Combining laboratory measurements and proximal soil sensing data in digital soil mapping approaches

• Published in: Catena (Giessen) 2021-12, Vol.207, p.105702, Article 105702
• Main Authors: Zare, Sanaz, Abtahi, Ali, Fallah Shamsi, Seyed Rashid, Lagacherie, Philippe
• Format: Article
• Language: English
• Subjects: Digital soil mapping; Machine Learning; Quantile Random Forest; Regression co-kriging; Remote sensing; Soil salinity; Soil sensing; Statistics
• ISSN: 0341-8162; 1872-6887
• DOI: 10.1016/j.catena.2021.105702

[Display omitted] •Soil sensing products are the potential inputs for DSM.•Three possible approaches for integrating such new input are proposed.•Regression co-kriging is an appropriate method for integration.•EM38MK2 could be used in DSM as a surrogate input data for mapping soil salinity.•EM38MK2 data was a solution for partially mitigating the sparsity of costly real data. Digital soil mapping (DSM) products are limited in accuracy because of the lack of soil inputs. Soil sensing is a promising alternative to direct soil measurements that could provide much denser spatial samplings. Although using relevant and detailed soil sensing input in DSM is considered as vital to increase the prediction performances, there has been no studies in the literature that compare and develop the methods for integrating new sources of soil data that can be applied as inputs of DSM. This paper fills this gap on the example of mapping electrical conductivities from sites with laboratory measurements, in-field EM38MK2 measurements and spatially exhaustive covariates. Three different approaches are tested for putting in synergy real measurements and EM38MK2 measurements: (i) EM38MK2 measurement considered as measured points, (ii) EM38MK2 measurement used for building a new soil covariate and (iii) EM38MK2 measurement considered as a soft data in a regression co-kriging approach. According to soil analysis's financial expenditure, choosing an optimal sample size to merge laboratory analysis and in-field EM38MK2 measurements as surrogate data was done on the best method. The results showed (i) the utility of EM38MK2 data in DSM as a surrogate input data for mapping soil salinity (ii) Regression co-kriging was the best method for integration and (iii) The impact of EM38MK2 data on the gains of performance becomes greater and greater as the sizes of real measurements of soil salinity decrease. Hence, in other areas worldwide that soil sensing as alternative data is accessible, this research's future utilization could be possible as a promising way to tackle one of the essential constraints of DSM.