How advanced analytics pulls insights from the weather, part 2
The forces of nature can be unpredictable. But as noted in the first blog post in this series, businesses and organizations can pull substantial value our of weather data through advanced analytics, machine learning and AI.
In my last post, I drilled into the industries and organizations that consume weather-related data intelligence. In this post, I’ll look at who is creating and gathering all of this valuable, actionable data surrounding weather.
Here are five key examples:
- The Weather Company provides an API that helps companies ingest a continuous stream of data about weather that includes precipitation, temperature, currents, clouds, rain, snow, ice, heat, storms and potential hazardous conditions. All of this data is available for all ZIP codes and latitudes/longitudes. Applying machine learning models to this data and applying AI algorithms, businesses can provide detailed recommendations needed for use by farmers, airlines, real-estate companies or the energy industry.
- NASA generates space-based forecasts, photos, videos, temperatures and other important outer environment data gathered using sensors across the devices in the space. The data streams are sent to the base stations and the data is available to all. The integration is done using an API that uses geographical information which can be useful when integrating all data into machine-learning ecosystems.
- Farmers aren’t just consumers of weather data. They are making use of sensors on the field and across the entire farming process, from transportation through retail. Data generated by sensors or agricultural drones collected at farms, on the field or during transportation offer a wealth of information about soil, seeds, livestock, crops, costs and farm equipment, as well as the use of water and fertilizer.
- Scientists generate data from algorithms that can be used to feed models in a machine-learning ecosystem. These data sets are very structured and highly complex in nature. Feeding them into more complex ecosystems requires complete understanding of the data to which these datasets will be integrated.
- Researchers have been publishing findings and recommendations that today can be harnessed into digital formats. These findings provide several layers of machine learning models and algorithms. When integrated and harnessed, this data can enable even more insights and enable behavioral analysis of how sensors might react in any given situation, what intelligence should be applied to derive the outcomes needed or what margins of error are acceptable in the world of digital information platform.
These are not just a dream. We are talking about the reality of today and the world of future. This is a place like what we have seen in the movies: a world where data is the driver and analytics are the key. This world will need more compute and more automation.
I see a world where we will live differently, think differently and survive differently.
Interested in learning more about IBM analytics, and how industries are making better data-driven decisions on the road to AI? Read more in our interactive guide to hybrid data management.
This article is offered for publication in association with the Big Data Seminar 2018 NYCity, 25 - 26 October, 2018 in New York City at Hotel Pennsylvania, 401 7th Avenue, New York, N.Y., sponsored by Data Management Forum. Additional information is available in the Big Data Seminar flyer. For additional information please call (516) 221-5560 or email here.