APPLICATAION OF A NEURAL NETWORK TO MONITOR STREAM SURFACEWATER QUALITY USING SATELLITE REMOTE SENSING DATA

摘要

The investigation of earth's resources is an important aspect of remote monitoring application. Through the datarnreceived, land use and surface covering and environmental quality in rivers, dams, and lakes can be detected. Thisrnresearch incorporates multivariate regression, artificial neural network, and discriminate analysis to examine andrncompare the relationships of optical spectrum and water quality. The investigation will determine the possibility ofrnusing the images obtained through automatic remote monitoring to determine the changes in river water quality and itsrnindex derived from dissolved oxygen, biological oxygen demand, suspended solid, and ammonia nitrogen. Concurrentrnin situ surface water quality measurements, optical (SPOT) data were obtained in selected locations in five differentrndays. Although significant correlations were not observed between optical data and water quality parameters, the resultrnof this investigation has shown, based on the water predictions from monitoring stations that the analysis fromrnmultivariate regression is not as good as the results obtained from artificial neural network in the study area. Likewise, arnneural network algorithm is applied to estimate the transfer functions between the major characteristics of surface waterrnindex and the satellite optical data. The results also show that the estimation accuracy, with acceptable level for majorrncharacteristics of surface water index using the neural network pairing up with the conjugate gradient decent searchingrnmethod is more feasible than those from discriminate analysis. The results also indicate that conjugate gradient decentrnsearching algorithm can assist to improve the categorization. However, this result of limited optical data learningrnalgorithm needs to be further confirmed by more case studies. The technique still needs to be refined in detail in order torndetect differences within the typical range of these water quality index found in the area under study. Basically, it isrnevident that artificial neural network has the potential and feasibility of monitoring water qualities and index.