Combining cosmic-ray neutron and capacitance sensors and fuzzy inference to spatially quantify soil moisture distribution

This paper combines data from soil moisture capacitance probes and a cosmic-ray neutron probe in a fuzzy inference system to estimate spatially variable soil moisture in a ∼28 ha circular area at an hourly interval in northeast Tasmania, Australia. The technique uses hourly counts of cosmic-ray neutrons, a network of 25 capacitance probes measuring soil moisture at half hourly intervals and at five depths (0-50 cm), and a multiple adaptive neuro-fuzzy inference system. We quantified soil moisture in the top portion of the soil during wet and dry periods for training and testing periods. After training, the technique provided reliable estimates of temporal pattern of soil moisture at 10- and 20-cm depths during a wet period using input data only from the cosmic-ray neutron probe. There was overprediction of soil moisture during a dry period, which suggests a longer training period representative of the full range of likely conditions might be required. Spatial maps of soil water content produced from the single cosmic-ray neutron probe were similar to those of the capacitance probe