Seabed sediment textural parameters such as mud, sand and gravel content can be useful surrogates for predicting patterns of benthic biodiversity. Multibeam sonar mapping can provide near-complete spatial coverage of high-resolution bathymetry and backscatter data that are useful in predicting sediment parameters. Multibeam acoustic data collected across a ∼1000 km² area of the Carnarvon Shelf, Western Australia, were used in a predictive modelling approach to map eight seabed sediment parameters. Four machine learning models were used for the predictive modelling: boosted decision tree, random forest decision tree, support vector machine and generalised regression neural network. The results indicate overall satisfactory statistical performance, especially for %Mud, %Sand, Sorting, Skewness and Mean Grain Size. The study also demonstrates that predictive modelling using the combination of machine learning models has provided the ability to generate prediction uncertainty maps. However, the single models were shown to have overall better prediction performance than the combined models. Another important finding was that choosing an appropriate set of explanatory variables, through a manual feature selection process, was a critical step for optimising model performance. In addition, machine learning models were able to identify important explanatory variables, which are useful in identifying underlying environmental processes and checking predictions against the existing knowledge of the study area. The sediment prediction maps obtained in this study provide reliable coverage of key physical variables that will be incorporated into the analysis of covariance of physical and biological data for this area.

Spatially continuous predictions of seabed hardness are important baseline environmental information for sustainable management of Australia’s marine jurisdiction. Seabed hardness is often inferred from multibeam backscatter data with unknown accuracy and can be inferred from underwater video footage at limited locations. In this study, we classified the seabed into four classes based on two new seabed hardness classification schemes (i.e., hard90 and hard70). We developed optimal predictive models to predict seabed hardness using random forest (RF) based on the point data of hardness classes and spatially continuous multibeam data. Five feature selection (FS) methods that are variable importance (VI), averaged variable importance (AVI), knowledge informed AVI (KIAVI), Boruta and regularized RF (RRF) were tested based on predictive accuracy. Effects of highly correlated, important and unimportant predictors on the accuracy of RF predictive models were examined. Finally, spatial predictions generated using the most accurate models were visually examined and analysed. This study confirmed that: 1) hard90 and hard70 are effective seabed hardness classification schemes; 2) seabed hardness of four classes can be predicted with a high degree of accuracy; 3) the typical approach used to pre-select predictive variables by excluding highly correlated variables needs to be re-examined; 4) the identification of the important and unimportant predictors provides useful guidelines for further improving predictive models; 5) FS methods select the most accurate predictive model(s) instead of the most parsimonious ones, and AVI and Boruta are recommended for future studies; and 6) RF is an effective modelling method with high predictive accuracy for multi-level categorical data and can be applied to ‘small p and large n’ problems in environmental sciences. Additionally, automated computational programs for AVI need to be developed to increase its computational efficiency and caution should be taken when applying filter FS methods in selecting predictive models.