ecocast
Home Data Reserach Applications Technology Education Publications People
 
Research  >  IEP > Architecture
< Overview  |  IEP  |  TOPS  |  REASoN  |  EOS  |  IDS >
Intelligent Ecosystem Prediction with Identification and Analysis of Extreme Events (IEP)

System Architecture

The architecture being developed is adaptable and reusable for a wide range of forecasting capabilities for decision making support. Application front-ends, predictive models, and data mining algorithms are modular and can be easily swapped out as needed to solve different problems. The modular architecture also allows for the concurrent use of multiple biospheric models to generate forecasts for different parameters. Autonomous methods for model validation and update are incorporated into the architecture to continuously improve forecast accuracy.

Component technologies include the following systems:

Biospheric Model
Terrestrial Observation and Prediction System (TOPS), University of Montana / NASA Ames. TOPS is a modeling software system that brings together technologies in information technology, weather/climate forecasting, ecosystem modeling, and satellite remote sensing to enhance management decisions related to floods, droughts, forest fires, human health, and crop, range, and forest production.
(more)

Autonomous Discovery
Tetrad IV Causal Analysis System, UWF / CMU. The TETRAD software system contains a library of algorithms for inferring features of causal structure from background knowledge and statistical constraints. The Tetrad IV architecture allows for modular addition of new models and editors. Basic features include: Building causal graphs. Parameterizing causal graphs as Bayes nets or structural equation models. Instantiating Bayes net and structural equation models from their parameterizations. Estimating Bayes net and structural equation models from data. Searching for causal structure from data using PC, FCI, and Genetic Algorithm procedures. (more)

Planning and Scheduling
IMAGEbot Data Processing Planner, NASA Ames. IMAGEbot is a software agent designed for data processing tasks, such as image processing, text processing and document conversion. These tasks require the planner to reason about the structure and information content of data files and to construct dataflow programs that pipe multiple data-processing commands together. IMAGEbot is a heuristic-search constraint-based planner specialized for planning in the presence of incomplete information and very large universes. (more)

Monitoring and Detection of Events
Web Agent, Fetch Technologies. Fetch has developed agent-based technology for navigating through complex Web sites and extracting data from semi-structured sources. The Fetch web agent enables online sources to be queried as if they were databases. Fetch then provides the assimilated data as a web notification service, which can be integrated with execution agents such as the DoPPLER planner. (more)

 

Summary
Technical Significance
System Architecture
Technical Approach
Accomplishments
Publications & Materials
Partner Institutions
Support

 
footer graphic

Questions & Comments
updated 03/31/04

NASA Official: Rama Nemani
Curator: Forrest Melton