Mapping the maximum peat thickness of cultivated organic soils in the southwest plain of Montreal

Abstract

Large organic deposits in the southwestern plain of Montreal have been converted to agricultural land for vegetable production. In addition to the variable depth of the organic deposits, these soils commonly have an impermeable coprogenous layer between the peat and the underlying mineral substratum. Estimations of the depth and thickness of these materials is critical for soil management. Therefore, five drained and cultivated peatlands were studied to estimate their maximum peat thickness (MPT) — a potential key soil property that can help identify management zones for their conservation. MPT can be defined as the depth to the mineral layer (DML) minus the coprogenous layer thickness (CLT). The objective of this study was to estimate DML, CLT, and MPT at a regional-scale using environmental covariates derived from remote sensing. Three machine-learning models (Cubist, Random Forest, and k-Nearest Neighbor) were compared to produce maps of DML and CLT, which were combined to generate MPT at a spatial resolution of 10 m. The Cubist model performed the best for predicting both features of interest, yielding Lin's concordance correlation coefficients of 0.43 and 0.07 for DML and CLT, respectively, using a spatial cross-validation procedure. Interpretation of the drivers of CLT was limited by the poor predictive power of the final model. More precise data on MPT is needed to support soil conservation practices, and more CLT field observations are required to obtain a higher prediction accuracy. Nonetheless, digital soil mapping using open-access geospatial data shows promise for understanding and managing cultivated peatlands.

Modeling Geospatial Distribution of Peat Layer Thickness Using Machine Learning and Aerial Laser Scanning Data

“…This study uses various land surface characterizing indices, which are basically obtained from laser scanning data, such as DEM, slope, WAM, DTW and SAGA TWI, and various cartographic materials such as a historical soil map, quaternary sediment map, etc., as well as geographical characteristics such as X and Y coordinates, continentality, and distance to rivers/lakes. Deragon et al [42] showed that in cultivated agricultural lands, the concentration of various chemical elements on the surface of the soil (thorium, uranium), various topographic indices, such as multiresolution index of the ridge top flatness and valley bottom flatness, and mid-slope position, as well as distance from each peatland's center and other covariates, can all be important in mapping organic soils using machine learning [12]. Gatis et al demonstrated that passive airborne gamma-ray spectrometric data can also be used in peat layer thickness mapping.…”

Vegetable Response to Added Nitrogen and Phosphorus Using Machine Learning Decryption and the N/P Ratio

“…Peat thickness less than 60 cm shows signs of soil degradation [38]. Soil thickness and quality may vary widely [39].…”

Advances in soil survey and classification in Canada

“…In this collection, manuscripts apply various machine learning techniques to address classification (Heung et al 2022;Kiss et al 2023;Saurette 2022;Sorenson et al 2022Sorenson et al , 2023 and regression (Deragon et al 2022;Paul et al 2023;Saurette 2022;Zhang et al 2022) applications in DSM. When addressing classification applications of DSM, the methods of analysis fall within two broad categories: polygon disaggregation and point-based mapping approaches.…”

“…In British Columbia, explore the concept of ensemble modelling in DSM research. Deragon et al (2022) characterize the spatial variability of organic deposits in the southwestern plains of Montreal by predicting three soil depth-related properties that are yet to be explored in DSM research: depth to mineral layer, coprogenous layer thickness, and maximum peat thickness. Similarly, Paul et al (2023) apply a similar approach and map the spatiotemporal dynamics of a soil property that is yet to be mapped using DSM techniques: active organic carbon.…”