西藏高原典型草地地上生物量遥感估算

Aboveground biomass estimate methods for typical grassland types in the Tibetan Plateau

准确估算草地地上生物量对合理规划区域畜牧业、评估草地植被的生态效益有重要意义。利用每月两次的野外调查资料和对应的MODIS植被指数,以GIS空间数据处理技术和多元统计分析方法等为手段,建立了西藏高寒草甸、高寒草原和温性草原3个典型草地类型的地上生物量遥感估算模型和方法。结果表明:MODIS植被指数更适合于高寒草甸和高寒草原的地上生物量估算,对于高寒草甸,最佳估算模型是基于归一化植被指数(normalized differ-ence vegetation index,NDVI)的三次多项式,其相关系数为0.82;对高寒草原,则是基于增强型植被指数(enhanced veg-etation index,EVI)的三次多项式,相关系数达0.83;由于温性草原存在很强的空间异质性,估算效果较其他2个草地类型差。MODIS植被指数对草地生长期鲜草生物量的估算和模拟效果要优于总地上生物量。在生长期,高寒草甸和高寒草原的鲜草生物量与植被指数之间的相关系数都大于0.8,最高达0.92;对温性草原,两者的相关系数也均大于0.67,其中,NDVI是高寒草甸和温性草原鲜草生物量估算的最佳植被指数,对高寒草原则是EVI。对同一草地类型,由于地上生物量差异较小,使得相比其他模型,线性或多项式回归模型更适合于西藏高原草地地上生物量的估算。

The estimation of aboveground biomass（AGB） is necessary for studying productivity,carbon cycles,nutrient allocation,fuel accumulation in terrestrial ecosystems,and rangeland management and monitoring.In this study,AGB estimate models were developed for 3 major grassland types（alpine meadow,alpine steppe,and temperate steppe） in the Tibetan Plateau by integrating AGB data collected from 6 sites in central Tibet in 2004 and concurrent vegetation index（VI） derived from MODIS data sets.The results show that MODIS VI is more suitable for estimates of alpine meadow and alpine steppe.The cubic polynomial regression based on NDVI is the best estimate model for alpine meadow with the correlation of 0.82,while for alpine steppe the model is EVI based cubic polynomial regression model with the correlation of 0.83;due to strong spatial heterogeneity of temperate steppe in central Tibet,the relationship between AGB and VI for temperate steppe is poorer than that for alpine grassland（alpine meadow,alpine steppe）.The MODIS VI based estimates of AGB during the growing season is better than the total biomass;during the growing season the correlation between AGB of alpine grassland（alpine meadow and alpine steppe） and MODIS VI is higher than 0.8 with a maximum value of 0.92,and for temperate steppe it is above 0.67 also.In contrast,NDVI is the best vegetation index for AGB estimates of alpine meadow and temperate steppe while EVI is the best for alpine steppe.Due to unique spectral response of green vegetation,MODIS VI is more suitable for estimates of AGB during the growing season,and the accuracy of AGB estimates will decrease during the non-growing season.For the same types of grassland with less difference in AGB,the linear or polynomial regression model is more suitable for modeling or estimating AGB in the Tibetan Plateau than other estimate models.