MIT Tech Review: Crystal Ball for Corn Crop Yields Will Revolutionize Commodity Trading.

November 13, 2017

Upward revisions from USDA on corn yield are in line with TellusLabs' outlook

Our coverage of the US growing season

At TellusLabs, our mission is to build live systems for environmental intelligence at a planetary scale. We seek fast-moving problems where a spaceborne perspective is decisive and stakes are high for markets and society. Behind the scenes, we rely on a powerful, multi-source framework for remote sensing analysis and a human-led approach to machine learning.


TellusLabs yield estimates for the 2017 season: The Kernel web app allows customers to access county-scale visualizations of yield.  Source: Kernel; TellusLabs.

For the past two years, we have monitored the US corn and soy growing seasons because we think they pose a difficult but crucial challenge. In 2016, we shared yield estimates daily with 600 beta participants. During that record-breaking harvest, our models  showed remarkable earliness and accuracy,  particularly for soy.

This year, a cohort of commercial users accessed our US corn and soy insights through  Kernel,  an immersive web app and API. The application covers the season every day, including yield estimates, weather, plant health, public data, and commentary. This week, we are sharing a recap of our 2017 results publicly, and we are opening up a  trial  of the product.

Corn in 2017

This year, we produced three models for US corn yield. The  TL 2017  model (green below) started the season at  166.2 bu/ac  (June 28th coverage). From July, we also produced  TL 2016  (blue below) – a model with same structure as the corn model we ran in 2016 (that predicted corn with 1% error), but trained on more recent data. Just prior to finishing model operations (October 3rd) we provided  TL 2017 Baseline  (purple below), which explored the impact of an alternative approach to long-term trend adjustment (in response to customer requests).  


TellusLabs corn yield estimates for 2017 season.  Brighter colors for each model indicate first date of introduction into Kernel; dotted orange line is USDA.  Source: Kernel; TellusLabs.

As is clear from the figure above, all three models underwent a steep increase of roughly 4 bu/ac over the course of August. Our preferred model,  TL 2017  (green) lagged our legacy  TL 2016  model (blue), but both arrived  above 175 bu/ac  by early September. They ended the season at an average of  178.4 bu/ac.

The figures above tell a consistent story: a very strong, potentially historic year for corn. Until Thursday (November 9th), neither the USDA nor the general market shared that view. Trade estimates (via Reuters) were in the 166-170 bu/ac range for all of August-October and the USDA’s own estimates (orange) ranged from 169.5 to 171.8 bu/ac over the same period.  

That USDA outlook changed sharply last week with the  November 9th Production Report,  which featured a revised forecast of  175.4 bu/ac.  The  market conversation  certainly reflects the surprise at this revision. We are pleased that our preferred corn models anticipated the historic strength of this harvest well ahead of both the government and market consensus (since late-August and early-September).

Soy in 2017

TellusLabs produced three models for US soy yield this year, in a similar framework to the corn models described above (in figure below,  TL 2017  is purple,  TL 2016  is blue, and  TL 2017 Baseline  is green). We opened the season with a soy outlook of  49.5 bu/ac  (June 28th coverage).  


TellusLabs soy yield estimates for 2017 season.  Brighter colors for each model indicate first date of introduction into Kernel; dotted orange line is USDA. Source: Kernel; TellusLabs.

We’ve seen a much wider range for soy this year than for corn (shaded area above). As was the case for corn, the  TL 2017 Baseline  variant was the low water mark for our estimates. For a good portion of the season, that  TL 2017 Baseline  model was the company outlook (meaning that we believed it had the strongest predictive potential of the three). By October, we concluded that conditions did not support such a conservative view on soy, partly thanks to the close agreement emerging between the  TL 2016  and  TL 2017  models (as with corn). Our final guidance to customers in October was for expectations on the upper end of the range we see above. We are not anticipating significant further movement for US soy this season.

What’s next for us?

The  Kernel  mission is to provide agricultural intelligence globally. As such, we’ll be building on the success of our Argentina soy beta last year and launching corn and soy forecast coverage for both Argentina and Brazil this season (December - June). By end of 2017, we will also be providing full imagery, weather and plant health metrics for the entire Southern Hemisphere (see below). By Spring 2018 that coverage will span the whole globe and include a new crop (wheat).


TellusLabs Kernel platform.  As we prepare for South America coverage, the team at TellusLabs is lighting up weather forecasts for the entire planet.  Source: NOAA-GFS; TellusLabs.

Join us!

We learned a great deal this season on every front: product, engineering, data science and commercial. All of those lessons are helping us deliver better insights to a growing  Kernel  community.

We urge you to join us as Kernel becomes more global, more immersive and more inclusive. Please  sign up here  for trial access – if you’ve read this far you deserve it!


About TellusLabs

TellusLabs is a Boston-based satellite imagery and machine learning company whose mission is to build live environmental intelligence systems at a planetary scale. In 2016 & 2017, our agricultural intelligence product,  Kernel,  anticipated US soy and corn yields ahead of the USDA. We've been featured in  MIT Tech Review  and  TechCrunch  and have been recognized as a MassChallenge  Diamond Award Winner,  FIA  Innovator of the Year  and Singularity University  Global Grand Challenge Winner.

Also in News

Happy Thanksgiving from TellusLabs
Happy Thanksgiving from TellusLabs

November 22, 2017

TellusLabs named 2017 FIA Innovator of the Year
TellusLabs named 2017 FIA Innovator of the Year

October 28, 2017

Last week, we attended the FIA's annual expo to share the work we're doing using satellite remote sensing and machine learning to drive value in agricultural commodities markets. At the end of the Expo, we were awarded the 2017 FIA Innovator of the Year award! It was a fantastic week overall and we're looking forward to continuing the awesome dialogue with the futures community.
Tina Cormier presentation at Harvard's ABCD-GIS
Tina Cormier presentation at Harvard's ABCD-GIS

October 20, 2017

On October 19, Tina Cormier, a Remote Sensing Scientist here at TellusLabs, presented to the ABCD-GIS working group at Harvard University. Her presentation explored vector GIS, raster processing, lidar data, and cartography with R, an open source software environment and programming language that is well-positioned to have an impact in the rapidly emerging field of geospatial data science.