Moonshots, Models, IoT and Machine Learning in Agriculture
What do Google, Climate Corporation, early stage startups in farm robotics, and researchers trying to figure out how to feed the world sustainably have in common? They’re all grappling with one of the toughest challenges of working with natural systems - how do you work with data that is sparse, unevenly distributed and with systems that have so many connections and interactions with other systems?
Before the advent of cheap sensors that are connected to phones, easily accessible satellite data and drones that can fly over fields quickly and inexpensively - scientists in companies and academia worked on developing plant and crop models that incorporated as many aspects of the farm and as much data as was available so that they could understand and predict what was likely to happen on the field. Understandably, the forecasts took some time to produce and as the models grew more complex, issues about how to estimate model parameters and the uncertainty associated with the results became critical issues.
Now, of course - it sometimes seems like there’s too much data floating around! That’s certainly true with data associated with websites and other internet services - but it still isn’t necessarily true for data in agriculture or other clean technology sectors. There’s more data for sure - but we still need to figure out how useful they are and how best to compensate for errors and gaps in the data. And so, startups, companies like Google, large agricultural companies like Trimble, Bayer and BASF and researchers are trying to do this by combining different datasets, developing new indices and parameters to monitor, integrating all this with crop models and adding on with machine learning to make it all faster and more effective.
In fact, if you look at any of the job postings in the field, you’ll see that the companies are either building up teams with people having different expertise, or looking for people who have a systems view and can understand all these different aspects of the farm sector and build useful applications.
If you’re curious about the state of agricultural data, popular crop models, how machine learning can be used and the challenges associated with building these applications, come and join us this Sunday, October 25th at 11am -12.30 pm Pacific Time where we’ll work through these concepts and more using a hands-on problem where we’ll predict crop yields.