安徽省土壤湿度时空变化规律分析及遥感反演
|
摘要
为获取安徽省的土壤湿度时空信息,采用克里金法将站网实测多层土壤湿度数据插值为网格数据,分析其时空变化特征;进而建立遗传算法优化的BP(back propagation)神经网络模型进行土壤湿度反演。该模型以风云3B卫星的亮温数据为主要输入,训练后对该模型验证并进行预测。结果表明:安徽省土壤湿度月均值波动较频繁,淮北平原和大别山区较其他区域干燥;随着深度的增加,土壤湿度增大且季节和空间差异变小;所有分区平均模拟值与实测值的日序列相关性达到0. 605,均方根误差为0. 056 m~3/m~3,说明该模型能够较好地反演安徽省土壤湿度。
To obtain the spatiotemporal characteristics of soil moisture in Anhui Province,the Kriging method was firstly used to interpolate the in-situ observed and multilayer soil moisture to gridded data. Then,the spatiotemporal variability of soil moisture across this region was analyzed. A Back Propagation( BP) neural network optimized by the genetic algorithm was established to retrieve the soil moisture using the brightness temperature measured by the Fengyun 3 B satellite. The results show that soil moisture across Anhui Province shows high temporal fluctuations.And,the soil moisture in the Huaibei plain and the Dabie Mountains is lower than the other regions. As depth becomes deeper,soil moisture has a higher value with lower seasonal and horizontal variability. The correlation between retrieved and observed daily gridded values across the five sub-regions is 0.605,while the corresponding root mean square error is 0. 056 m~3/m~3. Clearly, the proposed retrieval algorithm is able to capture the spatiotemporal variability of soil moisture in Anhui Province.
To obtain the spatiotemporal characteristics of soil moisture in Anhui Province,the Kriging method was firstly used to interpolate the in-situ observed and multilayer soil moisture to gridded data. Then,the spatiotemporal variability of soil moisture across this region was analyzed. A Back Propagation( BP) neural network optimized by the genetic algorithm was established to retrieve the soil moisture using the brightness temperature measured by the Fengyun 3 B satellite. The results show that soil moisture across Anhui Province shows high temporal fluctuations.And,the soil moisture in the Huaibei plain and the Dabie Mountains is lower than the other regions. As depth becomes deeper,soil moisture has a higher value with lower seasonal and horizontal variability. The correlation between retrieved and observed daily gridded values across the five sub-regions is 0.605,while the corresponding root mean square error is 0. 056 m~3/m~3. Clearly, the proposed retrieval algorithm is able to capture the spatiotemporal variability of soil moisture in Anhui Province.
引文
[1]刘荣华,张珂,晁丽君,等.基于多源卫星观测的中国土壤湿度时空特征分析[J].水科学进展,2017,28(4):479-487.(LIU Ronghua,ZHANG Ke,CHAO Lijun,et al.Analysis of spatiotemporal characteristics of surface soil moisture across China based on multi-satellite observations[J].Advances in Water Science,2017,28(4):479-487.(in Chinese))
[2]王逸男,安如,尤加俊,等.CCI土壤湿度产品在中国区的降尺度与融合研究[J].河海大学学报(自然科学版),2018,46(3):196-202.(WANG Yinan,AN Ru,YOU Jiajun,et al.Downscaling and merging of the CCI soil moisture product over China[J].Journal of Hohai University(Natural Sciences),2018,46(3):196-202.(in Chinese))
[3]向怡衡,张明敏,张兰慧,等.祁连山区不同植被类型上的SMOS遥感土壤水分产品质量评估[J].遥感技术与应用,2017,32(5):835-843.(XIANG Yiheng,ZHANG Mingmin,ZHANG Lanhui,et al.Validation of SMOS soil moisture products on different vegetation types in Qilian Mountain[J].Remote Sensing Technology and Application,2017,32(5):835-843.(in Chinese))
[4]马春芽,王景雷,黄修桥.遥感监测土壤水分研究进展[J].节水灌溉,2018(5):70-74.(MA Chunya,WANG Jinglei,HUANG Xiuqiao.Progress of soil moisture monitoring by remote sensing[J].Water Saving Irrigation,2018(5):70-74.(in Chinese))
[5]RODRGUEZ-FERNNDEZ N J,AIRES F,RICHAUME P,et al.Soil moisture retrieval using neural networks:application to SMOS[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(11):5991-6007.
