Within agricultural businesses, the ability to accurately predict the yield of a crop each year is critical for enhancing the efficiency, profitability, and sustainability of that business. The earlier the yield can be predicted, the more efficiently that resources can be allocated, supply chain managed, the harvest scheduled, and the storage logistics of the business be determined. 

A current challenge in the sugar beet industry is climate change, which is causing increased variability of yields from year to year. The rapidly changing weather conditions make yield estimation less predictable and ultimately increases costs to all stakeholders.

Harnessing the power of data analytics and machine learning is one way to improve the accuracy and timeliness of yield predictions. A predictive model was built in JMP to predict sugar beet yields. The whole process was possible in JMP alone: data collection, cleaning, preprocessing, exploratory data analysis, feature engineering, model selection, training, evaluation, tuning, and subsequent deployment and maintenance.