Soil organic carbon (SOC) is an essential component, which soil quality depends on. Thus, understanding the spatial distribution and controlling factors of SOC is paramount to achieving sustainable soil management. In this study, SOC prediction for the Ourika watershed in Morocco was done using four machine learning (ML) algorithms: Cubist, random forest (RF), support vector machine (SVM), and gradient boosting machine (GBM). A total of 420 soil samples were collected at three different depths (0–10 cm, 10–20 cm, and 20–30 cm) from which SOC concentration and bulk density (BD) were measured, and consequently SOC stock (SOCS) was determined. Modeling data included 88 variables incorporating environmental covariates, including soil properties, climate, topography, and remote sensing variables used as predictors. The results showed that RF (R² = 0.79, RMSE = 1.2%) and Cubist (R² = 0.77, RMSE = 1.2%) were the most accurate models for predicting SOC, while none of the models were satisfactory in predicting BD across the watershed. As with SOC, Cubist (R² = 0.86, RMSE = 11.62 t/ha) and RF (R² = 0.79, RMSE = 13.26 t/ha) exhibited the highest predictive power for SOCS. Land use/land cover (LU/LC) was the most critical factor in predicting SOC and SOCS, followed by soil properties and bioclimatic variables. Both combinations of bioclimatic–topographic variables and soil properties–remote sensing variables were shown to improve prediction performance. Our findings show that ML algorithms can be a viable tool for spatial modeling of SOC in mountainous Mediterranean regions, such as the study area.

Boreal peatlands represent a biogeochemically unique and diverse environment in high-latitude landscape. They represent a long-term globally significant sink for carbon dioxide and a source of methane, hence playing an important role in regulating the global climate. There is an increasing interest in deciphering peatland biogeochemical processes to improve our understanding of how anthropogenic and climate change effects regulate the peatland biogeochemistry and greenhouse gas balances. At present, most studies investigating land-atmosphere exchanges of peatland ecosystems are commonly based on single-tower setups, which require the assumption of homogeneous conditions during upscaling to the landscape. However, the spatial organization of peatland complexes might feature large heterogeneity due to its varying underlying topography and vegetation composition. Little is known about how well single site studies represent the spatial variations of biogeochemical processes across entire peatland complexes. The recently established Kulbäcksliden Research Infrastructure (KRI) includes five peatland study sites located less than 3 km apart, thus providing a unique opportunity to explore the spatial variation in ecosystem-scale processes across a typical boreal peatland complex. All KRI sites are equipped with eddy covariance flux towers combined with installations for detailed monitoring of biotic and abiotic variables, as well as catchment-scale hydrology and hydrochemistry. Here, we review studies that were conducted in the Kulbäcksliden area and provide a description of the site characteristics as well as the instrumentation available at the KRI. We highlight the value of long-term infrastructures with ecosystem-scale and replicated experimental sites to advance our understanding of peatland biogeochemistry, hydrology, ecology, and its feedbacks on the environment and climate system.

The Eddy Covariance method (EC) is widely used for measuring carbon (C) and energy fluxes at high frequency between the atmosphere and the ecosystem, but has some methodological limitations and a spatial restriction to an area, called a footprint. Remotely sensed information is usually used in combination with eddy covariance data in order to estimate C fluxes over larger areas. In fact, spectral vegetation indices derived from available satellite data can be combined with EC measurements to estimate C fluxes outside of the tower footprint. Following this approach, the present study aimed to model C fluxes for a karst grassland in Slovenia. Three types of model were considered: (1) a linear relationship between Net Ecosystem Exchange (NEE) or Gross Primary Production (GPP) and each vegetation index; (2) a linear relationship between GPP and the product of a vegetation index with PAR (Photosynthetically Active Radiation); and (3) a simplified LUE (Light Use-Efficiency) model assuming a constant LUE. We compared the performance of several vegetation indices derived from two remote platforms (Landsat and Proba-V) as predictors of NEE and GPP, based on three accuracy metrics, the coefficient of determination (R²), the Root Mean Square Error (RMSE) and the Akaike Information Criterion (AIC). Two types of aggregation of flux data were explored: midday average and daily average fluxes. The vapor pressure deficit (VPD) was used to separate the growing season into two phases, a wet and a dry phase, which were considered separately in the modelling process, in addition to the growing season as a whole. The results showed that NDVI is the best predictor of GPP and NEE during the wet phase, whereas water-related vegetation indices, namely LSWI and MNDWI, were the best predictors during the dry phase, both for midday and daily aggregates. Model 1 (linear relationship) was found to be the best in many cases. The best regression equations obtained were used to map GPP and NEE for the whole study area. Digital maps obtained can practically contribute, in a cost-effective way to the management of karst grasslands.

