Seabed sediment predictions at regional and national scales in Australia are mainly based on bathymetry-related variables due to the lack of backscatter-derived data. In this study, we applied random forests (RFs), hybrid methods of RF and geostatistics, and generalized boosted regression modelling (GBM), to seabed sand content point data and acoustic multibeam data and their derived variables, to develop an accurate model to predict seabed sand content at a local scale. We also addressed relevant issues with variable selection. It was found that: (1) backscatter-related variables are more important than bathymetry-related variables for sand predictive modelling; (2) the inclusion of highly correlated predictors can improve predictive accuracy; (3) the rank orders of averaged variable importance (AVI) and accuracy contribution change with input predictors for RF and are not necessarily matched; (4) a knowledge-informed AVI method (KIAVI2) is recommended for RF; (5) the hybrid methods and their averaging can significantly improve predictive accuracy and are recommended; (6) relationships between sand and predictors are non-linear; and (7) variable selection methods for GBM need further study. Accuracy-improved predictions of sand content are generated at high resolution, which provide important baseline information for environmental management and conservation. <b>Citation:</b> Li, J.; Siwabessy, J.; Huang, Z.; Nichol, S. Developing an Optimal Spatial Predictive Model for Seabed Sand Content Using Machine Learning, Geostatistics, and Their Hybrid Methods. <i>Geosciences</i> 2019, 9, 180. https://doi.org/10.3390/geosciences9040180

Spatial predictive methods are increasingly being used to generate predictions across various disciplines in environmental sciences. Accuracy of the predictions is critical as they form the basis for environmental management and conservation. Therefore, improving the accuracy by selecting an appropriate method and then developing the most accurate predictive model(s) is essential. However, it is challenging to select an appropriate method and find the most accurate predictive model for a given dataset due to many aspects and multiple factors involved in the modeling process. Many previous studies considered only a portion of these aspects and factors, often leading to sub-optimal or even misleading predictive models. This study evaluates a spatial predictive modeling process, and identifies nine major components for spatial predictive modeling. Each of these nine components is then reviewed, and guidelines for selecting and applying relevant components and developing accurate predictive models are provided. Finally, reproducible examples using spm, an R package, are provided to demonstrate how to select and develop predictive models using machine learning, geostatistics, and their hybrid methods according to predictive accuracy for spatial predictive modeling; reproducible examples are also provided to generate and visualize spatial predictions in environmental sciences. <b>Citation:</b> Li, J. A Critical Review of Spatial Predictive Modeling Process in Environmental Sciences with Reproducible Examples in R. Appl. Sci. 2019, 9, 2048. https://doi.org/10.3390/app9102048

Spatial predictive models have been increasingly employed to generate spatial predictions for environmental management and conservation in parallel to the advancement in data acquisition, data processing and computing capabilities. The accuracy of predictive models and their predictions is crucial to evidence-informed decision making and policy. However, the accuracy of predictive models in general is unknown and often accessed using error measures or even correlation measure. In this study, we clarified relevant issues about variance explained for predictive models (VEcv), established the relationships between commonly used predictive error measures like root mean square error (RMSE) and VEcv, unified these measures under VEcv, discovered that VEcv is independent of unit/scale and data variation, quantified the relationships between these error measures and data variation, and quantified the relationship between relative root mean square error (RRMSE) and relative mean absolute error (RMAE). We then assessed the performance of predictive models in the environmental sciences based on about 300 previously published applications and then classified the predictive models based on their performance. This study provided a tool to directly compare the accuracy of predictive models for data with different unit/scale and variation, and established a cross-disciplinary context and benchmark for assessing predictive models in environmental sciences and other disciplines. Recommendations for future studies were provided to objectively assess the performance of predictive models and make the accuracy of predictive models for different disciplines directly comparable. Abstract presented at the 23rd Australian Statistical Conference 2016