Our Virtual Sensors use various models, including multilayer perceptrons, support vector machines (SVMs) with radial basis function kernels, and SVMs with mixture density Mercer kernels.
Data from instruments built in a phased approach, with additional measurement capabilities added in later phases, can be combined using Virtual Sensors.
Technology may mature to the point that an instrument offers new measurement capabilities that were not planned in the original design of the instrument. Virtual Sensors can use older low resolution data to obtain new high resolution data, to match higher-resolution instrument capabilities.
High-resolution spectral measurements may be too costly to perform on a large sample, and therefore, lower resolution spectral instruments are used to take the majority of measurements. Virtual Sensors can use low resolution data to predict high resolution spectra.
Ashok Srivastava, Ph.D.
Nikunj C. Oza, Ph.D. (co-I)
Virtual Sensors for Earth Science Paper - Broken