By Olivier Allain, Roland N. Horne (auth.), Ibrahim Palaz, Sailes K. Sengupta (eds.)
Here is a state of the art survey of synthetic intelligence in smooth exploration courses. Focussing on typical exploration tactics, the contributions learn the benefits and pitfalls of utilizing those new innovations, and, within the strategy, supply new, extra actual and constant tools for fixing outdated difficulties. They express how professional structures supplies the combination of data that's crucial within the petroleum while fixing the complex questions dealing with the fashionable petroleum geoscientist.
Read Online or Download Automated Pattern Analysis in Petroleum Exploration PDF
Similar analysis books
This primary ebook of a 3-volume set on Fracture Mechanics is principally founded at the great diversity of the legislation of statistical distributions encountered in quite a few medical and technical fields. those legislation are critical in figuring out the chance habit of elements and mechanical buildings which are exploited within the different volumes of this sequence, that are devoted to reliability and qc.
- Policy Implementation in Federal and Unitary Systems: Questions of Analysis and Design
- Analysis of Variance for Random Models [Vol II - Unbalanced Data]
- Early Fourier Analysis
- Discourse and Digital Practices: Doing Discourse Analysis in the Digital Age
Additional resources for Automated Pattern Analysis in Petroleum Exploration
Of Nijmegen, Netherlands. analysis by a computer assisted matching procedure: paper SPE 6547 presented at the 47th Soc. Petro Engr. , 1983, Perceptual Organization and Visual Annual California Regional Meeting, Bakersfield, Recognition: Kluwer Academic Publishers, Boston. CA. , 1988, test analysis: Soc. Petro Engr. J. 21, 441-446. , 1976, Computer science Model selection for well test and production data as empirical inquiry: Symbols and search: Commun. analysis: Soc. Petro Engr. Formation Evaluation Assoc.
8). We change this expression in the following way. We call [~, ... , s~], LI and [sf, . ,S;], L 2 and consider a rule giving the effect of combining a sublist L~ of L 2, with sJ. L~ is equal to [~, ... , si] for some k :5 p, and we call Li the list constituted by the remaining elements of L2 (it can be empty). With those definitions, the combination of the two models considered is obtained by appending onto [s~, . , sJ_1' comb(sJ, q)] the list L~. For the two previous examples, the addition of new combination rules allows us to correct the behavior of the matching procedure.
B. the models proposed would never be too complex. However, more information means more difficulties, because real data are never totally ideal. It is necessary to develop methods that allow the algorithm to ignore or modify some of the additional information. We will not present such methods here, although some examples can be found in Allain (1988). For the moment, we simply add to the methods developed so far, the two new combination rules (21) and (22), and the restriction to rule (17). With those modiftcations, the matching procedure can in most cases propose the adequate interpretation models.