Quantcast
Last updated on April 19, 2014 at 9:20 EDT

EarthRisk Technologies Announces First Fully Operational “Genetic Algorithm” for Long-Range Commercial Weather Forecasts

October 10, 2012

SAN DIEGO, Oct. 10, 2012 /PRNewswire/ — EarthRisk Technologies, a pioneer in the research, analysis and visualization of extreme temperature and weather pattern risks, released today TempRisk 4.0, an important update of the company’s flagship platform used for detecting both hot and cold weather patterns up to 40 days before they occur.

The core improvement for TempRisk 4.0 is the introduction of the new comprehensive empirical forecast model which optimizes forecast signals through the usage of a genetic algorithm. This algorithm works by producing educated guesses to the solution of a problem, keeping good solutions and removing bad ones, effectively creating a “survival of the fittest” method of optimization.

Genetic algorithms are increasingly used to plan efficient routes and scheduling for travel planners, traffic routers and shipping companies. Automotive design companies use genetic algorithms to determine materials and shapes for faster, lighter, fuel-efficient vehicles. And the telecommunications industry developed genetic algorithms to optimize placement of routing cell towers for best coverage.

“By using genetic algorithms with our empirical forecast model, TempRisk is now able to present more accurate forecasts by finding best possible combinations of precursor weather patterns and subsequent extreme temperature events,” says EarthRisk CEO John Plavan. “It significantly increases forecast skill and reduces false alarms by intelligently identifying and removing redundant synoptic precursor signals. We also redesigned the TempRisk Almanac, TempRisk Indices, Dashboard, and Forecast Scorecard to give our commercial clients a more powerful and user friendly forecasting tool.”

  • New comprehensive empirical forecast model uses genetic algorithm to better capture non-linear atmosphere events
  • New TempRisk Almanac with an advanced search option that allows the viewing of synoptic patterns by region, season, lead window, and initialization date. Users have enhanced visibility into the traditional signal maps and information to view patterns over certain time frames
  • Redesigned TempRisk Indices offers increased usability with multiple overlays to view multiple regions and HeatRisk and ColdRisk data on the same chart
  • TempRisk Dashboard features visual bars to represent heat and cold probabilities over the full range of lead times. Includes regional forecast chart alerts sent to customers daily.
  • Completely revised TempRisk Forecast Scorecard with ability to view HeatRisk and ColdRisk events on the same page

TempRisk provides the information necessary to extend forecast confidence beyond one week, the point where weather simulations face deteriorating skill. The platform’s patent-pending algorithms run four million calculations a day, incorporating 200 weather patterns, 10,000 days and multiple global regions. The result: quantified weather risk.

TempRisk version 4.0 is based on the software-as-a-service (SaaS) subscription model and is available now.

About EarthRisk Technologies:
EarthRisk Technologies is a San Diego-based software company founded in 2010. The company’s product suite, TempRisk, is a web-based platform that crunches more than 60 years of weather data to formulate the odds of cold snaps and heat waves up to 40 days in advance, a lead-time that is twice as long as any in the industry. Trading groups, power producers and energy traders around the globe use TempRisk for a climatological edge in their investments. For more information, visit www.earthrisktech.com

SOURCE EarthRisk Technologies


Source: PR Newswire