Every few weeks, gMail has stopped auto-completing addresses as I type them into the “To:” box. Rebooting Chrome does doesn’t help. Rebooting my MacBook Pro doesn’t help. Clearing my cache doesn’t help.

The obvious remedy of typing people’s addresses manually requires that I remember their addresses. That  has only gotten less plausible as I’ve aged. Just ask our cat Smokey. No, wait, it’s Pearl. Hold on, I think it has something to do with being an outlaw. Smokey? No. Capone? We wouldn’t have named a cat “Dahmer”, would we? Oh, wait, it begins with an S! Sam Bankman-Fried? Smokey?  Oh, I remember! We don’t have a cat.

I hope you enjoyed that dramatic pre-enactment of what’s in store for you.

In any case, the solution I have stumbled upon is to turn off Chrome extensions one by one, test gMail’s autocomplete, turn the extension back on, and then turn off the next one. In short, do the first thing any “how to” that actually knows anything would have suggested, to who which I reply: D’oh!

Oddly, a different extension has been the culprit each time. But, in truth, isn’t the real culprit all of us? Or possibly Google. Nah, it’s gotta be all of us.

BTW, has anyone seen Dahmer, that fluffy little furball!

Be the first to comment »

My prompt

If you were going to train a model to predict rain showers, what data might you use that is currently not being widely used?

ChaptGPT 4o

Many advanced weather models incorporate a variety of data sources, but some of the more innovative and less traditional data types mentioned are not commonly used in current weather prediction models. Here are some of the data types from the previous list that are typically underutilized or not used at all:

Environmental and Geographical Data

1. Soil Moisture Levels:
   • While some models use soil moisture data, it is not as widely incorporated or detailed as it could be.
2. Vegetation and Land Cover Data:
   • Detailed vegetation and land cover data are often not integrated into weather prediction models at the level of granularity that might be beneficial.
3. Surface Roughness:
   • Data on surface roughness is generally underutilized in most weather prediction models.

Atmospheric Data

1. Aerosol Concentrations:
   • Detailed aerosol concentration data, particularly on a fine scale, is not commonly used in many weather prediction models.
2. Atmospheric Composition:
   • Comprehensive data on various gases beyond the primary greenhouse gases (like ozone and carbon dioxide) are generally not integrated into weather prediction models.
3. Cloud Microphysics:
   • Detailed cloud microphysics data, such as cloud droplet size distributions and ice crystal concentrations, are typically underutilized.

Human and Technological Data

1. Pollution Levels:
   • Pollution data, including detailed air quality indices, are not commonly used in weather prediction models.
2. Traffic and Transportation Data:
   • Vehicle emissions and heat data from traffic and transportation are rarely used in current models.

Temporal and Historical Data

1. Real-time Social Media and Crowd-sourced Data:
   • While there are some experimental uses, real-time social media and crowd-sourced weather observations are not widely used in standard weather models.

Biological and Ecological Data

1. Plant Phenology:
   • Data on plant life cycles and their impact on local humidity and temperature are generally not used in weather prediction models.
2. Animal Movement Patterns:
   • Animal behavior in response to atmospheric conditions is not utilized in current weather models.

Advanced Technological Data

1. LiDAR Data:
   • While LiDAR is used in some atmospheric research, it is not commonly integrated into standard weather prediction models.

Integration of Multidisciplinary Data

1. Health and Epidemiological Data:
   • Data on health conditions correlated with atmospheric changes are generally not used in weather prediction models.
2. Economic Activity Data:
   • Information on industrial activity and energy consumption is typically not integrated into weather prediction models.

Summary

To improve weather prediction, especially for phenomena like rain showers, integrating these underutilized data sources could provide a more comprehensive and accurate understanding of atmospheric processes. Leveraging innovative data sources such as aerosol concentrations, detailed cloud microphysics, and real-time social media observations could enhance the predictive power of weather models.

Be the first to comment »