A novel approach for precipitation forecast via improved K-nearest neighbor algorithm. (August 2017)

• Record Type: Journal Article
• Authors: Huang, Mingming; Lin, Runsheng; Huang, Shuai; Xing, Tengfei
• Is Part Of: Advanced engineering informatics. Volume 33(2017)
• Page Start: 89
• Page End: 95
• Publication Date: 2017-08
• Subjects: KNN algorithm -- Improved KNN algorithm -- Precipitation -- Precipitation forecast; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2017.05.003
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: The prediction method plays crucial roles in accurate precipitation forecasts. Recently, machine learning has been widely used for forecasting precipitation, and the K -nearest neighbor (KNN) algorithm, one of machine learning techniques, showed good performance. In this paper, we propose an improved KNN algorithm, which offers robustness against different choices of the neighborhood size k, particularly in the case of the irregular class distribution of the precipitation dataset. Then, based our improved KNN algorithm, a new precipitation forecast approach is put forward. Extensive experimental results demonstrate that the effectiveness of our proposed precipitation forecast approach based on improved KNN algorithm.