[6]KOLASSA J,REICHLE R H,LIU Q,et al.Estimating surface soil moisture from SMAP observations using a Neural Network technique[J].Remote Sensing of Environment,2018,204:43-59.
[7]聂兵,沈非,徐光来,等.安徽省近50年降水时空变化分析[J].安徽师范大学学报(自然科学版),2017,40(6):574-579.(NIE Bing,SHEN Fei,XU Guanglai,et al.Analysis of temporal-spatial change in Anhui Province in recent 50 years[J].Journal of Anhui Normal University(Natural Science),2017,40(6):574-579.(in Chinese))
[8]林金煌,林广发.福建省降水空间插值方法比较与区域分布特征研究[J].海南师范大学学报(自然科学版),2015,28(1):61-65.(LIN Jinhuang,LIN Guangfa.Comparison of spatial interpolation methods for precipitation and regional distribution characteristic in Fujian Province[J].Journal of Hainan Normal University(Natural Science),2015,28(1):61-65.(in Chinese))
[9]戴培培,靖常峰,杜明义.基于雨量计的城区降雨插值不确定性分析[J].人民黄河,2015,37(4):38-42.(DAI Peipei,JING Changfeng,DU Mingyi.Uncertainty analysis of urban rainfall spatial interpolation based on gauges data[J].Yellow River,2015,37(4):38-42.(in Chinese))
[10]钱安,易爽,孙广通,等.GLDAS_NOAH_M.2.1水文模型在青藏高原的适定性分析[J].大地测量与地球动力学,2018,38(3):254-259.(QIAN An,YI Shuang,SUN Guangtong,et al.GLDAS_NOAH_M.2.1 hydrological model and its application analysis in the Qinghai-Tibet Plateau[J].Journal of Geodesy and Geodynamics,2018,38(3):254-259.(in Chinese))
[11]韩通,李致家,刘开磊,等.山区小流域洪水预报实时校正研究[J].河海大学学报(自然科学版),2015,43(3):208-214.(HAN Tong,LI Zhijia,LIU Kailei,et al.Research on real-time correction method of flood forecasting in small mountain watershed[J].Journal of Hohai University(Natural Sciences),2015,43(3):208-214.(in Chinese))
[12]卢文喜,杨忠平,李平,等.基于改进BP算法的地下水动态预测模型[J].水资源保护,2007,23(3):5-8.(LU Wenxi,YANG Zhongping,LI Ping,et al.Dynamic prediction model of groundwater level based on improved BP algorithm[J].Water Resources Protection,2007,23(3):5-8.(in Chinese))
[13]徐伟,董增川,付晓花,等.基于BP人工神经网络的河流生态健康预警[J].河海大学学报(自然科学版),2015,43(1):54-59.(XU Wei,DONG Zengchuan,FU Xiaohua,et al.Early warning of river ecosystem health based on BP artificial neural networks[J].Journal of Hohai University(Natural Sciences),2015,43(1):54-59.(in Chinese))
[14]李培都,司建华,冯起,等.疏勒河年径流量变化特征分析及模拟[J].水资源保护,2018,34(2):52-60.(LI Peidu,SIJianhua,FENG Qi,et al.Analysis and simulation on annual runoff variation characteristics of Shule River[J].Water Resources Protection,2018,34(2):52-60.(in Chinese))
[15]RODRGUEZ-FERNNDEZ N J,KERR Y H,SCHALIE R V D,et al.Long term global surface soil moisture fields using an SMOS-trained neural network applied to AMSR-E data[J].Remote Sensing,2016,8:959-985.
[16]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.(LI Xiaogang,WANG Jing,MA Youhua,et al.Research on soil moisture forecast model based on BP neural network-a case study at Feidong County[J].Chinese Journal of Soil Science,2017,48(2):292-297.(in Chinese))
[2]王逸男,安如,尤加俊,等.CCI土壤湿度产品在中国区的降尺度与融合研究[J].河海大学学报(自然科学版),2018,46(3):196-202.(WANG Yinan,AN Ru,YOU Jiajun,et al.Downscaling and merging of the CCI soil moisture product over China[J].Journal of Hohai University(Natural Sciences),2018,46(3):196-202.(in Chinese))
[3]向怡衡,张明敏,张兰慧,等.祁连山区不同植被类型上的SMOS遥感土壤水分产品质量评估[J].遥感技术与应用,2017,32(5):835-843.(XIANG Yiheng,ZHANG Mingmin,ZHANG Lanhui,et al.Validation of SMOS soil moisture products on different vegetation types in Qilian Mountain[J].Remote Sensing Technology and Application,2017,32(5):835-843.(in Chinese))
[4]马春芽,王景雷,黄修桥.遥感监测土壤水分研究进展[J].节水灌溉,2018(5):70-74.(MA Chunya,WANG Jinglei,HUANG Xiuqiao.Progress of soil moisture monitoring by remote sensing[J].Water Saving Irrigation,2018(5):70-74.(in Chinese))
[5]RODRGUEZ-FERNNDEZ N J,AIRES F,RICHAUME P,et al.Soil moisture retrieval using neural networks:application to SMOS[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(11):5991-6007.
