Geosensor Network Optimisation to Support Decisions at Multiple Scales

Abstract

Geosensor networks are often used to monitor processes at different spatial scales. Existing approaches for configuring geosensor locations (i.e. sample design) do not address two key challenges: 1) they are limited to a single scale of analysis and do not support multiple scales of evaluation, and 2) they assume that the geosensor network, once established at whatever scale, does not change either in terms of location or number of geosensors. While approaches exist in part for 1) and 2) they do not for both combined. This paper describes a novel approach for optimising geosensor locations in support of multi-scale decisions. It uses the local variation in environmental gradient as a cost surface to approximate the process of interest a proxy for measurements of the process of interest. Cross-scale evaluations of geosensor spatial configurations are supported by measurements of the information loss within spatially nested decision scales. The methods described in this paper fill an important gap as they are i) suggest appropriate sample and geosensor network designs to support cross-scale monitoring, ii) inform on how current network or geosensor coverage could be enhanced by filling gaps, and iii) quantify the information trade-offs (information loss) associated with designs when they are evaluated from the perspective of different decision scales.