Coastal upland forests are facing widespread mortality as sea-level rise accelerates and precipitation and storm regimes change. The loss of coastal forests has significant implications for the coastal carbon cycle; yet, predicting mortality likelihood is difficult due to our limited understanding of disturbance impacts on coastal forests. The manipulative, ecosystem-scale Terrestrial Ecosystem Manipulation to Probe the Effects of Storm Treatments (TEMPEST) experiment addresses the potential for freshwater and estuarine-water disturbance events to alter tree function, species composition, and ecosystem processes in a deciduous coastal forest in MD, USA. The experiment uses a large-unit (2000 m²), un-replicated experimental design, with three 50 m × 40 m plots serving as control, freshwater, and estuarine-water treatments. Transient saturation (5 h) of the entire soil rooting zone (0–30 cm) across a 2000 m²coastal forest was attained by delivering 300 m³of water through a spatially distributed irrigation network at a rate just above the soil infiltration rate. Our water delivery approach also elevated the water table (typically ~ 2 m belowground) and achieved extensive, low-level inundation (~ 8 cm standing water). A TEMPEST simulation approximated a 15-cm rainfall event and based on historic records, was of comparable intensity to a 10-year storm for the area. This characterization was supported by showing that Hurricane Ida’s (~ 5 cm rainfall) hydrologic impacts were shorter (40% lower duration) and less expansive (80% less coverage) than those generated through experimental manipulation. Future work will apply TEMPEST treatments to evaluate coastal forest resilience to changing hydrologic disturbance regimes and identify conditions that initiate ecosystem state transitions.

Purpose: Machine learning models can improve the prediction of spatial variation of wetland soil properties, such as soil moisture content (SMC) and soil organic matter (SOM). Their performance, however, relies on the quantity of data used to train the model, limiting their use with insufficient data. In this study, we assessed the use of synthetic data constrained by limited field data for training an eXtreme Gradient Boosting (XGBoost) algorithm used to predict the distribution of soil properties based on geophysical measurements constrained by soil samples. Materials and methods: A spatial distribution of soil apparent electrical conductivity (ECa) and laboratory measurements of SOM and SMC from twenty-two core samples were acquired at the St. Michael restored wetland near Defiance, Ohio. The correlations between ECa, SOM, and SMC were explored for predicting the spatial distribution of SOM and SMC. We used a Beta Variational AutoEncoder (β-VAE) approach to synthetically generate over 70,000 training data from the original twenty-two data from soil cores. The training data samples were taken from the latent space. The XGBoost algorithm was then trained on the β-VAE generated data and used to predict the spatial distribution of SOM and SMC at the site. We also validated the accuracy of the XGBoost predictions using an original holdout model validation technique. Results and discussions: The generated synthetic data using the β-VAE include both soil attributes and ECa, which are larger and more diverse than the original training set with an absolute mean reconstructed error for SMC and SOM ranging from 0.018 to 0.022 and 0.026 to 0.041, respectively. This indicates that the β-VAE successfully generated a realistic synthetic dataset and overcame the technical barrier of using limited datasets. In addition, using generated data to expand the original training data helps the XGBoost model make more accurate predictions compared to training on the original data. The XGBoost prediction performance yielded average Lin’s concordance correlation coefficient (LCCC) values of 0.82 and 0.85 for SOM and SMC and a ratio of performance to deviation (RPD) values of 1.92 and 2.22 respectively, indicating a good performance. Conclusions: This study validated the use of β-VAE to successfully generate synthetic wetland soil datasets with attributes of the original field data that can be effectively used to train the machine learning XGBoost model. The proposed framework offers an efficient solution for mapping the spatial variability of soil property in data-scarce wetland soil environments.