Multiple data fusion for rainfall estimation using a NARX-based recurrent neural network _ the development of the REIINN model

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Ang, M.R.C.O.^1 ; Gonzalez, R.M.^1 ; Castro, P.P.M.^2

Department of Geodetic Engineering, University of the Philippines, Diliman, Quezon City 1101, Philippines^1

Institute of Civil Engineering, University of the Philippines, Diliman, Quezon City 1101, Philippines^2

关键词: Cloud-top temperatures;    Correlation coefficient;    Ground based measurement;    Information integration;    Rainfall estimations;    Rainfall measurements;    Remote sensing images;    Root mean square errors;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012019/pdf
DOI  :  10.1088/1755-1315/17/1/012019

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Rainfall, one of the important elements of the hydrologic cycle, is also the most difficult to model. Thus, accurate rainfall estimation is necessary especially in localized catchment areas where variability of rainfall is extremely high. Moreover, early warning of severe rainfall through timely and accurate estimation and forecasting could help prevent disasters from flooding. This paper presents the development of two rainfall estimation models that utilize a NARX-based neural network architecture namely: REIINN 1 and REIINN 2. These REIINN models, or Rainfall Estimation by Information Integration using Neural Networks, were trained using MTSAT cloud-top temperature (CTT) images and rainfall rates from the combined rain gauge and TMPA 3B40RT datasets. Model performance was assessed using two metrics-root mean square error (RMSE) and correlation coefficient (R). REIINN 1 yielded an RMSE of 8.1423 mm/3h and an overall R of 0.74652 while REIINN 2 yielded an RMSE of 5.2303 and an overall R of 0.90373. The results, especially that of REIINN 2, are very promising for satellite-based rainfall estimation in a catchment scale. It is believed that model performance and accuracy will greatly improve with a denser and more spatially distributed in-situ rainfall measurements to calibrate the model with. The models proved the viability of using remote sensing images, with their good spatial coverage, near real time availability, and relatively inexpensive to acquire, as an alternative source for rainfall estimation to complement existing ground-based measurements.