Gro Intelligence today released its third monthly estimates of global agricultural supply and demand, updating data ranging from South African corn and Argentine soybean yields to US and China soybean crush rates.
The March estimates are available on the Gro website, which can be accessed by signing up for a free Gro account. Follow the instructions here to learn how to find Gro’s estimates. Gro is releasing its forecasts ahead of the USDA’s issuing of its monthly World Agricultural Supply and Demand Estimates, or WASDE.
Gro has built one of the world’s largest agricultural data platforms. We use a variety of global sources to inform our estimates. SAGIS, a South African industry association, provided its first forecast for the current summer crop, for example, while government departments like Eurostat provided trade data that boosted estimates for European corn imports and wheat exports.
Among other Gro estimates, US soybean crush is up 17 million bushels from last month’s forecast, underlining continuing year-over-year gains. Evapotranspiration was drier than normal in Argentina, which led to a decline in the Gro yield model. Meanwhile, China soybean crush rates and imports have both been revised lower.
Gro uses five distinct methodologies to estimate supply and demand for 23 country/crop pairings.
One set of forecasts leverages Gro’s machine-learning-based yield and production forecast models, which update daily on a district level for in-season crops. These models have been extensively backtested for performance.
Another set of production forecasts, for which Gro does not yet have in-season daily yield models, uses an array of satellite-generated knowledge to assess the current weather’s impact on a crop.
A third set of forecasts relies on country-specific data sources that are available in Gro and that the USDA typically uses to generate WASDE estimates.
Our fourth set of forecasts only applies to crops that are between seasons and for which production estimates are unlikely to have changed significantly in recent weeks (growing seasons can be tracked using crop progress calendars available in Gro).
A last set of forecasts uses linear regression to model annual crop demand, based on the pace of higher frequency US demand statistics for the current marketing year. In addition, various non-US data sets that are available in Gro are used to gather new weekly and monthly data to better inform cumulative year-over-year comparisons with conservative assumptions about future progress.
In our latest analysis, we also determined which country/crop pairing estimates are most likely to be revised in the upcoming WASDE report and have the greatest impact on global agricultural markets. The analysis looked back over 11 years of WASDE reports to assess how many times data each country/crop pairing was revised between February and March in each year.
The table below highlights the historical tendency of adjustments to be made in the March WASDE for different country/crop pairings. The higher the ranking, the greater the likelihood a country/crop pairing changed in the past 11 years between February and March. In this report, the USDA usually adjusts production only for Southern Hemisphere countries, such as Argentina, Brazil, and Australia, who are currently in the middle of their growing season. Meanwhile, consumption figures tend to be more frequently revised, regardless of geography.