Cost-Sensitive Rainfall Intensity Prediction with High-Noise Commercial Microwave Link Data

Liankai Zheng, Jiaxiang Lin (), Zhixin Huang, Yu Lin, Qin Zheng, Qianqian Chen, Lizheng Lin and Jianyun Chen
Additional contact information
Liankai Zheng: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Jiaxiang Lin: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Zhixin Huang: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Yu Lin: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Qin Zheng: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Qianqian Chen: Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Lizheng Lin: Fujian Provincial Meteorological Bureau, Fujian Provincial Atmospheric Detection Technology Support Center, Fuzhou 350028, China
Jianyun Chen: Meteorological Bureau of Fuzhou, Fuzhou 350008, China

Sustainability, 2024, vol. 16, issue 18, 1-13

Abstract: Rainfall intensity prediction based on commercial microwave link data has received significant attention in recent years due to the higher spatial resolution and lower energy consumption. However, the predictive performance is inferior to the model based on meteorological data by reason of the high noise in commercial microwave link data, further exacerbated by the imbalance in the number of samples across different rainfall intensities. Hence, a cost-sensitive rainfall intensity prediction model (CSRFP) is proposed to achieve better predictive performance in high-noise commercial microwave link data. First, the spatiotemporal scene information is encoded, and its weights are trained to provide the model with correlations between signal data from different stations, which helps the model to better capture potential patterns between the data and thus reduce the effect of noise. Next, the rainfall cross-entropy loss based on the rainfall distribution provides the model with the probability of different rainfall intensities occurring and back-calculates the signal attenuation at a specific rainfall intensity, assigning more reasonable weights to different samples considering signal attenuation, which makes the model cost-sensitive and can address the class imbalance problem. Extensive experiments are carried out on high-noise communication data and imbalanced rainfall data in Fuzhou. Compared to typical prediction methods such as RNN applied to rainfall and communication data, CSRFP improves Recall , Precision , AUC ROC , AUC PR and F 1 and Accuracy by approximately 19%, 37%, 8%, 22%, 30%, and 17%, respectively. Significantly, the model’s prediction accuracy for heavy rain with the smallest number of samples improves by about 13%.

Keywords: time series prediction; class imbalance; cost sensitive; commercial microwave links (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/16/18/8067/pdf (application/pdf)
https://www.mdpi.com/2071-1050/16/18/8067/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:16:y:2024:i:18:p:8067-:d:1478742

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().