Abstract

This study compared the traditional regression models and support vector machine (SVM) for estimation of aboveground biomass (ABG) of an agro-pastoral ecology using vegetation indices derived from Landsat 8 satellite data as explanatory variables . The area falls in the Shivpuri Tehsil of Madhya Pradesh, India, which is predominantly a semi-arid tract of the Bundelkhand region. The Enhanced Vegetation Index-1 (EVI-1) was identified as the most suitable input variable for the regression models, although the collective effect of a number of the vegetation indices was evident. The EVI-1 was also the most suitable input variable to SVM, due to its capacity to distinctly differentiate diverse vegetation classes. The performance of SVM was better over regression models for estimation of the AGB. Based on the SVM-derived and the ground observations, the AGB of the area was precisely mapped for croplands, grassland and rangelands over the entire region.

摘要

本研究比较了传统回归模型和支持向量机 (SVM) 对农牧生态地上生物量 (ABG) 的估计，使用来自 Landsat 8 卫星数据的植被指数作为解释变量。该地区位于印度中央邦的 Shivpuri Tehsil，该地区主要是本德尔坎德地区的半干旱地区。增强型植被指数-1 (EVI-1) 被确定为回归模型最合适的输入变量，尽管一些植被指数的集体效应很明显。EVI-1 也是 SVM 最合适的输入变量，因为它能够明显区分不同的植被类别。在估计 AGB 时，SVM 的性能优于回归模型。基于 SVM 导出的和地面观测，