Gro Yield Model Forum

Welcome to Gro’s Yield Model Forum! Please feel free to post any comments, feedback, or questions here. Note that you can opt to receive email notifications to stay updated on the threads you comment by going into your user settings.

Check out our yield model page to learn more about the model and download our paper: https://gro-intelligence.com/yield-model

An open forum to foster engaging and interactive discussions about Gro's yield forecast model.

(thinking…)

Enter your idea and we'll search to see if someone has already suggested it.

If a similar idea already exists, you can support and comment on it.

If it doesn't exist, you can post your idea so others can support it.

Enter your idea and we'll search to see if someone has already suggested it.

  1. Historical data

    Do you have historical yield prediction data ranging back so far that there are enough data points to include in another machine learning model?

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  2. 1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  3. 2 votes
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →

    Hi Eric, thanks for your question!
    April is already close to harvest, so crops are either mature or at the end of grain-filling. The water demand of crops should be low if not zero, but too much rain may hurt or delay harvesting.
    Additionally, no weather variables post-March showed up as significant variables to yield in the Gro Argentine soy model.

  4. US Yield Model - late season changes

    I just listened to the webinar from yesterday, and have a question on the US corn yield model. You mentioned that the last change was in late December, but by that time the crop was already harvested. What changed at that point in the season that caused for a change to your yield estimates?

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    2 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →

    Hi Mike, thanks for your question.

    The major reasons for yield forecasting changes post-season:
    1. Our US corn yield forecast is aggregated up from sub-national level forecasts. Yields from US corn belt counties are from the Gro yield model, yields from US non corn belt states are from USDA NASS. Last year our corn belt yield forecasts changed slightly after October. The major changes came from USDA’s forecasts out of corn belt states, although weighted only less than 20% of the national yield aggregation.
    2. Usually after the growing season, our county level yield forecasts do not change, unless we added/backfilled new features that were fully tested for increasing our model’s performance, which was the case of precipitation from TRMM last year for US corn model.

  5. Today's yield update

    Hi, I see you updated your US yield today in light of USDA's huge number, but you have the date as "7 November (latest)". Shouldn't this be 9 November? You were showing 172.6 earlier today.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    4 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →

    Hi Josh,

    Thank you for your comment. Our US corn yield is updated daily on our platform. The website is reflecting our November 7th number with a slight delay. You’ll be able to access our November 9th yield forecast on our data platform, Gro.

  6. Argentine Soy model

    Hi, looking forward to seeing your Argentine soy yield model forecasts. Do you have any data on its historical track record?
    Thanks!

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  7. Do you have any data about GMO corn vs. Non-GMO corn?

    Can you separate corn yields by GMO and Non-GMO corn?

    2 votes
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    3 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  8. Historical Track Record vs USDA

    Do you have available somewhere or could you share a table of your model forecasts around the time of historical USDA forecasts? It would be helpful to see that.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  9. Weekly Commentary - October 13, 2017

    The Gro Intelligence US corn yield model estimate has dropped slightly again from 172.7 bu/ac (or 10.84 t/ha) to 172.6 bu/ac (or 10.83 t/ha). USDA validated the model’s bearish tendency in yesterday’s WASDE. Knowing our model as we do, we don’t expect any further significant changes in our estimate. Therefore, we will end this series of comments for 2017, barring an unexpectedly large change in the model estimate or some other notable event.

    Thank you for your interest in Gro’s US corn yield model. The estimate will continue to update daily on our data platform. Subscribers currently have access to…

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  10. Weekly Commentary - October 4, 2017

    The Gro Intelligence US corn yield model estimate has fallen slightly for the second week in a row, from 172.9 bu/ac (or 10.85 t/ha) to 172.7 bu/ac (or 10.84 t/ha). The model is likely to be stabilizing near its final value for the year, since satellite greenness indicators have peaked and harvest is well under way. Our estimate remains significantly higher than USDA’s and the general trade consensus. The model is therefore bearish on prices, expecting another increase in USDA’s yield at the 12 October World Agricultural Supply/Demand Report (WASDE). While our model will continue to update on our subscription-based…

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  11. 1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Questions  ·  Flag idea as inappropriate…  ·  Admin →
  12. Weekly Commentary - September 25, 2017

    For the first time in nine weeks, the Gro US corn yield model’s estimated value has fallen slightly, from 173.0 bu/ac (or 10.86 tonnes/hectare) to 172.9 bu/ac (or 10.85). The change occurred due to similarly small changes in satellite greenness indications. This is effectively an unchanged result. Accordingly, our view remains bearish on corn prices, calling for a yield higher than either the USDA, the general trade consensus, or the long term trend.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  13. Weekly Commentary - September 20, 2017

