24
A knowledge-based system to generate internet weather forecasts. Dr Harvey Stern, Bureau of Meteorology, Australia

A knowledge-based system to generate internet weather forecasts

  • Upload
    aitana

  • View
    46

  • Download
    0

Embed Size (px)

DESCRIPTION

A knowledge-based system to generate internet weather forecasts. Dr Harvey Stern, Bureau of Meteorology, Australia. … a work in progress . Introduction. A “pilot” knowledge-based system for the generation of internet forecasts is described. The system has been developed for Victoria. - PowerPoint PPT Presentation

Citation preview

Page 1: A knowledge-based system to generate internet weather forecasts

A knowledge-based system to generate internet weather forecasts.

Dr Harvey Stern,Bureau of Meteorology, Australia

Page 2: A knowledge-based system to generate internet weather forecasts

… a work in progress ...

Page 3: A knowledge-based system to generate internet weather forecasts

IntroductionIntroduction

• A “pilot” knowledge-based system for the generation of internet forecasts is described.

• The system has been developed for Victoria.

• Forecasts generated include those for public, aviation, marine and media interests.

Page 4: A knowledge-based system to generate internet weather forecasts

Description of the System.Description of the System.

• At the core of the system is an algorithm, written in HTML (and incorporating some JavaScript).

• The algorithm combines statistical interpretation of NWP output with other knowledge.

• The statistical interpretation component includes identification of the synoptic type.

Page 5: A knowledge-based system to generate internet weather forecasts

Synoptic TypingSynoptic Typing

• The basis for the system is identification of the expected synoptic type.

• The direction, strength and curvature of the isobaric (surface) flow determine the type.

• These characteristics are determined from a grid of forecast pressure values.

Page 6: A knowledge-based system to generate internet weather forecasts

Generating the OutputGenerating the Output

• Data associated with the identified type are statistically analysed.

• In a Perfect Prog mode, statistical relationships so derived are used to generate forecasts.

• HTML Code (incorporating JavaScript) is generated.

• The Code is uploaded to a Web Site.

Page 7: A knowledge-based system to generate internet weather forecasts

Opening View.Opening View.

Page 8: A knowledge-based system to generate internet weather forecasts

Entering the DataEntering the Data

Page 9: A knowledge-based system to generate internet weather forecasts

Generating the Code.Generating the Code.

Page 10: A knowledge-based system to generate internet weather forecasts

The “Bank” of Experience• Ramage proposed an “iterative” approach to locking in

improvements in forecasting.

• This is, indeed, the approach adopted here.

• Thereby, the skill increases as new knowledge is incorporated.

• Hence, progress is made towards the realisation of Ramage’s dream.

Page 11: A knowledge-based system to generate internet weather forecasts

Multi-lingual FeatureMulti-lingual Feature

• An increasing component of the WEB is in languages other than English.

• Chinese may become the common language of the WEB.

• The system has a component that generates a forecast summary in Chinese.

Page 12: A knowledge-based system to generate internet weather forecasts

The Output GeneratedThe Output Generated

Page 13: A knowledge-based system to generate internet weather forecasts

Segment of the OutputSegment of the Output

Page 14: A knowledge-based system to generate internet weather forecasts

Sample of the Forecasts.Sample of the Forecasts.

Page 15: A knowledge-based system to generate internet weather forecasts

The Aviation Forecasts.The Aviation Forecasts.

Page 16: A knowledge-based system to generate internet weather forecasts

Verification of SystemVerification of System

• Five skill measures are used.

• These are MIN, MAX, QPF, Precip/No Precip (P/NP), & BRIER.

• Skill measures are positive for forecasts better than climatology.

Page 17: A knowledge-based system to generate internet weather forecasts

A Preliminary TrialA Preliminary Trial

• Conducted (last April) on an earlier (and much abbreviated) version of the system.

• Evaluation limited to one month, one location (Melbourne), and to day one.

Page 18: A knowledge-based system to generate internet weather forecasts

A Subsequent TrialA Subsequent Trial

• Conducted (last November).

• Evaluation extended to include days one to seven.

• Still only for one location.

Page 19: A knowledge-based system to generate internet weather forecasts

Combined Skill of Subsequent TrialCombined Skill of Subsequent Trial

Page 20: A knowledge-based system to generate internet weather forecasts

Skill of Subsequent Trial’sSkill of Subsequent Trial’sMin Temp ForecastsMin Temp Forecasts

Page 21: A knowledge-based system to generate internet weather forecasts

Skill of Subsequent Trial’sSkill of Subsequent Trial’sMax Temp ForecastsMax Temp Forecasts

Page 22: A knowledge-based system to generate internet weather forecasts

Skill of Subsequent Trial’sSkill of Subsequent Trial’sQuantitative Precipitation ForecastsQuantitative Precipitation Forecasts

Page 23: A knowledge-based system to generate internet weather forecasts

System PerformanceSystem Performance

• Skill Measures all show system forecasts better than climatology.

• They also are better than persistence.

• They are (on most measures) inferior to official forecasts, especially for days 1 and 2;

- with the notable exception of minimum temperature forecasts for days 3 to 7, inclusive.

• System forecasts would be expected to improve as new knowledge is incorporated.

Page 24: A knowledge-based system to generate internet weather forecasts

Future Plans

• Extensively verify the system, covering all current observing sites.

• Enhance the sophistication of the statistical analysis.

• Incorporate new forecaster knowledge.

• Extend the multi-lingual feature to Australian indigenous languages.