients for Sentinel-2 MSI At-Sensor Reflectance Data. IEEE J Sel Top Appl Earth Observ Remote Sens 12: 4038–4048. https://doi.org/10.1109/JSTARS.2019.2938388 doi: 10.1109/JSTARS.2019.2938388
|
| [62] | Crist EP, Cicone RC (1984) Application of the tasseled cap concept to simulated thematic mapper data. Photogramm Eng Remote Sens 50: 343–352. |
| [63] |
Kartoziia A (2024) Using Google Earth Engine to Assess the Current State of Thermokarst Terrain on Arga Island (the Lena Delta). Earth 5: 228-243. https://doi.org/10.3390/earth5020012 doi: 10.3390/earth5020012
|
| [64] | Breiman L, Friedman J, Olshen R, et al. (2017) Classification and regression trees, New York: Routledge, 368. https://doi.org/10.1201/9781315139470 |
| [65] |
Breiman L (1998) Arcing classifier (with discussion and a rejoinder by the author). Ann Statist 26: 1011–1027. https://doi.org/10.1214/aos/1024691079 doi: 10.1214/aos/1024691079
|
| [66] |
Breiman L (2001) Random Forests. Mach Learn 45: 5–32. https://doi.org/10.1023/A:1010933404324 doi: 10.1023/A:1010933404324
|
| [67] |
Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inform Theory 13: 21–27. https://doi.org/10.1109/TIT.1967.1053964 doi: 10.1109/TIT.1967.1053964
|
| [68] |
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20: 273–297. https://doi.org/10.1007/BF00994018 doi: 10.1007/BF00994018
|
| [69] |
Stehman S (1997) Selecting and interpreting measures of thematic classification accuracy. Remote Sens Environ 62: 77–89. https://doi.org/10.1016/S0034-4257(97)00083-7 doi: 10.1016/S0034-4257(97)00083-7
|
| [70] | Congalton R, Green K (2008) Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Second Edition, Boca Raton: CRC Press, 200. https://doi.org/10.1201/9781420055139 |
| [71] | Sasaki Y (2007) The truth of the F-measure. Teach Tutor Mater 1: 1–5. |
| [72] |
Cohen J (1960) A Coefficient of Agreement for Nominal Scales. Educ Psychol Meas 20: 37–46. https://doi.org/10.1177/001316446002000104 doi: 10.1177/001316446002000104
|
| [73] | Koukoulas S, Blackburn G (2001) Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments. Photogramm Eng Remote Sens 67: 499–510. |
| [74] | Labatut V, Cherifi H (2011) Evaluation of Performance Measures for Classifiers Comparison. arXiv abs/1112.4133. |
| [75] | Albertz J (2009) Einführung in die Fernerkundung: Grundlagen der Interpretation von Luft- und Satellitenbildern, Darmstadt: Wiss. Buchges, 254. |
| [76] | Pirotti F, Sunar F, Piragnolo M (2016) Benchmark of machine learning methods for classification of a Sentinel-2 image. Int. Arch. Photogramm. Remote Sens Spatial Inf Sci XLI-B7: 335–340. https://doi.org/10.5194/isprs-archives-XLI-B7-335-2016 |
| [77] |
Zhou L, Luo T, Du M, et al. (2021) Machine Learning Comparison and Parameter Setting Methods for the Detection of Dump Sites for Construction and Demolition Waste Using the Google Earth Engine. Remote Sens 13. https://doi.org/10.3390/rs13040787 doi: 10.3390/rs13040787
|
| [78] |
Merchant M, Brisco B, Mahdianpari M, et al. (2023) Leveraging Google Earth Engine cloud computing for large-scale arctic wetland mapping. Int J Appl Earth Obs 125: 103589. https://doi.org/10.1016/j.jag.2023.103589 doi: 10.1016/j.jag.2023.103589
|
| [79] |
Nitze I, Grosse G (2016) Detection of landscape dynamics in the Arctic Lena Delta with temporally dense Landsat time-series stacks. Remote Sens Environ 181: 27–41. https://doi.org/10.1016/j.rse.2016.03.038 doi: 10.1016/j.rse.2016.03.038
|
Figures(6) / Tables(5)
Andrei Kartoziia. Comparison of machine learning techniques for thermokarst landscape mapping using Google Earth Engine[J]. AIMS Geosciences, 2025, 11(3): 704-724. doi: 10.3934/geosci.2025030
DownLoad: