No abstract

No abstract

No abstract

No abstract

This study was carried out in an Atlantic forest remnant in Southeastern Brazil and aimed to spatially model the soil water content (SWC) and net precipitation (NP) on a monthly time scale and to assess the spatial behavior of these hydrological variables in the different seasons. NP is defined by summing throughfall and stemflow, which have been collected after each rain event and accumulated monthly. Soil moisture measurements were carried out monthly up to a depth of 1.00 m and then integrated to obtain the SWC. The exponential semivariogram model was fitted for both hydrological variables, and the goodness-of-fit was assessed by a cross-validation procedure, spatial dependence degree (SDD) and spatial dependence index (SDI). This model provided adequate performance for SWC and NP mapping according to the cross-validation statistics. Based on the SDD, both variables have been classified as a ‘strong spatial dependence structure’. Nevertheless, when the SDI was assessed, NP showed less spatial dependence, while the SWC maintained almost the same performance. Kriging maps pictured the regional climate seasonality due to higher values of both variables in spring and summer than in autumn and winter seasons. However, correlations between NP and SWC are not expressive in the studied period.

Significant differences were found between an Atlantic Forest remnant and a Eucalyptus urograndis plantation in terms of throughfall indicators.The Atlantic Forest remnant receives a higher values of NH 3 and NH 4 from the surrounding lands.Forests promote rain water enrichment with nutrients, performing key role on biogeochemical cycles.

Understanding the spatiotemporal behaviour of soil moisture in tropical forests is fundamental because it mediates processes such as infiltration, groundwater recharge, runoff and evapotranspiration. This study aims to model the spatiotemporal dynamics of soil moisture in an Atlantic forest remnant (AFR) through four machine learning algorithms, as these dynamics represent an important knowledge gap under tropical conditions. Random forest (RF), support vector machine, average neural network and weighted k‐nearest neighbour were studied. The abilities of the models were evaluated by means of root mean square error, mean absolute error, coefficient of determination (R2) and Nash‐Sutcliffe efficiency (NS) for two calibration approaches: (a) chronological and (b) randomized. The models were further compared with a multilinear regression (MLR). The study period spans from September 2012 to November 2019 and relies on variables representing the weather, geographical location, forest structure, soil physics and morphology. RF was the best algorithm for modelling the spatiotemporal dynamics of the soil moisture with an NS of 0.77 and R2 of 0.51 in the randomized approach. This finding highlights the ability of RF to generalize a dataset with contrasting weather conditions. Kriging maps highlighted the suitability of RF to track the spatial distribution of soil moisture in the AFR. Throughfall (TF), potential evapotranspiration (ETo), longitude (Long), diameter at breast height (DBH) and species diversity (H) were the most important variables controlling soil moisture. MLR performed poorly in modelling the spatiotemporal dynamics of soil moisture due to the highly nonlinear condition of this process. Highlights Modelling soil moisture in an Atlantic forest through machine learning. Machine learning algorithms are powerful tools to address the spatiotemporal dynamics of soil moisture. Climate, position and forest variables drive the spatiotemporal pattern of soil moisture. Random forest is the best algorithm to simulate soil moisture dynamics.

No abstract