中国四维测绘技术有限公司
纸质出版:2024
移动端阅览
谢永强. 集成多源数据与XGBoost算法京津冀地区土壤水分空间反演[J]. 地理空间信息, 2024,22(12):20-24+29.
谢永强. 集成多源数据与XGBoost算法京津冀地区土壤水分空间反演[J]. 2024, 22(12): 20-24+29.
为提升土壤水分(soil moisture
SM)遥感反演时效性及其空间分辨率,以京津冀地区为研究区,集成Sentinel-1Synthetic Aperture Radar (SAR)、Sentinel-2 Multi-Spectral Imaging (MSI)、Digital Elevation Model (DEM)、气候数据与地面同步实测SM资料,引入Extreme Gradient Boosting (XGBoost)算法构建SM预测模型进而反演区域100 m分辨率水平上SM空间分布,最后通过决定系数(R2)、平均绝对误差(mean absolute error
MAE)和均方根误差(root mean square error
RMSE)评估反演精度。结果表明,京津冀地区SM空间异质性受地形因素控制,不同类型的环境变量在反演SM分布中的贡献率依次为:地形因子(39.84%)>MSI (22.05%)>气候因素(19.66%)>SAR (18.45%)。XGBoost算法具有较强拟合能力,其反演的SM精度R2达0.72
MAE、RMSE分别为0.030、0.036,反演结果显示京津冀地区SM呈现自东北向周边地带性减少分布。该研究展示了集成多源数据结合XGBoost算法在异质性景观区SM监测方面的潜力。
艾小童.基于ELM模型的极化SAR土壤水分降尺度研究[J].地理空间信息,2023(07).
王井利,高天娇,李荣平,余鹏程,马运涛,米娜,温日红,张凯.基于光学遥感和微波遥感的土壤水分反演模型研究[J].气象与环境学报,2023(01).
王思楠,李瑞平,吴英杰,赵水霞,王秀青.基于环境变量和机器学习的土壤水分反演模型研究[J].农业机械学报,2022(05).
吴善玉,鲍艳松,李叶飞,吴莹.基于神经网络算法的Sentinel-1和Sentinel-2遥感数据联合反演土壤湿度研究[J].大气科学学报,2021(04).
Jamei Mehdi,Ali Mumtaz,Karbasi Masoud,Sharma Ekta,Jamei Mozhdeh,Chu Xuefeng,Yaseen Zaher Mundher.A high dimensional features-based cascaded forward neural network coupled with MVMD and Boruta-GBDT for multi-step ahead forecasting of surface soil moisture[J].Engineering Applications of Artificial Intelligence,2023.
Wang Zhen,Zhao Tianjie,Shi Jiancheng,Wang Hongquan,Ji Dabin,Yao Panpan,Zheng Jingyao,Zhao Xuesheng,Xu Xia.1-km soil moisture retrieval using multi-temporal dual-channel SAR data from Sentinel-1 A/B satellites in a semi-arid watershed[J].Remote Sensing of Environment,2023.
Nativel Simon,Ayari Emna,RodriguezFernandez Nemesio,Baghdadi Nicolas,Madelon Remi,Albergel Clement,Zribi Mehrez.Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation[J].Remote Sensing,2022.
Bhogapurapu Narayanarao,Dey Subhadip,Mandal Dipankar,Bhattacharya Avik,Karthikeyan L.,McNairn Heather,Rao Y.S..Soil moisture retrieval over croplands using dual-pol L-band GRD SAR data[J].Remote Sensing of Environment,2022.
Kaijun Wu,Gabriela Arambulo Rodriguez,Marjana Zajc,Elodie Jacquemin,Michiels Clément,Albéric De Coster,Sébastien Lambot.A new drone-borne GPR for soil moisture mapping[J].Remote Sensing of Environment,2019.
Marko Malajner,Dusan Gleich,Peter Planinsic.Soil type characterization for moisture estimation using machine learning and UWB-Time of Flight measurements[J].Measurement,2019.
Jiaqi Han,Kebiao Mao,Tongren Xu,Jingpeng Guo,Zhiyuan Zuo,Chunyu Gao.A soil moisture estimation framework based on the CART algorithm and its application in China[J].Journal of Hydrology,2018.
Pedro Carmona,Francisco Climent,Alexandre Momparler.Predicting failure in the U.S. banking sector: An extreme gradient boosting approach[J].International Review of Economics and Finance,2019.
Carlos M. Guio Blanco,Victor M. Brito Gomez,Patricio Crespo,Mareike Ließ.Spatial prediction of soil water retention in a Páramo landscape: Methodological insight into machine learning using random forest[J].Geoderma,2018.
Sajjad Ahmad,Ajay Kalra,Haroon Stephen.Estimating soil moisture using remote sensing data: A machine learning approach[J].Advances in Water Resources,2009.
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621