Extensive use of drainage ditches in European boreal forests and in some parts of North America has resulted in a major change in wetland and soil hydrology and impacted the overall ecosystem functions of these regions. An increasing understanding of the environmental risks associated with forest ditches makes mapping these ditches a priority for sustainable forest and land use management. Here, we present the first rigorous deep learning–based methodology to map forest ditches at regional scale. A deep neural network was trained on airborne laser scanning data (ALS) and 1,607 km of manually digitized ditch channels from 10 regions spread across Sweden. The model correctly mapped 86% of all ditch channels in the test data, with a Matthews correlation coefficient of 0.78. Further, the model proved to be accurate when evaluated on ALS data from other heavily ditched countries in the Baltic Sea Region. This study leads the way in using deep learning and airborne laser scanning for mapping fine-resolution drainage ditches over large areas. This technique requires only one topographical index, which makes it possible to implement on national scales with limited computational resources. It thus provides a significant contribution to the assessment of regional hydrology and ecosystem dynamics in forested landscapes.

Nutrient-rich organic soil management in agriculture is among the critical sources of greenhouse gas (GHG) emissions globally and at the European level, where the most significant effects are observed in Northern, Eastern, and Central Europe. Growing climate change mitigation targets urge the need to assess and analyze current organic soil management patterns and policy planning and look for appropriate future management strategies. The objectives of this research were to assess the nutrient-rich organic soil management patterns in Latvia during the last decade and to conclude whether organic soil management in agriculture has been climate change mitigation targeted and driven by agriculture support policy. We analyzed the complex, two state-level databases based organic soil data set by using the multidimensional approach of the research methods, including graphical, spatial, correlation, factor, and cluster analysis. Our results revealed the lack of purposeful organic soil management planning in light of the climate change policy in Latvia during the research period and the inexpediency of the agriculture support policy in this regard. The research introduced an innovative methodological approach for the analysis of organic soil management patterns and policy impacts, as well as opened the necessity for a revision of the nutrient-rich organic soil management perspective in light of climate change mitigation targets. Doi: 10.28991/CEJ-2022-08-10-017 Full Text: PDF

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.

When it comes to greenhouse gas (GHG) reduction, the role of water tables in former peat extraction areas has received considerable interest in recent decades. This study analysed the carbon dioxide (CO₂), methane (CH₄) and nitrous oxide (N₂O) surface-to-atmosphere fluxes from a rewetted and permanently flooded former peat extraction areas in comparison to pristine peatland in hemiboreal Latvia. Measurements of GHG fluxes combined gas sampling using a closed-chamber (opaque) method with the gas chromatography detection method. Among the studied land-use types, the highest annualised CO₂ fluxes (soil heterotrophic and autotrophic respiration) were recorded in rewetted former peat extraction areas with restored vegetation and in undisturbed peatland (4.10 ± 0.21 and 3.45 ± 0.21 t CO₂-C ha⁻¹ yr⁻¹, respectively), with the lowest in flooded former peat extraction areas (0.55 ± 0.05 t CO₂-C ha⁻¹ yr⁻¹); temperature and groundwater level were found to be significant influencing factors. The highest annualised CH₄ fluxes were recorded in undisturbed peatland (562.4 ± 155.8 kg CH₄-C ha⁻¹ yr⁻¹), followed by about two-fold and ~20-fold smaller CH₄ fluxes in flooded and rewetted areas, respectively. N₂O fluxes were negligible in all the studied land-use types, with the highest N₂O fluxes in undisturbed peatland (0.66 ± 0.41 kg N₂O-N ha⁻¹ yr⁻¹).

Emissions of carbon dioxide (CO₂), nitrous oxide (N₂O), and methane (CH₄), particularly those from organic soils, need to be reduced in the context of climate change mitigation (CCM). Here, we estimated the greenhouse gas (GHG) fluxes from nutrient-poor organic soils in cranberry (Vaccinium macrocarpon) and highbush blueberry (Vaccinium corymbosum) plantations established on former peat extraction fields compared to active peat extraction fields and pristine raised bogs in Latvia. A two-year study (2016–2018) was conducted using the manual closed chamber method. In berry plantations and active peat extraction fields, annual net CO₂ fluxes contributed the most to total GHG emissions, accounting for over 67%, and temperature had the most significant impact on CO₂ fluxes. Conversely, annual CH₄ fluxes were the primary contributor to total net GHG emissions in the pristine raised bog, which simultaneously acted as a slight CO₂ sink. N₂O fluxes were relatively low among all studied land use types. This study provided quantitative insights into the variation in GHG fluxes and the environmental variables influencing them, and the obtained data are valuable to estimate the impact of the establishment of berry plantations on former peat extraction fields on CCM in the hemiboreal region of Europe.