Abstract
The Nelson-Churchill River Basin (NCRB) is one of the largest river basins in North America, covering four provinces and four states in Canada and the United States, respectively. This study's primary objective is to evaluate the spatial variability and derive the optimal number of spatially contiguous regions of the NCRB using important soil health indicators (SHI) such as organic carbon, bulk density, cation exchange capacity, elevation, pH, and percentage of clay, gravel, silt, and sand extracted from the Unified North American Soil Map database. Several soil parameters are input into various watershed activities such as precision farming and water balance determination through hydrologic modeling. Therefore, information about their heterogeneities (homogeneities) is important from a best management practices (BMPs) perspective. This study applied a self-organizing map (SOM), an unsupervised artificial neural network technology that can visualize high-dimension datasets in a 2-D format and preserve the topology of multivariate datasets. The derived result (SOM nodes) from the SOM procedure was then clustered using the hierarchical clustering method (HCM). Using SOM and HCM, all the variables mentioned above were partitioned into a possible number of clusters that did not follow the geographical boundaries of seven sub-basins inside the NCRB. In addition, change point methods based on Markov Chain Monte Carlo and nonparametric E-Divisive change point methods were used to partition the within-cluster sum of squares into an optimal number of clusters. The study reveals two partitions (two and five regions) as optimal, meaning there would be no further striking changes to the number of clusters after these partitions. Therefore, both the two-region and five-region partitions would help in the decision process, especially when there are project initiatives or interventions at a scale larger than a watershed or sub-basin. A proper understanding of the spatial heterogeneity and the optimal number of clusters in a large regional river basin such as the NCRB could aid BMPs, climate change adaptation efforts, precision agriculture, and water resources management through hydrologic modeling.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The code that supports the findings of this study is available from the author upon reasonable request.
References
Azhar M, Huang JZ, Masud MA, Li MJ, Cui L (2020) A hierarchical Gamma Mixture Model-based method for estimating the number of clusters in complex data. Appl Soft Comput 87:105891. https://doi.org/10.1016/j.asoc.2019.105891
Bajracharya A, Awoye H, Stadnyk T, Asadzadeh M (2020) Time variant sensitivity analysis of hydrological model parameters in a cold region using flow signatures. Water 12(4):961. https://doi.org/10.3390/w12040961
Barbier N, Couteron P, Lejoly J, Deblauwe V, Lejeune O (2006) Self-organized vegetation patterning as a fingerprint of climate and human impact on semi-arid ecosystems. J Ecol 94:537–547. https://doi.org/10.1111/j.1365-2745.2006.01126.x
Barry D, Hartigan JA (1993) A Bayesian analysis for change point problems. J Am Stat Assoc 35(3):309–319
Boluwade A (2019) Regionalization and partitioning of soil health indicators for Nigeria using spatially contiguous clustering for economic and social-cultural developments. ISPRS Int J Geo Inf 8(10):458. https://doi.org/10.3390/ijgi8100458
Boluwade A (2020a) Joint simulation of spatially correlated soil health indicators, using independent component analysis and minimum/maximum autocorrelation factors. ISPRS Int J Geo Inf 9(1):30. https://doi.org/10.3390/ijgi9010030
