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

Abstract

Organic horizons including peat deposits are important terrestrial carbon pools, and various chemical, biological, and water exchange processes take place within them. Accurate information on the spatial distribution of organic soils and their properties is important for decision-making and land management. In this study, we present a machine learning approach for mapping the distribution of organic soils and determining the thickness of the peat layer using more than 24,000 peat layer thickness measurements obtained from field data, airborne laser scanning (ALS) data and various indices obtained from therein, as well as other cartographic materials. Our objectives encompassed two primary aims. Firstly, we endeavored to develop updated cartographic materials depicting the spatial distribution of peat layers. Secondly, we aimed to predict the depth of peat layers, thereby enhancing our understanding of soil organic carbon content. Continentality, a wet area map, latitude, a depth to water map with catchment area of 10 ha, and a digital elevation model were the most important covariates for the machine learning model. As a result, we obtained a map with three peat layer thickness classes, an overall classification accuracy of 0.88, and a kappa value of 0.74. This research contributes to a better understanding of organic soil dynamics and facilitates improved assessments of soil organic carbon stocks.

Quantifying Dissolved Organic Carbon Efflux from Drained Peatlands in Hemiboreal Latvia

“…Our results revealed that among all studied land use types of peatlands, the mean annual DOC efflux varied from 61.9 ± 4.4 kg ha −1 y −1 in grasslands to 513.1 ± 38.7 kg ha −1 y −1 active peat extraction sites. Silver birch (153.6 ± 11.2 kg ha −1 y −1 ) and Scots pine forests (328.3 ± 23.1 kg ha −1 y −1 ) are common in Latvia, where more than 10% of the total area is covered by peatlands [11,12]. The DOC efflux from Scots pine forests and all peat extraction sites coincided with values from the temperate climate zone, while efflux from silver birch forests, croplands, and grasslands were more comparable to the results from the boreal zone, which contributes to previous findings about the thermal gradient impact.…”

“…Lowering the water table by drainage is a prerequisite for peatland forestry, use for agriculture, and peat extraction in most countries [9,10]. These practices are also common in Latvia, where more than 10% of the total area is covered by peatlands [11,12]. As a result, the hydrological regime of the peatlands is altered, and mineralization of peat is promoted, resulting in increased gross C losses.…”