Monitoring of environmental phenomena with embedded networked sensing confronts the challenges of both unpredictable variability in the spatial distribution of phenomena, coupled with demands for a high spatial sampling rate in three dimensions. For example, low distortion mapping of critical solar radiation properties in forest environments may require two-dimensional spatial sampling rates of greater than 10 samples/m2 over transects exceeding 1000 m2. Clearly, adequate sampling coverage of such a transect requires an impractically large number of sampling locations. This work describes a new approach where the deployment of an adaptive sampling algorithm on a mobile sensor node improves the performance of spatiotemporal sampling density to better cope with a set of environmental mapping demands. Here the robot actively builds a statistical model of the environment and picks samples selectively to increase the performance of such modeling. In addition we will present our active modeling simulation that has been implemented in R statistical computing language and can potentially run on the robot in real time.