Irrigation Data: On-Farm Insights from Geospatial Analysis

As an Agribusiness, you understand just how important an effective irrigation system is to a farm’s success. Across the United States, farmers use different systems of irrigation for different fields. And to fully understand their operational needs, you need to better understand their irrigation system.

DTN supports your agribusiness with our irrigation data that provides deeper insights for better understanding and serving your farmer customers.

For decades, people have used remote sensing to evaluate irrigated areas. We take that a step further to both identify and classify farmers’ irrigation systems on a field-by-field basis. Learn more about how we conduct this analysis to provide you with better insights into the farmers you serve.

How the Process Works

We build our irrigation data using remote sensing and maps to place land into four irrigation categories:

Pivot irrigation
Non-pivot sprinkler
Other irrigation (flood, micro, etc.)
Non-irrigated

For our purposes, irrigated land is defined as cultivated crop locations receiving application of water means to offset precipitation shortfalls during the growing season. This definition includes water sources like surface and groundwater deliveries — as long as human intervention is involved in moving the water.

Determining irrigation criteria relies on several measures. First and foremost is the availability of water resources and their interaction with vegetation. We also include climate, resource availability, crop patterns, and technical expertise in our data collection.

The graphic below explains exactly how all this data fits together in the analysis:

The model relies heavily on monitoring changes in vegetation indices throughout the growing season. We specifically analyze this data during periods of rain and dryness.

It’s crucial that the timing of the image capture be precise. Precise timing helps to distinguish irrigated crops from each other and other land cover types.

This analysis helps detect vegetation activity over time through spectral (color) and temporal data. Spectral data examines vegetative growth, while temporal data helps us determine the rate of growth.

Identifying irrigated vs. non-irrigated fields

Our irrigation data model leverages a set of known data (referred to as a training data set) and sends it through a predictive model. Based on that training data, the model was able to determine and weigh key factors that indicate the irrigation status of a particular field.

Here are some things we have learned using that process:

In general, irrigated fields have higher vegetation index values than non-irrigated fields
Most irrigated fields have a low year-to-year variation in vegetation index due to climate dampening

We used a tree-based machine learning model — one widely used by the machine learning community — to separate irrigated from non-irrigated land.

In addition to classifying land by irrigation type, the model returned a confidence interval for each classification. Of course, as with any predictive model, it’s essential to test and refine the model to enhance its accuracy. In this case, the result is a cleaner and more accurate final irrigation map.

Finally, we evaluate the results and test them for accuracy in two ways:

By using ground-truth observations to create a statistical estimate of the map’s accuracy; and
By comparing area estimates made from the irrigation map with those reported by the USDA at the county level.

With the confidence that our data is accurate, we use this data in our applications to provide better insights to empower our clients. To learn more about how to access this data, contact our team here.