应用MODIS数据监测大范围病虫害植被指数变化——以2010年澳大利亚蝗灾为例  

Using MODIS Data to Monitor Pest Vegetation Index Change in a Large Scale──Take the Locust Plague in Australia in 2010 for Example

作　　者：苗静 赵梓淇[2] 刘焕莉 李琳琳 徐亚琪 刘青[6] 辛明月 张璐 李国春[7] 

机构地区：[1]盘锦市气象局,辽宁盘锦124010 [2]中国气象局沈阳大气环境研究所,沈阳110166 [3]河北省气象信息中心,石家庄050021 [4]辽宁省气象科学研究所,沈阳110161 [5]盖州市气象局,辽宁盖州115200 [6]沈阳市气象局,沈阳110168 [7]沈阳农业大学农学院,沈阳110161

出　　处：《中国农学通报》2015年第14期148-155,共8页Chinese Agricultural Science Bulletin

基　　金：中央级公益性科研院所基本科研业务费"基于干旱胁迫条件的春玉米高光谱参数特征研究"(2013IAE-CMA06)

摘　　要：为了分析2010年澳大利亚新南威尔士州大范围蝗灾的发生范围和受灾程度,利用2008—2010年MODIS/Terra数据,通过植被生长期内前后同期的NDVI差值图像△NDVI判断2010年植被长势情况。研究结果表明:从整体上看,监测到的受灾范围与受灾程度上基本一致,能较好的反映出新南威尔士州的受灾情况;2010年9月新南威尔士州未受灾面积约为41万km2;受灾较轻区域面积约为5万km2;受灾较重区域的面积约为34万km2;受灾总面积约为39万km2,约占总面积的49%。通过与官方统计数据对比,监测到的受灾面积与官方统计数据相对误差为22%,造成误差的主要原因是像元的缺失与个别错误的像元点,导致受灾区域缺失的像元不能统计在受灾面积中和降低了受灾情况分类的精度。可得出结论,此方法适用于在对蝗灾发生范围和受灾程度的研究中。In order to analyze the range and damage of locusts plague that occurred in New South Wales,Australia, 2010, the author used MODIS/Terra date from 2008 to 2010 to judge the vegetation growth in 2010 through △NDVI value image, which were the different NDVI images of before and after vegetation growingperiod. The results showed that： from an overall perspective, the detected damage and actual range werebasically the same, which could reflect the disaster situation in New South Wales; the undamaged area wasalmost 410,000 km2; the light damaged area was about 50,000 km2; the seriously damaged area was about 340,000 km2; the total damaged area was about 390,000 km2, which accounted for 49% of the total area. Comparedto the official statistics, the relative error of damaged area was about 22%, the reasons were the lack of pixelsand some wrong pixels, and the missing pixels could not be included in the calculation of the damaged areaand reduced the precision of damage situation classification. This method could be used to study the range anddamage of locusts plague.

关 键 词：EOS/MODIS 蝗灾 NDVI 相对变化量 

分 类 号：P49[天文地球—大气科学及气象学]