This is a trial run for a presentation at Geocomputation'97, of a joint paper between myself, Rob Pearson and Peter Whigham. We consider three approaches to learning natural resource models involving spatial relationships, based respectively on decision tree learning, genetic programming and inductive logic programming. In each case, the results of spatial learning on a natural resource problem are compared with the results of non-spatial learning from the same data, and improvements in predictivity or simplicity of the models are noted. We argue also that it is highly desirable that spatial learning systems for natural resource problems incorporate mechanisms for the user specification of learning biases.