ALBERT

Description: In forested regions, transpiration as a main component of evaporation fluxes is important for evaporation partitioning. Physiological behaviours among various vegetation species are quite different. Thus, an accurate estimation of the transpiration rate from a certain tree species needs specific parameterization of stomatal response to multiple environmental conditions. In this study, we chose a 300-m2 beech forest plot located in Vydra basin, the Czech Republic, to investigate the transpiration of beech (Fagus sylvatica) from the middle of the vegetative period to the beginning of the deciduous period, covering 100 days. The sap flow equipment was installed in six trees with varying ages among 32 trees in the plot, and the measurements were used to infer the stomatal conductance. The diurnal pattern of stomatal conductance and the response of stomatal conductance under the multiple environmental conditions were analysed. The results show that the stomatal conductance inferred from sap flow reached the highest at midday but, on some days, there was a significant drop at midday, which might be attributed to the limits of the hydraulic potential of leaves (trees). The response of stomatal conductance showed no pattern with solar radiation and soil moisture, but it did show a clear correlation with the vapour deficit, in particular when explaining the midday drop. The relation to temperature was rather scattered as the measured period was in the moderate climate. The findings highlighted that the parametrization of stress functions based on the typical deciduous forest does not perfectly represent the measured stomatal response of beech. Therefore, measurements of sap flow can assist in better understanding transpiration in newly formed beech stands after bark beetle outbreaks in Central Europe.

Description: One of the best preconditions for the sufficient monitoring of peat bog ecosystems is the collection, processing, and analysis of unique spatial data to understand peat bog dynamics. Over two seasons, we sampled groundwater level (GWL) and soil moisture (SM) ground truth data at two diverse locations at the Rokytka Peat bog within the Sumava Mountains, Czechia. These data served as reference data and were modeled with a suite of potential variables derived from digital surface models (DSMs) and RGB, multispectral, and thermal orthoimages reflecting topomorphometry, vegetation, and surface temperature information generated from drone mapping. We used 34 predictors to feed the random forest (RF) algorithm. The predictor selection, hyperparameter tuning, and performance assessment were performed with the target-oriented leave-location-out (LLO) spatial cross-validation (CV) strategy combined with forward feature selection (FFS) to avoid overfitting and to predict on unknown locations. The spatial CV performance statistics showed low (R2 = 0.12) to high (R2 = 0.78) model predictions. The predictor importance was used for model interpretation, where temperature had strong impact on GWL and SM, and we found significant contributions of other predictors, such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Index (NDI), Enhanced Red-Green-Blue Vegetation Index (ERGBVE), Shape Index (SHP), Green Leaf Index (GLI), Brightness Index (BI), Coloration Index (CI), Redness Index (RI), Primary Colours Hue Index (HI), Overall Hue Index (HUE), SAGA Wetness Index (TWI), Plan Curvature (PlnCurv), Topographic Position Index (TPI), and Vector Ruggedness Measure (VRM). Additionally, we estimated the area of applicability (AOA) by presenting maps where the prediction model yielded high-quality results and where predictions were highly uncertain because machine learning (ML) models make predictions far beyond sampling locations without sampling data with no knowledge about these environments. The AOA method is well suited and unique for planning and decision-making about the best sampling strategy, most notably with limited data.