ig data has the potential to be an invaluable tool for agriculture. It holds promise to help farmers make smarter decisions for

a broad range of activities including increasing irrigation efficiency, maximizing yield and improving profitability.

When using big data to make decisions in agriculture, it can be difficult to determine exactly what data is needed, how to collect it and how to use it to meet your specific needs. When done incorrectly, integrating big data can be overwhelming, daunting and costly, but done the right way, it can be a smart investment.

Is more better?

Often when the term big data is used, there is the notion that more data is better. However, that assumption deserves careful consideration. Collecting and analyzing data can be expensive. In addition, too much data without good systems to manage it may become overwhelming.

It is often wiser to first identify specific problems you are trying to solve. For example, if the goal is to improve irrigation efficiency, multiple data sources such as imagery, weather data, water deliveries, soil moisture content and infiltration rates can all be used to develop tools that lead to better practices, which make improving irrigation efficiency a reality.

However, initially capturing every possible source of data might be unrealistic and may not be necessary. Instead, determine which data is most essential in improving efficiency and begin by measuring this data. When changing irrigation practices, water deliveries should be measured to determine if the new practices provide measurable improvements.

If a water budget approach is desirable to help drive irrigation efficiency, weather and evapotranspiration data might be most important to collect. Over time, further improvements to the water budget can be made to increase efficiency using other data sources such as soil moisture content or ET derived from satellite imagery. Agricultural data is a long-term investment, and knowledge increases as you collect data over multiple seasons.

Find the right frequency

After deciding what data will be collected, the frequency at which data is collected needs consideration. For example, if flow is measured only once during an irrigation, variations in flow during the irrigation will be missed, which can result in inaccurate water delivery volumes.

On the other hand, if flow is measured frequently, such as one-second intervals, flow fluctuations will be captured in detail. However, collecting data at one- second intervals results in large data sets that are expensive to collect and difficult to manage. In addition, a one-second measurement interval may not provide a significant improvement when compared to data taken at a lower frequency such as 15-minute intervals. Lower frequencies will still provide an accurate record of flow while significantly reducing data volumes.

Is the data accurate?

There is often an assumption that once equipment is installed, data collection can begin and there is no need to inspect the data. If the data is found to be inaccurate, some might think that taking more data will average into good data. In reality, more bad data just results in even more bad data and lack of trust in the outcomes.

Agricultural data is a long-term investment, and knowledge increases as you collect data over multiple seasons. 25

Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40