    Gro’s US corn yield model has risen yet again, for the eighth consecutive week, to 173.0 bushels/acre (or 10.86 tonnes/hectare) from 172.0 (or 10.80). The main drivers again are satellite greenness indicators and crop condition scores. Other states are making up for increasing dryness in Iowa, as shown in the map of evapotranspiration (below). Somewhat uncomfortably, Gro has become an outlier on the bearish side at this point. It should be acknowledged, however, that our non-consensus bearish view before the September WASDE was correct.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  14. Weekly Commentary - September 12, 2017

    The USDA has come out with its September WASDE report, and it has raised its US corn yield estimate from 169.5 bushels/acre to 169.9. This flew in the face of an average trade expectation of 168.2, but moved USDA closer to Gro’s 172 bushels/acre. Traders who acted on the Gro model’s bearish estimate before the report are enjoying favorable price action today.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  15. Weekly Commentary - September 9, 2017

    Gro’s US corn yield model moved higher for the seventh consecutive time over the past week, moving from 170.6 bushels/acre (or 10.71 tonnes/hectare) to 172.0 (or 10.80). Gro’s forecast is solidly bigger than USDA’s and above consensus trend yield. Satellite greenness indicators have passed their seasonal peaks in most of the Corn Belt. As a result, crop condition scores have become more important factors in the model. Increases in good-to-excellent ratings in Iowa and Illinois outweighed deterioration elsewhere. Gro’s model remains on the price-bearish side of the market going into tomorrow’s USDA Supply/Demand report.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  16. Weekly Commentary - August 18, 2017

    Gro’s US corn yield model continues to edge higher as the price of corn moves lower. Our latest estimate has come in at 167.5 bushels/acre (or 10.51 tonnes/hectare), up from the 166.8 (or 10.47) issued prior to the USDA’s WASDE report, which was at 169.5 (or 10.64). Improving satellite vegetation greenness images (NDVI) and improving crop condition scores have driven our estimate’s consecutive increases.

    Gro’s chief yield modeler will be working as a crop scout for the Farm Journal Eastern Midwest Crop Tour next week. For updates from the fields, please post questions related to the Tour here in the…

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    3 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  17. Weekly Commentary - September 1, 2017

    Gro’s US corn yield model jumped significantly higher over the past week, rising from 169.9 bushels/acre (or 10.66 tonnes/hectare) to 170.6 (or 10.71). Now Gro’s forecast is solidly bigger than USDA’s and above consensus trend yield. The price-bearishness of the model has again been driven by satellite data showing greening in the Corn Belt. Unlike last week, which featured improvement in areas which had performed poorly so far, these were scattered around the Corn Belt.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  18. Weekly Commentary - August 25, 2017

    Gro’s US corn yield model jumped significantly higher over the past week, rising from 167.5 bushels/acre (or 10.51 tonnes/hectare) to 169.9 (or 10.66). For the first time this season, Gro’s forecast is bigger than USDA’s and near the trend. Most of the credit for the improvement goes to satellite data showing rapid greening of the South Dakota crop, which previously had provoked concern due to its poor condition.

    This development coincides with Gro’s yield modeler’s participation in the 2017 Farm Journal Midwest Crop Tour. The Tour samples crops between Ohio and Minnesota on the eastern leg and between South Dakota…

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  19. Weekly Commentary - August 11, 2017

    Yesterday, the USDA released its August estimate for US corn yield at 169.5 bushels/acre, down 1.2 bushels/acre from the earlier estimate of 170.7. With market expectations near 166, and Gro’s model at 166.8, this number was indisputably bearish. Corn futures prices reacted by dropping 4% in short order. From this new lower price level, Gro’s model remains bullish, currently calling for a further 2.7 bushels/acre decline before harvest.

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
  20. Weekly Commentary - August 9, 2017

    Gro’s US corn yield forecast stands at 166.80 bushels/acre (or 10.47 tonnes/hectare), up from 164.33 (or 10.31) last week and just in time for the important August 10th USDA report tomorrow. The increase in our forecast was mainly driven by signals indicating stronger crop health across the US Corn Belt.

    Our model’s increase flies in the face of declining condition averages, and probably means that our yield estimate is now higher than trade opinion for the first time this year. We believe that the majority of corn market participants use a simple linear method for estimating yield using the percent…

    1 vote
    Sign in
    (thinking…)
    Password icon
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Gro's Weekly Commentary  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1 3
  • Don't see your idea?

Gro Yield Model Forum

Feedback and Knowledge Base