A toolbox and record for scientific models

Computational science presents a host of challenges for the field of knowledge-based software design. Scientific computation models are difficult to construct. Models constructed by one scientist are easily misapplied by other scientists to problems for which they are not well-suited. Finally, models constructed by one scientist are difficult for others to modify or extend to handle new types of problems. Construction of scientific models actually involves much more than the mechanics of building a single computational model. In the course of developing a model, a scientist will often test a candidate model against experimental data or against a priori expectations. Test results often lead to revisions of the model and a consequent need for additional testing. During a single model development session, a scientist typically examines a whole series of alternative models, each using different simplifying assumptions or modeling techniques. A useful scientific software design tool must support these aspects of the model development process as well. In particular, it should propose and carry out tests of candidate models. It should analyze test results and identify models and parts of models that must be changed. It should determine what types of changes can potentially cure a given negative test result. It should organize candidate models, test data, and test results into a coherent record of the development process. Finally, it should exploit the development record for two purposes: (1) automatically determining the applicability of a scientific model to a given problem; (2) supporting revision of a scientific model to handle a new type of problem. Existing knowledge-based software design tools must be extended in order to provide these facilities.