Developing optimal spatial predictive model for seabed sand content using machine learning, geostatistics and their hybrid methods based on acoustic multibeam data and their derived variables

Seabed sediment predictions at regional and national scales in Australia are mainly based on bathymetry related variables due to the lack of backscatter related data. In this study, we applied random forests (RF), 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 the most accurate model to predict seabed sand content at local scale, by also addressing 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 can significantly improve predictive accuracy and are recommended; 6) relationships of 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 for environmental management and conservation in the study region. Citation: 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. Geosciences 2019, 9, 180. https://doi.org/10.3390/geosciences9040180