We present a flexible, extensible method for integrating multiple tools into a single large decision support system (DSS) using a forest ecosystem management DSS (NED-2) as an example. In our approach, a rich ontology for the target domain is developed and implemented in the internal data model for the DSS. Semi-autonomous agents control external components and communicate using a blackboard. We illustrate how this multi-agent approach with its blackboard architecture supports the expansion of a DSS (in this case, NED-2) to incorporate new models and decision support tools as they become available. The exemplar NED-2 DSS developed using this method is a goal-driven DSS that integrates a sophisticated inventory system, treatment plan development, growth-and-yield models, wildlife models, fire risk models, knowledge based systems for goal satisfaction analysis, and a powerful report generation system.

The creation of intelligent, human-like agents becomes increasingly eminent in the development of computer games. This paper discusses how the Turing Test might be applied to computer games to find an appropriate design for such an agent.

NED-2 is a Windows-based system designed to improve project-level planning and decision making by providing useful and scientifically sound information to natural resource managers. Resources currently addressed include visual quality, ecology, forest health, timber, water, and wildlife. NED-2 expands on previous versions of NED applications by integrating treatment prescriptions, growth simulation, and alternative comparisons with evaluations of multiple resources across a management unit. The NED-2 system is adaptable for small private holdings, large public properties, or cooperative management across multiple ownerships. NED-2 implements a goal-driven decision process that ensures that all relevant goals are considered; the character and current condition of forestland are known; alternatives to manage the land are designed and tested; the future forest under each alternative is simulated; and the alternative selected achieves the owner's goals. NED-2 is designed to link with the NedLite package for field data collection using a handheld PDA, and is constructed to be easy to link to third-party applications. The NED process is being field tested to demonstrate its utility and identify weaknesses. Results of case studies are summarized for two owners, a private individual and the City of Baltimore, Maryland, and its reservoir lands.

A wide variety of software tools are available to support decision in the management of forest ecosystems. These tools include databases, growth and yield models, wildlife models, silvicultural expert systems, financial models, geographical informations systems, and visualization tools. Typically, each of these tools has its own complex interface and data format. To use these tools in combination, a manager must learn each interface and manually convert data from one format to another. NED-2 uses a blackboard architechture and a set of semi-autonomous agents to manage these tools for hte user. Each agent has the procedural knowledge needed to operate a class of decisions support tools used in forest ecosystem management. The simulation agent can set up input for growth and yield models and knows how to interpret the output from these models. Meta-knowledge bases provide the simulation agent with information about the data formats and control codes used by different growth simulators. The GIS agent can merge information with a shape file and knows how to invoke a geographical information system to display the information. The visualization agent can generate input for stand and landscape visualization tools. The blackboard systems itself includes a powerful agent that integrates a database and a set of Prolog clauses into a single blackboard. The interface agent provides access to all the tools in the system through a single user interface. Other agents allow development of alternative treatment plans; provide analysis of timber, wildlife, water, ecology, and visual goals; and generate a wide variety of reports useful in forest management. The agent architecture is designed to facilitate integration of new third-party decision support tools as they become available.

NED-2 is a robust, intelligent, goal-driven ecosystem management decision sup- port system that integrates a wide variety of modeling tools. These tools include vegetation growth and yield models, wildlife models, silvicultural models, GIS, and visualization tools. Integrating growth and yield models is one of the key elements in the NED- 2 system. Without its integration goal analysis for projected data is impossible. This paper addresses implementation issues for FVS, the simulation model currently included in NED-2