Pseudo-nitzschia is a cosmopolitan phytoplankton genus of which some species can form blooms and produce the neurotoxin domoic acid (DA). Identification of Pseudo-nitzschia is generally based on field material or strains followed by morphological and/or molecular characterization. However, this process is time-consuming and laborious, and can not obtain a relatively complete and reliable profile of the Pseudo-nitzschia community, because species with low abundance in the field or potentially unavailable for culturing may easily be overlooked. In the present study, specific ITS primer sets were designed and evaluated using in silico matching. The primer set ITS-84F/456R involving the complete ITS1 region was found optimal. Based on matching with a Pseudo-nitzschia ITS1 reference sequence database carefully-calibrated in this study, a metabarcoding approach using annotated amplicon sequence variants (ASV) was applied in the Taiwan Strait of the East China Sea during two cruises in the spring and summer of 2019. In total, 48 Pseudo-nitzschia species/phylotypes including 36 known and 12 novel were uncovered, and verified by haplotype networks, ITS2 secondary structure comparisons and divergence analyses. Correlation analyses revealed that temperature was a key factor affecting the seasonal variation of the Pseudo-nitzschia community. This study provides an overview of the Pseudo-nitzschia community in the Taiwan Strait, with new insights into the diversity. The developed metabarcoding approach may be used elsewhere as a standard reference for accurate annotation of Pseudo-nitzschia.
Soil erosion by wind poses a significant threat to various regions across the globe, such as drylands in the Middle East and Iran. Wind erosion hazard maps can assist in identifying the regions of highest wind erosion risk and are a valuable tool for the mitigation of its destructive consequences. This study aims to map wind erosion hazards by developing an interpretable (explainable) model based on machine learning (ML) and Shapley additive exPlanation (SHAP) interpretation techniques. Four ML models, namely random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and quadratic discriminant analysis (QDA) were used. Thirteen features associated with wind erosion were mapped spatially and then subjected to a multivariate adaptive regression spline (MARS) feature selection algorithm, and then, tolerance coefficient (TC) and variance inflation factor (VIF) statistical tests were used to explore multicollinearity among the variables. MARS analysis shows that eight features consisting of elevation (or DEM), soil bulk density, precipitation, aspect, slope, soil sand content, vegetation cover (or NDVI), and lithology were the most effective for wind erosion, while no collinearity existed among these variables. The ML models were used for ranking the effective features, and the research introduces the application of an interpretable ML model for the interpretation of predictive model's output. The ranking of effective features by RF-as the most typical ML model-revealed that elevation and soil bulk density were the two most important features. According to the area under the receiver operating characteristic curve (AUROC) (with a value > 90%) and precision-recall (PR) (with a value > 90%) curves, all four ML models performed with great accuracy. According to the PR curve, the SVM model performed slightly better than others, and its results revealed that 20.9%, 23%, and 16.6% of the total area in Hormozgan Province is characterized by moderate, high, and very high hazard classes to wind erosion, respectively. SHAP revealed that soil sand content and elevation are the most important variables contributing to the predictive model output. Overall, our research is one of the pioneering applications of interpretable ML models in mapping wind erosion hazards in Southern Iran. We recommend that future research should address the aspect of interpretability in order to better understand predictive model outputs.