[6]KOLASSA J,REICHLE R H,LIU Q,et al.Estimating surface soil moisture from SMAP observations using a Neural Network technique[J].Remote Sensing of Environment,2018,204:43-59.
[7]聂兵,沈非,徐光来,等.安徽省近50年降水时空变化分析[J].安徽师范大学学报(自然科学版),2017,40(6):574-579.(NIE Bing,SHEN Fei,XU Guanglai,et al.Analysis of temporal-spatial change in Anhui Province in recent 50 years[J].Journal of Anhui Normal University(Natural Science),2017,40(6):574-579.(in Chinese))
[8]林金煌,林广发.福建省降水空间插值方法比较与区域分布特征研究[J].海南师范大学学报(自然科学版),2015,28(1):61-65.(LIN Jinhuang,LIN Guangfa.Comparison of spatial interpolation methods for precipitation and regional distribution characteristic in Fujian Province[J].Journal of Hainan Normal University(Natural Science),2015,28(1):61-65.(in Chinese))
[9]戴培培,靖常峰,杜明义.基于雨量计的城区降雨插值不确定性分析[J].人民黄河,2015,37(4):38-42.(DAI Peipei,JING Changfeng,DU Mingyi.Uncertainty analysis of urban rainfall spatial interpolation based on gauges data[J].Yellow River,2015,37(4):38-42.(in Chinese))
[10]钱安,易爽,孙广通,等.GLDAS_NOAH_M.2.1水文模型在青藏高原的适定性分析[J].大地测量与地球动力学,2018,38(3):254-259.(QIAN An,YI Shuang,SUN Guangtong,et al.GLDAS_NOAH_M.2.1 hydrological model and its application analysis in the Qinghai-Tibet Plateau[J].Journal of Geodesy and Geodynamics,2018,38(3):254-259.(in Chinese))
[11]韩通,李致家,刘开磊,等.山区小流域洪水预报实时校正研究[J].河海大学学报(自然科学版),2015,43(3):208-214.(HAN Tong,LI Zhijia,LIU Kailei,et al.Research on real-time correction method of flood forecasting in small mountain watershed[J].Journal of Hohai University(Natural Sciences),2015,43(3):208-214.(in Chinese))
[12]卢文喜,杨忠平,李平,等.基于改进BP算法的地下水动态预测模型[J].水资源保护,2007,23(3):5-8.(LU Wenxi,YANG Zhongping,LI Ping,et al.Dynamic prediction model of groundwater level based on improved BP algorithm[J].Water Resources Protection,2007,23(3):5-8.(in Chinese))
[13]徐伟,董增川,付晓花,等.基于BP人工神经网络的河流生态健康预警[J].河海大学学报(自然科学版),2015,43(1):54-59.(XU Wei,DONG Zengchuan,FU Xiaohua,et al.Early warning of river ecosystem health based on BP artificial neural networks[J].Journal of Hohai University(Natural Sciences),2015,43(1):54-59.(in Chinese))
[14]李培都,司建华,冯起,等.疏勒河年径流量变化特征分析及模拟[J].水资源保护,2018,34(2):52-60.(LI Peidu,SIJianhua,FENG Qi,et al.Analysis and simulation on annual runoff variation characteristics of Shule River[J].Water Resources Protection,2018,34(2):52-60.(in Chinese))
[15]RODRGUEZ-FERNNDEZ N J,KERR Y H,SCHALIE R V D,et al.Long term global surface soil moisture fields using an SMOS-trained neural network applied to AMSR-E data[J].Remote Sensing,2016,8:959-985.
[16]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.(LI Xiaogang,WANG Jing,MA Youhua,et al.Research on soil moisture forecast model based on BP neural network-a case study at Feidong County[J].Chinese Journal of Soil Science,2017,48(2):292-297.(in Chinese))