Gro’s 2023 Performance Report Shows Accurate Prediction Months in Advance of Final Reporting

2023 was a year of significant disruption in the global food supply chain, with extreme weather volatility and growing geo-political conflicts in critical crop growing and transit regions adding to already heightened global food price inflation.  With the need to navigate these risks, accurate and timely crop yield and acreage forecasts are more valuable than ever. 

Gro’s highly accurate Global Yield Forecast and Acreage Models offer a holistic view of global food supply up to 10 months in advance of final government reporting. These models are a key indicator for supply, prices, and farmer profitability and can be used to make decisions around product pricing, sourcing, trading, or policymaking.

Gro’s 2023 Models Accurately Predicted Yields Up To 10 Months Before Final Government Reporting

In our 2023 Report, we focus on the performance of our Global Yield Forecast Models across corn, soy, and wheat, as well as our US Planting Intentions Model and US Prevent Plant Model for corn, soy, wheat, and cotton. 

Gro’s suite of machine learning-based models includes 14 country/crop pairings that cover over 70% of global production for corn and soy, and 50% of the global production of wheat. Gro’s models also provide an unprecedented combination of accuracy, global coverage, and granularity down to the district level, with daily in-season updates. 

This is the only report currently available in the market that compares model performance against ground truth data in a comprehensive, transparent way. Our analysis shows that Gro’s models accurately predicted yields and planted acreage, averaging within 92%-99% of final government reporting up to 10 months in advance. 

Key takeaways of our 2023 report include:

• Despite a highly unusual year of extreme weather, Gro’s models provided an earlier view of final numbers, allowing customers to move ahead of the market. 
• Historically, for the past eight years, Gro’s US Corn Yield Forecast Model has been on average within 98% of the USDA final January report by October (i.e., three months in advance). Our US Soybean Yield Forecast Model has been on average within 99% of the USDA’s final number by October (i.e., three months in advance) for the last six years.

During the 2023 growing season, Gro’s US Soybean Yield Forecast Model was predicting lower yields starting in June due to significant drought conditions, providing early insight into lower-than-expected production and potentially lower exports, with the USDA eventually following this downward trend. Heavy rainfall in July, ahead of the critical growing period for soybean production, elevated the forecast until a period of relatively hot and dry conditions in September. Gro’s model ended within 0.4% of USDA final January reporting. 

• For the two major soybean exporting countries, the US and Brazil, Gro’s predictive yield models were 99.6% and 98.1% accurate for 2023, respectively.  
• In critical global regions, where the current marketplace does not have many machine learning-based predictive models, such as Ukraine, Brazil, and China, Gro’s 2023 Global Yield Forecast Models were on average 96% accurate up to 10 months ahead of final government reporting. 

Human Intelligence, Scaled by Artificial Intelligence

Gro Intelligence stands at the forefront of innovation in AI-driven data and analytics across climate, agriculture, and the economy. Gro empowers businesses, financial institutions, and governments to make better decisions on food security and climate risk.

With an extensive repository of 3.5 million unique, proprietary data series, Gro addresses a wide range of questions across crop yield and production, supply and demand, growing conditions, and climate scenarios.  Gro’s data series are curated and built by our team of domain experts, scaled through artificial intelligence, and commercialized as user-friendly predictive models and real-time applications. Our products provide accurate forecasts and holistic views of the most pressing climate and weather-related impacts across global food supply chains. 

Contact our team for a demo or to learn more about our predictive models here.

Download the full 2023 performance report here.