Time Series Prediction of In-situ Soil Moisture Based on Meteorological Data in the Yangtze River Delta

LI Liuyang; ZHU Qing; LIU Ya; LIAO Kaihua; LAI Xiaoming

doi:10.13870/j.cnki.stbcxb.2021.02.018

您当前的位置：

首页 >

文章列表页 >

Time Series Prediction of In-situ Soil Moisture Based on Meteorological Data in the Yangtze River Delta

更新时间：2025-03-12

- Time Series Prediction of In-situ Soil Moisture Based on Meteorological Data in the Yangtze River Delta
- Vol. 35, Issue 2, Pages: 131-137(2021)
- 作者机构：
  
  1. 中国科学院南京地理与湖泊研究所, 中国科学院流域地理学重点实验室,南京,210008
  2. 中国科学院大学,北京,100049
- 作者简介：
- 基金信息：
- DOI：10.13870/j.cnki.stbcxb.2021.02.018
  CLC： S152.7
- Published：2021
- 稿件说明：
移动端阅览
LI Liuyang, ZHU Qing, LIU Ya, et al. Time Series Prediction of In-situ Soil Moisture Based on Meteorological Data in the Yangtze River Delta[J]. 2021, 35(2): 131-137.
DOI：

LI Liuyang, ZHU Qing, LIU Ya, et al. Time Series Prediction of In-situ Soil Moisture Based on Meteorological Data in the Yangtze River Delta[J]. 2021, 35(2): 131-137. DOI： 10.13870/j.cnki.stbcxb.2021.02.018.

摘要

以长三角3省1市为研究区，旨在构建长三角地区土壤水分长时间序列，为农业生产和遥感算法提供数据支撑。研究基于空间匹配的站点土壤水分数据和气象数据，利用主成分分析得到4个有效主成分作为线性回归和BP神经网络模型的输入因子，建立土壤水分与气象因子间的定量关系，并评估所构建模型的精度。结果表明，基于全部站点数据建立的单一BP神经网络模型优于单一线性回归模型。单一线性回归模型的R2=0.34，RMSE=0.046 m3/m3，MAE=3.67%；而单一BP神经网络模型的训练、验证和测试3个数据集的R2均在0.64以上，RMSE<0.043 m3/m3，MAE低于3.4%。根据逐个站点分别构建分站点的BP神经网络模型，其总体精度高于基于全部站点数据构建的单一BP神经网络模型。分站点构建的BP神经网络模型的总体精度方面，3个数据集的R2均值在0.75以上，RMSE<0.039 m3/m3，MAE低于3%。通过对逐个站点分别构建BP神经网络模型，获得了精度较高、较稳定的土壤水分拟合结果。

Abstract

In order to construct a long-term series of soil moisture in the Yangtze River Delta

which is frequently used for the validation of various satellite products and agricultural production

the linear regression and BP neural network models were constructed respectively to describe the quantitative relationship between soil moisture and meteorological factors. Based on the paired data of in-situ soil moisture and meteorological observation in the Yangtze River Delta including the city of Shanghai and the provinces of Jiangsu

Anhui and Zhejiang

four effective principal components were obtained by principal component analysis as the input of the established models

and the accuracies of these models were evaluated systematically. The results showed that

although both based on all paired data from soil moisture and meteorological observation

the prediction accuracy of the single BP neural network model (the R2 were all above 0.64

and RMSE and MAE were less than 0.043 m3/m3 and 3.4% separately in the sets of the training

validation and testing data) was better than the single linear regression model (R2

RMSE and MAE were 0.34

0.046 m3/m3 and 3.67% respectively). However

accuracies of both these models were worse than the BP neural network models based on each paired soil moisture and meteorological observation data

with the average of R2above 0.75

and RMSE and MAE less than 0.039 m3/m3 and 3% respectively. By constructing the BP neural network models based on each paired soil moisture and meteorological observation data

a more accurate and stable soil moisture fitting result was obtained.

关键词

Keywords

references

季劲钧,刘青,李银鹏.半干旱地区地表水平衡的特征和模拟[J].地理学报,2004,59(6):964-971.

Seneviratne S I, Corti T, Davin E L, et al. Investigating soil moisture-climate interactions in a changing climate:A review[J].Earth Science Reviews,2010,99(3/4):125-161.

范科科,张强,孙鹏,等.青藏高原地表土壤水变化、影响因子及未来预估[J].地理学报,2019,74(3):520-533.

Zeng J Y, Li Z, Chen Q, et al. Evaluation of remotely sensed and reanalysis soil moisture products over the Tibetan Plateau using in-situ observations[J].Remote Sensing of Environment,2015,163:91-110.

范科科,张强,史培军,等.基于卫星遥感和再分析数据的青藏高原土壤湿度数据评估[J].地理学报,2018,73(9):1778-1791.

Hauser M, Orth R, Seneviratne S I. Role of soil moisture versus recent climate change for the 2010 heat wave in western Russia[J].Geophysical Research Letters,2016,43(6):2819-2826.

