太原理工大学学报2024，Vol.55Issue(4)：734-742,9.DOI:10.16355/j.tyut.1007-9432.2023BD010
基于深度学习和时空关联建模的降水数据地形订正方法
A Terrain-Based Bias-Correction Method for Precipitation Data Based on Deep Learning and Spatiotemporal Correlation Modeling
摘要
Abstract
[Purposes]How to perform bias-correction for precipitation data based on terrain information has been an important problem in meteorological big data research.However,the existing precipitation terrain-based bias-correction methods mostly suffer from two limitations.First,most of them are designed based on statistical models or conventional machine learning models,thus fails to go beyond to the deep learning models with more powerful feature learning ability.Second,they also lack the ability to incorporate the spatiotemporal correlation informa-tion in meteorological data for enhancing the bias-correction quality.[Methods]To address these limitations,in this paper,a terrain-based bias-correction method for precipitation data based on deep learning and spatiotemporal correlation modeling is presented.First,the precipitation data and multi-source terrain information with alignment and encoding based on the longitude and lati-tude are preprocessed,and thus the corresponding data matrices are constructed.Then the pre-cipitation and terrain data in the spatial and temporal neighborhood of each grid are adopted to a-chieve the multi-source spatiotemporal information modeling,and a down-sampling strategy is used to alleviate the imbalance between the precipitation grids and the non-precipitation grids.Fi-nally,the deep neural network is constructed for regression and bias-correction.The experiments are conducted on the real meteorological data from over 4 000 meteorological observation stations and over 150 thousand meteorological grids in Guangdong Province.[Findings]Experimental re-sults have verified the significance influence of the spatiotemporal modeling strategy over precipi-tation bias correction quality and performance advantage of the proposed method over the baseline methods.关键词
气象大数据/深度学习/降水量/地形订正/时空信息Key words
meteorological big data/deep learning/precipitation/terrain-based bias-correc-tion/spatiotemporal information分类
信息技术与安全科学引用本文复制引用
吴雪峰,陈逸智,王昌栋,黄栋..基于深度学习和时空关联建模的降水数据地形订正方法[J].太原理工大学学报,2024,55(4):734-742,9.基金项目
国家自然科学基金资助项目(61976097) （61976097）
广东省气象局科学技术研究资助项目(GRMC2022Q05) （GRMC2022Q05）
广东省气象局协同观测和多源实况数据融合分析技术创新团队资助项目(GRMCTD202103) （GRMCTD202103）
