Tidal marshes are threatened coastal ecosystems known for their capacity to store large amounts of carbon in their water-logged soils. Accurate quantification and mapping of global tidal marshes soil organic carbon (SOC) stocks is of considerable value to conservation efforts. Here, we used training data from 3710 unique locations, landscape-level environmental drivers and a global tidal marsh extent map to produce a global, spatially explicit map of SOC storage in tidal marshes at 30 m resolution. Here we show the total global SOC stock to 1 m to be 1.44 Pg C, with a third of this value stored in the United States of America. On average, SOC in tidal marshes’ 0–30 and 30–100 cm soil layers are estimated at 83.1 Mg C ha−1 (average predicted error 44.8 Mg C ha−1) and 185.3 Mg C ha−1 (average predicted error 105.7 Mg C ha−1), respectively.
26 January 2023 in Global Ecology and Biogeography
Aim: Global‐scale maps of the environment are an important source of information for researchers and decision makers. Often, these maps are created by training machine learning algorithms on field‐sampled reference data using remote sensing information as predictors. Since field samples are often sparse and clustered in geographic space, model prediction requires a transfer of the trained model to regions where no reference data are available. However, recent studies question the feasibility of predictions far beyond the location of training data.Innovation: We propose a novel workflow for spatial predictive mapping that leverages recent developments in this field and combines them in innovative ways with the aim of improved model transferability and performance assessment. We demonstrate, evaluate and discuss the workflow with data from recently published global environmental maps.Main conclusions: Reducing predictors to those relevant for spatial prediction leads to an increase of model transferability and map accuracy without a decrease of prediction quality in areas with high sampling density. Still, reliable gap‐free global predictions were not possible, highlighting that global maps and their evaluation are hampered by limited availability of reference data.
Random and spatial cross-validation (CV) methods are commonly used to evaluate machine-learning-based spatial prediction models, and the performance values obtained are often interpreted as map accuracy estimates. However, the appropriateness of such approaches is currently the subject of controversy. For the common case where no probability sample for validation purposes is available, in Milà et al. (2022) we proposed the nearest-neighbour distance matching (NNDM) leave-one-out (LOO) CV method. This method produces a distribution of geographical nearest-neighbour distances (NNDs) between test and training locations during CV that matches the distribution of NNDs between prediction and training locations. Hence, it creates predictive conditions during CV that are comparable to what is required when predicting a defined area. Although NNDM LOO CV produced largely reliable map accuracy estimates in our analysis, as a LOO-based method, it cannot be applied to the large datasets found in many studies. Here, we propose a novel k-fold CV strategy for map accuracy estimation inspired by the concepts of NNDM LOO CV: the k-fold NNDM (kNNDM) CV. The kNNDM algorithm tries to find a k-fold configuration such that the empirical cumulative distribution function (ECDF) of NNDs between test and training locations during CV is matched to the ECDF of NNDs between prediction and training locations. We tested kNNDM CV in a simulation study with different sampling distributions and compared it to other CV methods including NNDM LOO CV. We found that kNNDM CV performed similarly to NNDM LOO CV and produced reasonably reliable map accuracy estimates across sampling patterns. However, compared to NNDM LOO CV, kNNDM resulted in significantly reduced computation times. In an experiment using 4000 strongly clustered training points, kNNDM CV reduced the time spent on fold assignment and model training from 4.8 d to 1.2 min. Furthermore, we found a positive association between the quality of the match of the two ECDFs in kNNDM and the reliability of the map accuracy estimates. kNNDM provided the advantages of our original NNDM LOO CV strategy while bypassing its sample size limitations.
Spatial proxies, such as coordinates and distance fields, are often added as predictors in random forest (RF) models without any modifications being made to the algorithm to account for residual autocorrelation and improve predictions. However, their suitability under different predictive conditions encountered in environmental applications has not yet been assessed. We investigate (1) the suitability of spatial proxies depending on the modelling objective (interpolation vs. extrapolation), the strength of the residual spatial autocorrelation, and the sampling pattern; (2) which validation methods can be used as a model selection tool to empirically assess the suitability of spatial proxies; and (3) the effect of using spatial proxies in real-world environmental applications. We designed a simulation study to assess the suitability of RF regression models using three different types of spatial proxies: coordinates, Euclidean distance fields (EDFs), and random forest spatial prediction (RFsp). We also tested the ability of probability sampling test points, random k-fold cross-validation (CV), and k-fold nearest neighbour distance matching (kNNDM) CV to reflect the true prediction performance and correctly rank models. As real-world case studies, we modelled annual average air temperature and fine particulate air pollution for continental Spain. In the simulation study, we found that RFs with spatial proxies were poorly suited for spatial extrapolation to new areas due to significant feature extrapolation. For spatial interpolation, proxies were beneficial when both strong residual autocorrelation and regularly or randomly distributed training samples were present. In all other cases, proxies were neutral or counterproductive. Random k-fold cross-validation generally favoured models with spatial proxies even when it was not appropriate, whereas probability test samples and kNNDM CV correctly ranked models. In the case studies, air temperature stations were well spread within the prediction area, and measurements exhibited strong spatial autocorrelation, leading to an effective use of spatial proxies. Air pollution stations were clustered and autocorrelation was weaker and thus spatial proxies were not beneficial. As the benefits of spatial proxies are not universal, we recommend using spatial exploratory and validation analyses to determine their suitability, as well as considering alternative inherently spatial modelling approaches.