Spatial predictions including spatially continuous data play a significant role in planning, risk assessment and decision making in environmental management and conservation, and become increasingly required as geographic information systems and modelling techniques are becoming powerful tools in natural resource management and conservation. They are, however, usually not readily available and often difficult and expensive to acquire, especially for vast, mountainous or deep marine regions. Therefore, spatial predictive modelling methods are essential for generating such spatially continuous data. Because of the rapid development in and application of remote sensing in both terrestrial and marine environments, increasingly more environmental variables become available for spatial predictive modelling. This presents an opportunity for scientists to develop and improve their predictive models, but also presents a challenge to select the best set of predictors from a large number of variables to develop an optimal predictive model. Hence spatial predictive modelling is a rapidly developing area, including such as development of novel modelling methods/algorithms, new applications of the existing methods, model selection and predictive model assessment. Therefore, scientists are encouraged to submit their findings in using various predictive modelling methods (e.g. geostatistics, machine learning methods, modern statistics, or novel modelling methods), especially on model/feature selection and improvement of predictive accuracy, with an application case in environmental sciences.