黄土高原典型草原地上生物量估测模型

Estimation of aboveground biomass in the grassland of the Loess Plateau,Northern China

为了寻求有效的草地地上生物量估测方法和精确估测黄土高原典型草原草原地上生物量。于2014年8月中旬,在黄土高原典型草原草原地上生物量达到最大值,分别从单株水平和种群水平进行野外调查。以株高(H)和盖度(C)的复合因子(C×H)为自变量,通过回归分析,建立地上生物量估测模型,采用留一法对其精确性进行评估;并通过校正系数以及群落总生物量估测值和实测值比较单株水平和种群水平所建模型的精确性。结果表明:黄土高原典型草原草地,无论在单株水平还是种群水平,线性和幂函数对该区域生物量的拟合效果更好。估测模型检验结果表明,在单株水平各个物种的生物量估测值与实测值相关性较好,均达到了显著水平(P<0.05),其r值均大于0.6,总相对误差RS均小于10%,平均相对误差绝对值RMA(average absolute value of relative error)均小于30%,总生物量的实测值与估测值比较接近,校正系数均接近1;而在种群水平上,虽然各物种的生物量估测值与实测值相关性均达到了显著水平(P<0.05),但多数物种平均相对误差绝对值RMA大于30%,总相对误差RS(total relative error)均大于10%,总生物量的估测值均大于实测值,校正系数均偏离了1,说明在黄土高原典型草原通过单株水平建立的物种生物量估测模型的精度优于种群水平建立的物种生物量估测模型的精度。

In order to find an effective and precise method for estimating aboveground biomass and grassland biomass of the Loess Plateau, field surveys at the individual and population levels were conducted, and an estimation model was established. The model included the composite factor CH （product of vegetation coverage and height） as the independent variables, and regression analysis was used to estimate the grassland biomass of the Loess Plateau in mid-August of 2014. Simultaneously, the accuracy of the estimation models of aboveground biomass were assessed using the leave-one-out analysis method combined with the correlation coefficient （ r）, average absolute value of relative error （ RMA ）, total relative error （RS）, and correction factor. The results showed that all estimation models of aboveground biomass were linear and exponential functions at both the individual and population levels in the grassland of the Loess Plateau. The results of accuracy testing of the estimation model showed that the relationship between the estimated and measured biomass values were well correlated at the individual level, and reached a significant level （P〈0.05） with almost all r values greater than 0.6, RS values less than 10%, RMA less than 30%, and the correction coefficient close to 1. However, at the population level, ahhough the correlation between the estimated and measured biomass values was significant （P 〈 0.05）, the RMA of most species was greater than 30%, the RS values were greater than 10%, and the measured values were less than the estimated values with correction coefficients deviating from 1. Together, these results showed that the accuracy of estimation models of aboveground biomass established at the individual level is better than for those established at the population level in the Loess Plateau grassland.