引入地形因子的黑土区大豆干生物量遥感反演模型及验证

发布时间：2018-01-16 12:13

  本文关键词：引入地形因子的黑土区大豆干生物量遥感反演模型及验证　出处：《农业工程学报》2017年16期 　论文类型：期刊论文

  更多相关文章： 遥感 作物 模型 大豆 地上干生物量 地形因子

【摘要】：为了对田块尺度农作物地上干生物量进行估测,提高大豆地上干生物量反演模型的精度和稳定性,该文获取了研究区地块2016年7、8月份的SPOT-6多光谱数据,并测定不同地形坡位的大豆地上干生物量,以归一化植被指数(normalized difference vegetation index,NDVI)和增强型植被指数(enhanced vegetation index,EVI)为输入量,建立田块尺度大豆地上干生物量一元线性回归模型;加入与地上干生物量相关的地形因子,建立逐步多元回归和神经网络多层感知反演模型。结果表明:1)使用传统的单一植被指数模型预测大豆地上干生物量有可行性,但模型精度和稳定性不高。2)加入地形因子(海拔、坡度、坡向)的神经网络多层感知器模型,有较高的精度和可靠性,模型准确度达到90.4%,验证结果显示预估精度为96.2%。反演结果与地块的地形、地貌、气温和降水特征基本吻合,反映了作物长势的空间分布特征,可以为田块尺度大豆地上干生物量动态监测和精准管理,提供借科学依据。
[Abstract]:In order to estimate the aboveground dry biomass of field scale crops and improve the accuracy and stability of soybean aboveground dry biomass inversion model, this paper obtained the study area block on 2016 7. In August, the SPOT-6 multispectral data were obtained, and the dry aboveground biomass of soybean at different topographic slopes was measured. Normalized difference vegetation index is used as a normalized vegetation index. NDVI) and enhanced vegetation index (EVI) are the inputs. A linear regression model of aboveground dry biomass of field scale soybean was established. Topographic factors related to aboveground dry biomass were added. The stepwise multivariate regression and neural network multilayer perception inversion models were established. The results showed that the traditional single vegetation index model was feasible to predict the aboveground dry biomass of soybean. However, the model accuracy and stability are not high. 2) the neural network multilayer perceptron model with terrain factors (elevation, slope, slope direction) has high accuracy and reliability, and the accuracy of the model reaches 90.4%. The results show that the prediction accuracy is 96.2.The inversion results are basically consistent with the terrain, geomorphology, temperature and precipitation characteristics of the block, reflecting the spatial distribution characteristics of crop growth. It can provide scientific basis for dynamic monitoring and accurate management of field scale soybean aboveground dry biomass.
【作者单位】： 东北农业大学资源与环境学院;中国科学院东北地理与农业生态研究所;
【基金】：国家自然科学基金项目(41671438;41501357) “中国科学院东北地理与农业生态研究所”引进优秀人才项目
【分类号】：S565.1;TP79
【正文快照】： 0引言作物地上生物量是反映作物生长状况的重要指标,作物生物量估算是服务现代农业的一项重要内容,及时准确的生物量模拟对国家农业决策、农田生产管理、粮食仓储安全等都有重要意义[1]。传统地面调查监测的统计模型与物理模型难以实用化,无论是从时间还是从空间角度来获取生，

本文编号：1433065