A Sustainable Climate Forecast System for Post-processing of Precipitation With Application of Machine Learning Computations
In one sentence. Random forest post-processing of CFSv2 precipitation forecasts over Iran, with correlation above 0.87, packaged as a decision support system.
Abstract
Abstract Although many meteorological prediction models have been developed recently, but their predictions are still unreliable. Post-processing is a task for improving meteorological predictions. This study proposes a post-processing method for the Climate Forecast System Version2 (CFSV2) model. The applicability of the proposed method is shown in Iran for an observation data from 1982 to 2017. A software has been implemented which could be used to automatically perform post-processing in meteorological organizations. With application of the present study, Decision Support System (DSS) is implemented for controlling precipitation based natural side effects such as flood disaster or drought phenomenon. Likewise, it is worth noting that the mentioned DSS meets Sustainable Development Goals (SDGs) through grantee of human health and environmental protection issues. Finally, the most important section of DSS is related to prediction and in the present study it is performed by Random Forest algorithm with more than 0.87 correlation coefficient.
Labels
- Topic
- Post-processing & calibration
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- Seasonal to annual
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.21203/rs.3.rs-1552614/v1 OpenAlex:W4224301794
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.