Boluwade A (2020b) Spatial-temporal assessment of satellite-based rainfall estimates in different precipitation regimes in water-scarce and data-sparse regions. Atmosphere 11(9):901. https://doi.org/10.3390/atmos11090901
Boluwade A, Rasmussen P (2014) Frequency of floods in a changing climate: a case study from the Red River in Manitoba, Canada June 2015. Proc Int Assoc Hydrol Sci 371:83–88. https://doi.org/10.5194/piahs-371-83-201510.5194/piahs-371-83-2015
Boluwade A, Zhao K-Y, Stadnyk TA, Rasmussen P (2018) Towards validation of the Canadian Precipitation Analysis (CaPA) for hydrologic modeling applications in the Canadian Prairies. J. Hydrol 556(2018):1244–1255. https://doi.org/10.1016/j.jhydrol.2017.05.059
Brimelow J, Szeto K, Bonsal B, Hanesiak J, Kochtubajda B, Evans F, Stewart R (2015) Hydroclimatic aspects of the 2011 Assiniboine river basin flood. J Hydrometeor 16:1250–1272. https://doi.org/10.1175/JHM-D-14-0033.1
Brown and Lemon (2022) Fact Sheets Cations and Cation Exchange Capacity. Available at: https://www.soilquality.org.au/factsheets/cation-exchange-capacity. Accessed on 30th Aug 2022
Budhathoki S, Rokaya P, Lindenschmidt KE (2022) Impacts of future climate on the hydrology of a transboundary river basin in northeastern North America. J Hydrol. Elsevier. https://www.sciencedirect.com/science/article/pii/S0022169421013676. Accessed 10 Oct 2022
Cahn MD, Hummel JW, Brouer BH (1994) Spatial analysis of soil fertility for site-specific crop management. Soil Sci Soc Am J 58:1240–1248. https://doi.org/10.2136/sssaj1994.03615995005800040035x
Cambardella CA, Moorman TB, Novak JM, Parkin TB, Karlen DL, Turco RF, Konopka AE (1994) Field-scale variability of soil properties in central Iowa soils. Soil Sci Soc Am J 58:1501–1511. https://doi.org/10.2136/sssaj1994.03615995005800050033x
Canadian Society of Soil Science (2020) Soils of Canada. [Online] Available: soilsofcanada.ca. Access 6 Mar 2023
Crookston BS, Yost MA, Bowman M, Veum K, Cardon G, Norton J (2021) Soil health spatial-temporal variation influence soil security on Midwestern. U.S. farms. Soil Secur 3:100005. https://doi.org/10.1016/j.soisec.2021.100005
Et-taleby A, Boussetta M, Benslimane M (2020) Faults detection for photovoltaic field based on k-means, elbow, and average silhouette techniques through the segmentation of a thermal image. Int J Photoenergy. https://www.hindawi.com/journals/ijp/2020/6617597/
Environment and Climate Change Canada (2022) Canadian Environmental Sustainability Indicators: Greenhouse gas emissions. Accessed on 30th Sept 2022. Available at: www.canada.ca/en/environment-climate-change/services/environmental-indicators/greenhouse-gasemissions.html
Environment Canada (2015) Ecological Assessment of the Boreal Shield Ecozone Environment Canada, 20 August. 2022. Available at: http://www.ec.gc.ca/Publications/default.asp?lang=En
Erdman C, Emerson JW (2007) bcp: an R package for performing a Bayesian analysis of change point problems. J Stat Softw 23(3):1–13. https://doi.org/10.18637/jss.v023.i03
Everitt B, Landau S, Leese M, Stahl D (2011) Cluster analysis. Wiley, Chichester
Gholami V, Khaleghi MR, Salimi ET (2020a) Groundwater quality modeling using self-organizing map (SOM) and geographic information system (GIS) on the Caspian southern coasts. J Mountain Sci. https://doi.org/10.1007/s11629-019-5483-y. Springer
Gholami V, Sahour H, Hadian MA (2020b) Mapping soil erosion rates using self-organizing map (SOM) and geographic information system (GIS) on hillslopes. Earth Sci Inform. https://doi.org/10.1007/s12145-020-00499-w. Springer
