Mapping Dryland Salinity Using Neural Networks

摘要

Salinity is a growing problem that affects millions of hectares of agricultural land. Due to the devastating effects of dryland salinity, land owners, the government and catchment groups require cost effective information in the form of salinity maps. This paper investigates the use of a backpropagation neural network to map dryland salinity in the Wimmera region of Victoria, Australia. Data used in this research includes radiometric readings from airborne geophysical measurements and satellite imagery. The results achieved were very promising and indicate the potential for further research in this area.