基于遥感抽样的国家尺度农作物面积统计方法评估

国外从20世纪70年代已将遥感用于农业统计,中国从起步至今也有20多年的历史。遥感以其准确、及时、客观的优势推动了农业统计的进步,但对于遥感统计的精度评估一直不甚明确,影响了遥感监测的可信度和遥感技术优势的充分发挥。该文首先分析了目前国内外农业遥感统计的主要方法及其评估方式,针对中国大尺度农作物面积遥感统计方法的实际,采用多种指标对其进行评估,目的是对遥感统计调查的准确度予以明确的定义和计算。采用亚米级差分GPS采样获取足量样本的方法,对L andsat TM提取的水稻面积进行验证,基于原始的误差矩阵计算得出生产者精度为89.53%,用户精度为95.37%,总体精度为87.02%,地面实测数据和图像解译结果的相关系数为0.96;引入误差指标σ来直接反映分类结果较真值的总体误差,当σ〉0时,遥感解译结果较实际偏小,反之偏大,计算得到水稻遥感解译面积的σ值平均为0.084。

Accuracy assessment on the crop area estimating method based on RS sampling at national scale

Remote sensing technology has been used in agricultural statistics since early 1970s in developed countries such as USA and since late 1970s in China. It has greatly improved the efficiency with its accurate, timely and credible information. But agricultural monitoring using remote sensing has not yet been assessed with credible data in China and its accuracy seems not consistent and reliable to many users. The paper reviews different methods and the corresponding assessments of agricultural monitoring using remote sensing in developed countries and China, then assesses the crop area estimating method using Landsat TM remotely sensed data in Northeast China. The ground data were gathered with global positioning system and 40 sampling areas were used to assess the classification accuracy. The error matrix was constructed from which the accuracy was calculated. The producer accuracy, the user accuracy and total accuracy are 89.53%, 95.37% and 87.02%, respectively, and the correlation coefficient between the ground truth data and classification results is 0.96. A new error index a which measures how much the objective area estimation is apart from the ground truth data, is introduced and the average a of rice area estimation to the ground truth data is 0. 084.