|
Dr.Robert
Balch, Research
Group Head, e-mail: balch@prrc.nmt.edu Phone: 575-835-5305. Fax: 575-835-6031 |
|||||
| New Mexico Pit Rules | ||||||
| With the recent adoption of new "Pit Rules", New Mexico's small producers will experience an increased level of expenses for drilling and also be exposed to potentially unforeseeable financial risk due to a more complex and expensive application process and increases in need and expense of remediation at both new and existing well sites. We have been funded by the RPSEA Small Producer Program to generate software and maps that predict reasonable financial cost and risk for locating a well/pit in any particular location in New Mexico, including predictable leaching, potential site regulatory issues, and to the degree possible, a reduction in the need for specialist on-site evaluations by online mapping of government accepted data and automated forms. | ||||||
| Data Mining Consortium | ||||||
| Advances in computer power and database management have led to the development of powerful algorithms for making proactive business decisions using large databases. This consortium actively pursues research to apply data mining to industry applications. A pilot project was performed which determined optimal completion techniques for San Juan basin Dakota wells which can decrease overall completion costs while optimizing potential recovery. For information on joining the consortium contact Robert Balch | ||||||
| Fuzzy Expert Exploration (FEE) Tool | ||||||
| Incomplete or sparse information on types of data such as geologic or formation characteristics introduces a high level of risk for oil exploration and development projects. Expert systems developed and used in several disciplines and industries have demonstrated beneficial results. A state-of-the-art exploration "expert" tool, relying on a computerized database and computer maps generated by neural networks, is being developed through the use of "fuzzy" logic, a relatively new mathematical treatment of imprecise or non-explicit parameters and values. Oil prospecting risk can be reduced with the use of a properly developed and validated "Fuzzy Expert Exploration (FEE) Tool. | ||||||
| Web-Based Database Management System(WDMS) | ||||||
| A dynamic web-accessible database for storing, managing, accessing, and analyzing data. This Brushy Canyon specific database has also been used in the development of heuristic fuzzy rules. The data available in WDMS includes well log sections and production data for Brushy Canyon wells. Zoom able maps of key regional attributes such as structure, porosity thickness, gravity and aeromagnetic data are also available. Data is downloadable in Microsoft access or Excel formats and advanced queries are possible by users with SQL experience. | ||||||
| Fuzzy Rank | ||||||
| There are a number of ways to select the best set of inputs to be used to form a regression for a particular output. Simply crossplotting each input against the output can give an indication of the quality of linear or multiple linear regression models that could be formed. In the development of an on line Expert system for oil prospecting we have encountered many non-linear or complex problems. To address this software was developed based on a single stage fuzzy-ranking algorithm to select inputs best suited for predicting the desired output. This global algorithm statistically determines how we ll a particular input could resolve a particular output with respect to any number of other inputs using fuzzy curve analysis. | ||||||
| Predict Online | ||||||
| PredictOnline is a web based implementation of a neural network conjugate gradient algorithm using the conjugate gradient algorithm. PredictOnline is in its 6th version and the most recent improvements include the removal of the java policy file. In the previous versions, a java policy file was needed on the user's computer to allow PredictOnline to access data via applets. Upload and download functions without java policy files have been developed using Java Server Pages. | ||||||