Shinichi Hirako

A Revised Soil Spectrophotometer

Abstract Key points in the revised spectrophotometer design were: use of a RTK-GPS, improved soil penetrator to ensure a uniform soil surface under high speed conditions, and all units are re-arranged for compactness. Test runs proved that the traveling speed could be increased up to about at least 1 m/s, and that the reflectance can also be used for generating soil maps. Derivative operation could eliminate biases on the measured reflectance due to surface disturbance, which enabled to evaluate at least soil moisture and EC.

Development of On-the-go Soil Sensor for Rice Transplanter*

Abstract The objective of this paper was to provide the development of on-the-go soil sensor for rice transplanter, particularly from a perspective of precision agriculture applications. Ultrasonic sensor, electrodes and platinum resistance thermometer were employed for topsoil depth (TD) and apparent electrical conductivity (ECa) measurement. Soil fertility value (SFV) defined as new soil parameter, which consisted of EC a / TD. The results of field test revealed that the developed equipments could measure the TD (R 2 = 0.999), and the SFV had a strong relationship with measured EC (R 2 = 0.937).

SOIL PROPERTIES PREDICTION FOR REAL-TIME SOIL SENSOR BASED ON NEURAL NETWORK

Real-time soil sensor (RTSS) was built and tested, making use of a near-infrared spectrophotometer, which offered a convenient and quick method for in-situ soil organic matter (SOM), total nitrogen (TN), pH and moisture content (MC) measurement. The sensor could collect a spectrum absorbance of soil (i.e. 500-1650 nm with 7 nm interval). Neural network was used for making prediction model for each soil component. The training and testing of neural network was based on 1300 dataset was taken by the RTSS from 7 location of Japan where included paddy and upland crop field. Input variables represent spectrum absorbance of the points of interest, while the output variables represent SOM, TN, pH and MC data of the points of interest, which was analyzed in the laboratory. After the neural network has been successfully trained, its performance was tested on a separate testing set. The result of MC, pH, SOM and TN prediction indicated that the NN model validated coefficient of determination of R2=0.91, 0.75, 0.95 and 0.96, respectively.