基于高光谱和数据挖掘的油菜植株含水率定量监测模型

为了构建监测效果更好、更具普适性的油菜植株含水率(Plant water content,PWC)定量监测模型,以油菜品种浙杂903、宁油22和宁杂1818为试验材料,设置2个施肥水平和3个水分处理,基于2019-2020年和2020-2021年生长季田间试验资料,在PWC的高光谱响应敏感波段范围采用逐步回归(Stepwise regression, SR)分析、连续投影算法(Successive projection algorithm, SPA)、竞争自适应加权算法(Competitive adaptive reweighted sampling, CARS)以及减量精细采样法(Reduced precise sampling method, RPSM)深度挖掘高光谱数据,通过筛选最优波段组合与光谱指数,基于线性回归(Linear regression, LR)、BP神经网络(Back-propagation neural network, BPNN)和支持向量机回归(Support vector regression, SVR)方法构建并比较油菜植株含水率监测模型。结果表明,针对油菜PWC监测,SR分析筛选的最优波段组合为730 nm、986 nm和1 071 nm, SPA法分析筛选的最优波段组合为686 nm、695 nm、707 nm、746 nm、964 nm、1 065 nm和1 069 nm, CARS法分析筛选的最优波段组合为694 nm、695 nm、696 nm、863 nm、864 nm、893 nm、973 nm、986 nm、1 050 nm和1 071 nm。RPSM筛选的最优光谱指数是归一化差值光谱指数(R981,R894)和比值光谱指数(R981,R894),其利用的波段均位于近红外波段。前述3个方法筛选的波段变量更多,蕴含的信息更全面,估测精度普遍优于光谱指数。建模分析结果表明,SPA-LR模型、SPA-BP模型、SPA-SVR模型均能实现油菜PWC的精确监测,经检验,其估测值和实测值的R2分别为0.693、0.940、0.841,均方根误差(RMSE)分别为1.623%、1.836%和1.227%。结果证明高光谱数据具备深度挖掘价值,运用全波段光谱分析方法能够在降维的同时保留有效信息,利用筛选出的波段组合构建线性或非线性模型,均能实现大田条件下全生育期油菜植株含水率的定量监测。

The Variability of the Snow and Ice Melt in Alpine Rivers in Northwestern China

The study of snow and ice melt(SIM) is important in water-scarce arid regions for the assessment of water supply and quality. These studies involve unique difficulties, especially in the calibration of hydro-models because there is no direct way to continuously measure the SIM at hydrostations. The recursive digital filter(RDF) and the isotopic hydro-geochemical method(IHM) were coupled to separate the SIM from eight observed series of alpine streamflows in northwestern China.Validation of the calibrated methods suggested a good capture of the SIM characteristics with fair accuracy in both space and time. Applications of the coupled methods in the upper reaches of the Hei River Basin(HRB) suggested a double peak curve of the SIM fraction to streamflow for the multi-component recharged(MCR) rivers, while a single peak curve was suggested for the rainfall-dominant recharged(RDR)rivers. Given inter-annual statistics of the separation,both types of the alpine rivers have experienced an obvious decrease of SIM since 1960 s. In the past 10 years, the SIM in the two types of rivers has risen to the levels of the 1970 s, but has remained lower than the level of the 1960 s. The study provided a considerable evidence to quantify the alpine SIM based on the separation of observed data series at gauge stations. Application of the coupled method could be helpful in the calibration and validation of SIM-related hydro-models in alpine regions.