Video wird geladen...
Video konnte nicht geladen werden
.Google DeepMind is powering a new agricultural landscape understanding layer in Google Earth for portions of the Asia-Pacific region to bring powerful data to our iconic imagery. Leveraging machine learning and satellite imagery, this data layer is able to visualize the ""atomic units"" of agriculture: individual field boundaries. This... show more
231,640 Aufrufe • vor 8 Monaten •via X (Twitter)
22 Kommentare

@GoogleDeepMind You could put a solar yield sim on top. Simulating average or point in time solar irradiance. Seasonal and daily light distribution mapping is key for crop planing and yield. As this varies through a solar cycle, you can also plan crop and soil rest cycles, or grazing rotation.

@GoogleDeepMind I've used it and it's amazing 🤩

@GoogleDeepMind that land cover segmentation must be seriously complex

@GoogleDeepMind @googleearth & @GoogleDeepMind, this initiative is mind-blowing! Utilising AI to improve agricultural insights will empower farmers and improve resource management. I'm really excited to see the impact it will have in the region.

@GoogleDeepMind Defining agriculture in “atomic units” feels like the right abstraction for applying AI to real land management. This is where geospatial ML starts becoming infrastructure, not just visualization.

@GoogleDeepMind Been putting code and AI into the insights of the family farm productions. My mom has rain precipitation, production, prices and other data points for the last 7 years of production.

@GoogleDeepMind Why just Asia-pacific? Can’t we have this everywhere?

@GoogleDeepMind Good progress. What’s next?

@GoogleDeepMind Does it also integrated with local weather forecast? Like rainy days?

@GoogleDeepMind google earth is build with flutter, right?

@GoogleDeepMind @grok これは耕作、維持管理を判別できる?

@GoogleDeepMind All satellite image process: training site, groundtruething, image classification, etc should be

@GoogleDeepMind @yohaniddawela

@GoogleDeepMind Modeling agricultural landscapes from satellite imagery is harder than people think. You get radiance, clouds, seasonal artifacts, and messy ground truth. The real progress is in harmonizing temporal sequences into actionable, high-granularity crop maps.

@GoogleDeepMind 🚀

@GoogleDeepMind Brutal !

@GoogleDeepMind It has been two years almost and my area image isn’t updated, is this intended?

@GoogleDeepMind Oh

@GoogleDeepMind to provide real-time insights on crop health and land use

@GoogleDeepMind curious how this will impact crop yield predictions and resource allocation in the region

@GoogleDeepMind Refinement! 👌

@GoogleDeepMind flustered
