search.noResults

search.searching

dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
The saying “garbage in, garbage out” certainly applies to big data.


When bad data is used as the basis for decision-making, the resulting changes in practice can have devastating and costly effects. Instead, when collecting data, it is important to ask about and verify the accuracy of the measurements.


The best way to determine whether or not measurements are accurate is by comparing data to alternate data sources. For example, if flow is recorded at a flume, the data can be cross-checked with flow measured using a doppler. Cross-checking data is time-consuming and can be costly; however, it can give invaluable insight into data quality. When it is not possible to cross-check data, it should at the very least be analyzed to make sure it makes sense.


Managing expectations


Once data has been analyzed to help make decisions, results may differ from expectations. It is important to build trust in the results, as trust leads to new and better practices over historic approaches based on flawed or outdated information. This may seem paradoxical, as it was just mentioned that data should be questioned and not assumed to be correct.


A combination of both trusting and questioning data is a good practice. When results vary from expectations, recheck the data and analysis to determine if there are errors or inaccuracies. When unexpected


results persist, consider that the results can certainly be correct.


By considering what data needs to be collected and creating a data collection plan that considers frequency and quality control, big data can be an asset and improve decision-making. The goal of using big data should be to positively impact hurdles that farms are facing today, whether it be improved operational efficiency, management visibility or improved farm profitability.


Astrid Vreugdenhil is a data scientist at SWIIM System Ltd.


By considering what data needs to be collected and creating a data collection plan that considers frequency and quality control, big data can be an asset and improve decision-making.


Configuring a data logger


and telemetry unit Photo credit: SWIIM System Ltd.


26 Irrigation TODAY | April 2019 Maintaining a flow meter at an irrigation district gate Photo credit: SWIIM System Ltd.


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