Rewetting is considered a strategy for mitigating carbon dioxide (CO₂) emissions from drained peatlands, with associated climate benefits often derived by applying emission factors (EFs). However, data from rewetted sites are lacking, particularly for boreal peatland forests established on drained nutrient‐poor fens. Instead, their EFs have been developed primarily based on data from natural mires, implying similar carbon (C) cycles. In this study, we integrated eddy covariance measurements of ecosystem CO₂ and methane (CH₄) exchanges with dissolved C export estimates to compare the net ecosystem C balance (NECB) of a recently rewetted minerogenic peatland and two nearby undisturbed fen‐type mires in northern Sweden. We found that the rewetted peatland was an annual C source with a mean NECB of +77 ± 34 g C m⁻² year⁻¹ (±SD) over the initial 3 years following rewetting. In comparison, the mires were nearly C neutral or a C sink with their 3‐year mean NECB ranging between +11 and −34 g C m⁻² year⁻¹. The net CO₂ emission of the rewetted peatland declined to about half by the third year coinciding with an increase in gross primary production. Annual CH₄ emissions from the rewetted peatland steadily increased but remained at 32% and 49% in the first and third year, respectively, relative to the mires. We further noted differences in key environmental response functions of CO₂ and CH₄ fluxes between the rewetted and natural peatlands. Relative to the mires, the dissolved C loss was significantly greater in the rewetted peatland during the first year, but similar in subsequent years. Thus, our study demonstrates that the C balance of a recently rewetted minerogenic peatland may not immediately resemble that of natural mires. This further highlights the need for separate and dynamic EFs to improve estimates of the short‐term climate benefit of rewetting measures.

Karst systems represent an important carbon sink worldwide. However, several phenomena such as the CO₂ degassing and the exchange of cave air return a considerable amount of CO₂ to the atmosphere. It is therefore of paramount importance to understand the contribution of the ecosystem to the carbon budget of karst areas. In this study conducted in a mid-succession ecosystem developed on abandoned karst grassland, two types of model were assessed, estimating the gross primary production (GPP) or the net ecosystem exchange (NEE) based on seven years of eddy covariance data (2013–2019): (1) a quadratic vegetation index-based empirical model with five alternative vegetation indices as proxies of GPP and NEE, and (2) the vegetation photosynthesis model (VPM) which is a light use efficiency model to estimate only GPP. The Enhanced Vegetation Index (EVI) was the best proxy for NEE whereas SAVI performed very similarly to EVI in the case of GPP in the empirical model setting. The empirical model performed better than the VPM model which tended to underestimate GPP. Therefore, for this ecosystem, we suggest the use of the empirical model provided that the quadratic relationship observed persists. However, the VPM model would be a good alternative under a changing climate, as it is rooted in the understanding of the photosynthesis process, if the scalars it involves could be improved to better estimate GPP.

Phenological events are good indicators of the effects of climate change, since phenological phases are sensitive to changes in environmental conditions. Although several national phenological networks monitor the phenology of different plant species, direct observations can only be conducted on individual trees, which cannot be easily extended over large and continuous areas. Remote sensing has often been applied to model phenology for large areas, focusing mostly on pure forests in which it is relatively easier to match vegetation indices with ground observations. In mixed forests, phenology modelling from remote sensing is often limited to land surface phenology, which consists of an overall phenology of all tree species present in a pixel. The potential of remote sensing for modelling the phenology of individual tree species in mixed forests remains underexplored. In this study, we applied the seasonal midpoint (SM) method with MODIS GPP to model the start of season (SOS) and the end of season (EOS) of six different tree species in Slovenian mixed forests. First, substitute locations were identified for each combination of observation station and plant species based on similar environmental conditions (aspect, slope, and altitude) and tree species of interest, and used to retrieve the remote sensing information used in the SM method after fitting the best of a Gaussian and two double logistic functions to each year of GPP time series. Then, the best thresholds were identified for SOS and EOS, and the results were validated using cross-validation. The results show clearly that the usual threshold of 0.5 is not best in most cases, especially for estimating the EOS. Despite the difficulty in modelling the phenology of different tree species in a mixed forest using remote sensing, it was possible to estimate SOS and EOS with moderate errors as low as <8 days (Fagus sylvatica and Tilia sp.) and <10 days (Fagus sylvatica and Populus tremula), respectively.