1. Accounting for data sparsity when forming spatially coherent zones
- Author
-
Andrew P. Whitmore, Alice E. Milne, and Kirsty L. Hassall
- Subjects
Precision agriculture ,Crop yields ,Computer science ,Applied Mathematics ,02 engineering and technology ,computer.software_genre ,01 natural sciences ,Data type ,Article ,Set (abstract data type) ,Identification (information) ,Spatial coherence ,020303 mechanical engineering & transports ,Cluster analysis ,0203 mechanical engineering ,Data sparsity ,Modeling and Simulation ,0103 physical sciences ,Data mining ,010301 acoustics ,computer - Abstract
Highlights • There exist three distinct types of data sparsity that inhibit the formation of spatially coherent zones. • By defining a neighbourhood of points through the Voronoi partition, the effects of spatial sparsity can be avoided. • Observed data points are often not co-located, resulting in big data losses through current methods. • By implementing missing data approaches within the clustering algorithms, data loss can be mitigated., Efficient farm management can be aided by the identification of zones in the landscape. These zones can be informed from different measured variables by ensuring a sense of spatial coherence. Forming spatially coherent zones is an established method in the literature, but has been found to perform poorly when data are sparse. In this paper, we describe the different types of data sparsity and investigate how this impacts the performance of established methods. We introduce a set of methodological advances that address these shortcomings to provide a method for forming spatially coherent zones under data sparsity.
- Published
- 2019