Researchers from DEMETER, Morteza Abdipourchenarestansofla of John Deere and Christof Schroth of Fraunhofer IESE have a new publication titled ‘The importance of data quality assessment for machinery data in the field of agriculture”. The pilot study in DEMETER ‘In-Service Monitoring of Agricultural Machinery” is used to investigate data quality issues for machinery data. This use case develops a job cost
calculation system which aims to support the farmer by automating cost calculation associated to a given field operation. This technology, its reliability and accuracy, requires high-quality data that avoids misleading results. The system leverages telematics machinery data with the scope of fertilizer and chemical applicators in small grain. The chemical and fertilizer applications take place several times during the season.
The paper appears in VDI-Berichte and the abstract is as follows:
In the field of agriculture, particularly in the horizon of farming 4.0, more and more smart sensors are being used and telematics brought lots of machinery data production in agricultural. The data obtained can help the farmer with optimization or decision support by means of Artificial Intelligence. In the horizon 2020 DEMETER project, we develop a job cost system which aims to enable calculating site-specific costs for fertilization and plant protection applications. Telematics machinery data are leveraged for developing the system. As such field operation data are complex and contaminated by various sources of measurement and documentation errors, it is crucial to have an appropriate Data Quality approach which can reveal issues in such data. In this work we present concrete quality challenges in geospatial machinery sensor data and their metadata documentation, and how we check them based on ISO 25012 and ISO25024 standards via an automated data quality assessment service.
Download the full paper here
