English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

During the summer of 1989, the Forecast Systems Laboratory of the NationalOceanic and Atmospheric Administration sponsored an evaluation of artificialintelligence-based systems that forecast severe convective storms. Theevaluation experiment, called Shootout-89, took place in Boulder, and focussedon storms over the northeastern Colorado foothills and plains (Moninger, etal., 1990). Six systems participated in Shootout-89. These included traditionalexpert systems, an analogy-based system, and a system developed using methodsfrom the cognitive science/judgment analysis tradition. Each day of theexercise, the systems generated 2 to 9 hour forecasts of the probabilities ofoccurrence of: non significant weather, significant weather, and severeweather, in each of four regions in northeastern Colorado. A verificationcoordinator working at the Denver Weather Service Forecast Office gatheredground-truth data from a network of observers. Systems were evaluated on thebasis of several measures of forecast skill, and on other metrics such astimeliness, ease of learning, and ease of use. Systems were generally easy tooperate, however the various systems required substantially different levels ofmeteorological expertise on the part of their users--reflecting the variousoperational environments for which the systems had been designed. Systemsvaried in their statistical behavior, but on this difficult forecast problem,the systems generally showed a skill approximately equal to that of persistenceforecasts and climatological (historical frequency) forecasts. The two systemsthat appeared best able to discriminate significant from non significantweather events were traditional expert systems. Both of these systems requiredthe operator to make relatively sophisticated meteorological judgments. We areunable, based on only one summer's worth of data, to determine the extent towhich the greater skill of the two systems was due to the content of theirknowledge bases, or to the subjective judgments of the operator. A follow-onexperiment, Shootout-91, is currently being planned. Interested potentialparticipants are encouraged to contact the author at the address above.

Shootout-89: A Comparative Evaluation of Knowledge-based Systems that Forecast Severe Weather