Guan K, Qu Y, Zhou W, Peng B, Tang J, Jin Z, Grant RF, Mezbahuddin S (2019) Simulating surface energy-water-carbon fluxes and crop yield using Ecosys model over agroecosystem in the US Corn Belt. AGU Fall Meeting. https://ui.adsabs.harvard.edu/abs/2019AGUFMGC31J1347G/abstract. Accessed 10 Oct 2022
Guo D (2008) Regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP). Int J Geogr Inf Sci 2008:801–823
Hsu K, Gupta HV, Gao X, Sorooshian S, Imam B (2002) Self-organizing linear output (SOLO): an artificial neural network suitable for hydrologic modeling and analysis. Water Resour Res 38(12):1302. https://doi.org/10.1029/2001WR000795
Indigenous Watchdog (2023). First Nations. Available at: https://www.indigenouswatchdog.org/first-nations/. Accessed on 6th Mar 2023
Iwashita F, Friedel MJ, Filho-Souza CR, Fraser SJ (2011) Hillslope chemical weathering across Paraná, Brazil: a data mining-GIS hybrid approach. Geomorphology 132(3–4):167–175. https://doi.org/10.1016/j.geomorph.2011.05.006
James NA, Matteson DS (2014) ecp: an R package for nonparametric multiple change point analysis of multivariate data. J Stat Softw 62(7):1–25. https://www.jstatsoft.org/v62/i07/. Accessed 10 Oct 2022
Keshav K, Haghnegahdar A, Elshamy M, Gharari S, Razavi S (2019) Aggregated gridded soil texture dataset for Mackenzie and Nelson-Churchill River Basins. Federated Research Data Repository. https://doi.org/10.20383/101.0154
Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480. https://doi.org/10.1109/5.58325
Kohonen T (2013) Essentials of the self-organizing map. Neural Netw 37:52–65. https://doi.org/10.1016/j.neunet.2012.09.018
Kohonen T, Oja E, Simula O, Visa A, Kangas J (1996) Engineering applications of the self-organizing map. Proc IEEE 84(10):1358–1384. https://doi.org/10.1109/5.537105
Lavelle P, Spain A, Blouin M, Brown G, Decaëns T, Grimaldi M, Jiménez JJ, McKey D, Mathieu J, Velasquez E, Zangerlé A (2016) Ecosystem engineers in a self-organized soil: a review of concepts and future research questions. Soil Sci 181(3/4):91–109. https://doi.org/10.1097/SS.0000000000000155
Lee E, Kim S (2021) Characterization of soil moisture response patterns and hillslope hydrological processes through a self-organizing map. Hydrol Earth Syst Sci 25:5733–5748. https://doi.org/10.5194/hess-25-5733-2021
Liu S, Wei Y, Post W, Cook B, Schaefer K, Thornton M (2013) The Unified North American Soil Map and its implication on the soil organic carbon stock in North America. Biogeosciences. https://doi.org/10.5194/bg-10-2915-2013
Löhr SC, Grigorescu M, Hodgkinson JH, Cox ME, Fraser SJ (2010) Iron occurrence in soils and sediments of a coastal catchment: a multivariate approach using self organising maps. Geoderma 156(3–4):253–266. https://doi.org/10.1016/j.geoderma.2010.02.025
MacDonald MK, Pomeroy JW, Pietroniro A (2009) Parameterizing redistribution and sublimation of blowing snow for hydrological models: tests in a mountainous subarctic catchment. Hydrol Process 23(18):2570–2583. https://doi.org/10.1002/hyp.7356
Mekonnen ZA, Riley WJ, Grant RF (2018) Accelerated nutrient cycling and increased light competition will lead to 21st century shrub expansion in North American Arctic tundra. J Geophys. https://doi.org/10.1029/2017JG004319. Wiley Online Library
Mokarram M, Sathyamoorthy D (2016) Clustering of landforms using self-organizing maps (SOM) in the west of Fars province. IOP Conf Ser: Earth Environ Sci 37:012009. https://doi.org/10.1088/1755-1315/37/1/012009
Moradkhani H, Hsu K, Gupta HV, Sorooshian S (2004) Improved streamflow forecasting using self-organizing radial basis function artificial neural networks. J Hydrol. Elsevier. https://www.sciencedirect.com/science/article/pii/S0022169404001787?casa_token=7UrW3fxukyYAAAAA:jctDFoFizdL57GkNojQBrxM-6pAEe3vgXkdNrbDTe-9ccAxy81Jrk8OKF9uxBMybKT-lAO30jlnZ. Accessed 10 Oct 2022
