Applying Upstream Satellite Signals and a 2-D Error Minimization Algorithm to Advance Early Warning and Management of Flood Water Levels and River Discharge.

Recent studies demonstrate the power of applying satellite imagery in combination with artificial intelligence (AI) methods to advance the accuracy of forecasting ungauged river network water levels and discharge for early flood warning and management. In predicting river water levels and discharge time series, one of the most common sources of error with AI forecasting algorithms is the input imitation defect. When the input imitation defect occurs, regression methods simply present the input variables as output. In this paper, the input imitation defect is minimized by first introducing the two concepts of vertical error and horizontal error. Subsequently, upstream imagery information is combined with previous lags to propose a new procedure for predicting future satellite signals accurately and with the lowest possible input imitation defect. To accomplish this, the brightness temperature received by the Advanced Microwave Scanning Radiometer is used as a proxy of river discharge. The proposed method (PM) is finally compared with the simple linear regression and three well-known AI methods, i.e., multilayer perceptron, extreme learning machines, and radial basis function. The study outcome indicates that the PM results are more trustworthy and realistic. [ABSTRACT FROM AUTHOR]