Miralles D G, Teuling A J, Van Heerwaarden C C, et al. Mega-heat wave temperatures due to combined soil desiccation and atmospheric heat accumulation[J].Nature Geoscience,2014,7(5):345-349.

薛晓萍,王新,张丽娟,等.基于支持向量机方法建立土壤湿度预测模型的探讨[J].土壤通报,2007,38(3):427-433.

朱青,廖凯华,赖晓明,等.流域多尺度土壤水分监测与模拟研究进展[J].地理科学进展,2019,38(8):1150-1158.

史舟,徐冬云,滕洪芬,等.土壤星地传感技术现状与发展趋势[J].地理科学进展,2018,37(1):79-92.

Chen Y Y, Yang K, Qin J, et al. Evaluation of AMSR-E retrievals and GLDAS simulations against observations of a soil moisture network on the central Tibetan Plateau[J].Journal of Geophysical Research Atmospheres,2013,118(10):4466-4475.

Liu Y Y, Dorigo W A, Parinussa R M, et al. Trend-preserving blending of passive and active microwave soil moisture retrievals[J].Remote Sensing of Environment,2012,123:280-297.

杨娜,刘良明,向大享,等.利用BP神经网络由特征气象要素预测土壤湿度[J].土壤通报,2011,42(6):1324-1329.

Chen N, Li X Y, Šimůnek J, et al. Evaluating soil nitrate dynamics in an intercropping dripped ecosystem using HYDRUS-2D[J].Science of the Total Environment,2020,718:1-13.

Dang T D, Vu D T, Chowdhury A F M K, et al. A software package for the representation and optimization of water reservoir operations in the VIC hydrologic model[J].Environmental Modelling and Software,2020,126:104673.

Chen M Y, Gassman P W, Srinivasan R, et al. Analysis of alternative climate datasets and evapotranspiration methods for the Upper Mississippi River Basin using SWAT within HAWQS[J].Science of the Total Environment,2020,720:137562.

王振龙,高建峰.实用土壤墒情监测预报技术[M].北京:中国水利水电出版社,2006.

郭庆春,王素娟,何振芳.基于BP人工神经网络的土壤含水量预测模型的研究[J].山东农业科学,2012,44(12):11-15.

李彬楠,樊贵盛.基于支持向量机方法的土壤水分特征曲线预测模型[J].节水灌溉,2019(1):108-111,117.

李小刚,王静,马友华,等.基于BP神经网络的土壤墒情预测精度研究:以肥东县为例[J].土壤通报,2017,48(2):292-297.

冯徽徽,刘元波,杨风亭.高植被覆盖区AMSR-E土壤水分数据校准方法[J].土壤通报,2014,45(4):816-822.

王青青,张珂,叶金印,等.安徽省土壤湿度时空变化规律分析及遥感反演[J].河海大学学报(自然科学版),2019,47(2):24-28.

辛强,李兆富,李瑞娟,等.基于温度植被干旱指数的华东地区AMSR-E土壤水分数据的空间降尺度研究[J].农业现代化研究,2016,37(5):956-963.

崔园园,张强,覃军,等.CLDAS融合土壤湿度产品在东北地区的适用性评估及订正[J].中国农业气象,2019,40(10):660-668.

Zhang Y G, Schaap M G, Zha Y Y. A high-resolution global map of soil hydraulic properties produced by a hierarchical parameterization of a physically based water retention model[J].Water Resources Research,2018,54(12):9774-9790.

袁淑杰,何兴潼,谷晓平,等.贵州喀斯特区域土壤湿度持续下降时期气象要素对土壤湿度影响研究[J].土壤通报,2018,49(2):320-328.

盛承懋.应用回归分析[M].上海:上海科学技术文献出版社,1989.

刘学勤,何力春,奥小平.宜林荒山春季土壤含水率与气象因子的相关分析[J].北京林业大学学报,1993,15(3):26-33.

孙倩倩,刘晶淼,梁宏.东北地区土壤湿度的区域性预报模型研究[J].自然资源学报,2014,29(6):1065-1075.

陈昌华,谭俊,尹健康,等.基于PCA-RBF神经网络的烟田土壤水分预测[J].农业工程学报,2010,26(8):85-90.

Views

1155

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Vulnerability Assessment of Soil Erosion in Southwestern Hubei Province Based on RUSLE Model and Geographic Detector

Related Author

YANG Yanpan

TIAN Pei

SHEN Chenzhu

PING Yaodong

JIA Tinghui

YUE Xue

HUANG Jianwu

ZHANG Xiaoyan

Related Institution

Key Laboratory for Geographical Process Analysis & Simulation Hubei Province, Central China Normal University

College of Urban and Environmental Sciences,Central China Normal University

Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Guangxi Teachers Education University), Ministry of Education

Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation(Guangxi Teachers Education University)

Hunan First Normal University

⁰