Morari F, Castrignanò A, Pagliarin C (2009) Application of multivariate geostatistics in delineating management zones within a gravelly vineyard using geo-electrical sensors. Comput Electron Agric. 68:97–107
Paini DR, Worner SP, Cook DC, De Barro PJ, Thomas MB (2010) Using a self-organizing map to predict invasive species: sensitivity to data errors and a comparison with expert opinion. J Appl Ecol. https://doi.org/10.1111/j.1365-2664.2010.01782.x. Wiley Online Library
Pantazi XE, Moshou D, Alexandridis RL, Whetton AMM (2016) Wheat yield prediction using machine learning and advanced sensing techniques. Comput Electron Agric 121:57–65. https://doi.org/10.1016/j.compag.2015.11.018
Park YS, Céréghino R, Compin A, Lek Sovan (2003) Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecol Model 160(3):265–280. https://doi.org/10.1016/S0304-3800(02)00258-2
Pokorny S, Stadnyk TA, Lilhare R, Ali G, Déry SJ, Koenig K (2020) Use of Ensemble-Based Gridded Precipitation Products for Assessing Input Data Uncertainty Prior to Hydrologic Modeling. Water 12(10):2751. https://doi.org/10.3390/w12102751
Pomeroy JW, Schmidt RA (1993) The use of fractal geometry in modeling intercepted snow accumulation and sublimation. Proceedings of the 50th Eastern Snow Conference/61st Western Snow Conference. http://www.merrittnet.org/Papers/Pomeroy_Schmidt_1993.pdf. Accessed 10 Oct 2022
Pomeroy JW, Li L (2000) Prairie and arctic areal snow cover mass balance using a blowing snow model. J Geophys Res 105(D21):26619– 26634. https://doi.org/10.1029/2000JD900149
Rannie WF (2002) The role of the Assiniboine River in the 1826 and 1852 Red River floods. Prairie Perspect. http://pcag.uwinnipeg.ca/Prairie-Perspectives/PP-Vol05/Rannie.pdf. Accessed 10 Oct 2022
Rasouli K, Pomeroy JW, & Whitfield PH (2022) The sensitivity of snow hydrology to changes in air temperature and precipitation in three North American headwater basins. J Hydrol. Elsevier. https://www.sciencedirect.com/science/article/pii/S002216942200035X. Accessed 10 Oct 2022
Rokaya P, Peters D, Elshamy M, Budhathoki S, Lindenschmidt KE (2020) Impacts of future climate on the hydrology of a northern headwaters basin and its implications for a downstream ecosystem. Hydrol Process. https://doi.org/10.1002/hyp.13687
Sarparandeh M, Hezarkhani A (2017) Application of unsupervised pattern recognition approaches for exploration of rare earth elements in Se-Chahun iron ore, central Iran. Geosci Instrum Method Data Syst 6:537–546. https://doi.org/10.5194/gi-6-537-2017
Saxton KE, Rawls WJ (2006) Soil water characteristic estimates by texture and organic matter for hydrologic solutions. Soil Sci Soc Am J 70:1569–1578. https://doi.org/10.2136/sssaj2005.0117
Srinivasulu A, Jain A (2006) A comparative analysis of training methods for artificial neural network rainfall-runoff models. Appl Soft Comput 6(3):295–306. https://doi.org/10.1016/j.asoc.2005.02.002
Sz’ekely GJ, Rizzo ML (2005) Hierarchical clustering via joint between-within distances: extending ward’s minimum variance method. J Classif 22:151–183
Teichgraeber H, Brandt AR (2018) Systematic comparison of aggregation methods for input data time series aggregation of energy systems optimization problems. In: Eden MR, Ierapetritou MG, Towler GP (eds) Computer aided chemical engineering, vol 44, pp 955-960. https://doi.org/10.1016/B978-0-444-64241-7.50154-3
