Linking Singular Spectrum Analysis and Machine Learning for Monthly Rainfall Forecasting
| Autor: | Tao Chang Yang, Pa Ousman Bojang, Quoc Bao Pham, Pao Shan Yu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
rainfall forecasting
random forests Watershed 010504 meteorology & atmospheric sciences Mean squared error Calibration (statistics) 0208 environmental biotechnology 02 engineering and technology Machine learning computer.software_genre 01 natural sciences lcsh:Technology lcsh:Chemistry General Materials Science Instrumentation Singular spectrum analysis lcsh:QH301-705.5 0105 earth and related environmental sciences Fluid Flow and Transfer Processes business.industry lcsh:T Process Chemistry and Technology General Engineering least square support vector regression singular spectrum analysis lcsh:QC1-999 020801 environmental engineering Computer Science Applications Random forest Water resources machine learning lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 Environmental science Data pre-processing Artificial intelligence business Surface runoff lcsh:Engineering (General). Civil engineering (General) computer lcsh:Physics |
| Zdroj: | Applied Sciences, Vol 10, Iss 3224, p 3224 (2020) Applied Sciences Volume 10 Issue 9 |
| ISSN: | 2076-3417 |
| Popis: | Monthly rainfall forecasts can be translated into monthly runoff predictions that could support water resources planning and management activities. Therefore, development of monthly rainfall forecasting models in reservoir watersheds is essential for generating future rainfall amounts as an input to a water-resources-system simulation model to predict water shortage conditions. This research aims to examine the reliability of linking a data preprocessing method (singular spectrum analysis, SSA) with machine learning, least-squares support vector regression (LS-SVR), and random forest (RF), for monthly rainfall forecasting in two reservoir watersheds (Deji and Shihmen reservoir watersheds) located in Taiwan. Merging SSA with LS-SVR and RF, the hybrid models (SSA-LSSVR and SSA-RF) were developed and compared with the standard models (LS-SVR and RF). The proposed models were calibrated and validated using the watersheds&rsquo observed areal monthly rainfalls separated into 70 percent of data for calibration and 30 percent of data for validation. Model performances were evaluated using two accuracy measures, root mean square error (RMSE) and Nash&ndash Sutcliffe efficiency (NSE). Results show that the hybrid models could efficiently forecast monthly rainfalls. Nonetheless, the performances of the hybrid models vary in both watersheds which suggests that prior knowledge about the watershed&rsquo s hydrological behavior would be helpful to implement the appropriate model. Overall, the hybrid models significantly surpass the standard models for the two studied watersheds, which indicates that the proposed models are a prudent modeling approach that could be employed in the current research regions for monthly rainfall forecasting. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|