United States Environmental Protection Agency (EPA) (2022) Sources of Greenhouse Gas Emissions. Accessed on 30th Sept 2022. Available at: https://www.epa.gov/ghgemissions/sources-greenhouse-gas-emissions
Wang Y, Fu B, Lü Y, Song C, Luan Y (2010) Local-scale spatial variability of soil organic carbon and its stock in the hilly area of the loess plateau, China. Quat Res 73(1):70–76. https://doi.org/10.1016/j.yqres.2008.11.006
Ward ND, Bianchi TS, Medeiros PM, Seidel M, Richey JE, Keil RG, Sawakuchi HO (2017) Where carbon goes when water flows: carbon cycling across the aquatic continuum. Front Mar Sci 4:7
Wehrens R, Kruisselbrink J (2018) Flexible self-organizing maps in kohonen 3.0. J Stat Softw 87(7):1–18. https://doi.org/10.18637/jss.v087.i07
Wheater HS, Pomeroy JW, Pietroniro A, Davison B, Elshamy M, Yassin F, Rokaya P, Fayad A, Tesemma Z, Princz D, Loukili Y, DeBeer CM, Ireson AM, Razavi S, Lindenschmidt K-E, Elshorbagy A, MacDonald M, Abdelhamed M, Haghnegahdar A, Bahrami A (2022) Advances in modelling large river basins in cold regions with Modélisation Environmentale Communautaire—Surface and Hydrology (MESH), the Canadian hydrological land surface scheme. Hydrol Process 36(4):1–24. https://doi.org/10.1002/hyp.14557
Whittingham H, Ashenden SK (2021) Chapter 5 - hit discovery. In: Ashenden SK (ed) The era of artificial intelligence, machine learning, and data science in the pharmaceutical industry. Academic Press, pp 81–102. https://doi.org/10.1016/B978-0-12-820045-2.00006-4
Xiang Q, Huan Yu, Hongliang Chu, Mengke Hu, Tao Xu, Xiaoyu Xu, Ziyi He (2022) The potential ecological risk assessment of soil heavy metals using self-organizing map. Sci Total Environ 843:156978. https://doi.org/10.1016/j.scitotenv.2022.156978
Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Ann Data Sci 2:165–193. https://doi.org/10.1007/s40745-015-0040-1
Xu X, Frey SK, Boluwade A, Erler AR, Khader O, Lapen DR, Sudicky E (2019) Evaluation of variability among different precipitation products in the Northern Great Plains. J Hydrol: Reg Stud 24. https://doi.org/10.1016/j.ejrh.2019.100608
Yang J, Lee JY, Choi M, Joo Y (2019) A new approach to determine the optimal number of clusters based on the gap statistic. International Conference on Machine … Springer. https://doi.org/10.1007/978-3-030-45778-5_15
Zhao H, Lin Y, Zhou J, Delang CO, He H (2022) Simulation of Holocene soil erosion and sediment deposition processes in the Yellow River basin during the Holocene. CATENA 219:106600. https://doi.org/10.1016/j.catena.2022.106600
Žibret G, Šajn R (2010) Hunting for geochemical associations of elements: factor analysis and self-organising maps. Math Geosci 42:681–703. https://doi.org/10.1007/s11004-010-9288-3
Zubrycki K, Roy D, Osman H, Lewtas K, Gunn G, Grosshans R (2016) Large area planning in the Nelson-Churchill River Basin (NCRB): laying a foundation in northern Manitoba. Available at: https://www.iisd.org/system/files/publications/large-area-planning-nelson-churchill-river-basin-full-report.pdf. Accessed 10 Oct 2022
Acknowledgements
The author would like to thank anonymous reviewers, whose suggestions helped improve the quality of this research.
Author information
Authors and Affiliations
Contributions
All sections of this manuscript were written by the author.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Communicated by: H. Babaie
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Boluwade, A. Spatial heterogeneity and partitioning of soil health indicators in the Northern Great Plains using self-organizing map and change point methods. Earth Sci Inform 16, 2017–2031 (2023). https://doi.org/10.1007/s12145-023-01007-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01007-6