Deep neural network algorithm for estimating maize biomass based on simulated Sentinel 2A vegetation indices and leaf area index

Accurate estimation of biomass is necessary for evaluating crop growth and predicting crop yield.Biomass is also a key trait in increasing grain yield by crop breeding.The aims of this study were(i)to identify the best vegetation indices for estimating maize biomass,(ii)to investigate the relationship between biomass and leaf area index(LAI)at several growth stages,and(iii)to evaluate a biomass model using measured vegetation indices or simulated vegetation indices of Sentinel 2A and LAI using a deep neural network(DNN)algorithm.The results showed that biomass was associated with all vegetation indices.The three-band water index(TBWI)was the best vegetation index for estimating biomass and the corresponding R2,RMSE,and RRMSE were 0.76,2.84 t ha−1,and 38.22%respectively.LAI was highly correlated with biomass(R2=0.89,RMSE=2.27 t ha−1,and RRMSE=30.55%).Estimated biomass based on 15 hyperspectral vegetation indices was in a high agreement with measured biomass using the DNN algorithm(R2=0.83,RMSE=1.96 t ha−1,and RRMSE=26.43%).Biomass estimation accuracy was further increased when LAI was combined with the 15 vegetation indices(R2=0.91,RMSE=1.49 t ha−1,and RRMSE=20.05%).Relationships between the hyperspectral vegetation indices and biomass differed from relationships between simulated Sentinel 2A vegetation indices and biomass.Biomass estimation from the hyperspectral vegetation indices was more accurate than that from the simulated Sentinel 2A vegetation indices(R2=0.87,RMSE=1.84 t ha−1,and RRMSE=24.76%).The DNN algorithm was effective in improving the estimation accuracy of biomass.It provides a guideline for estimating biomass of maize using remote sensing technology and the DNN algorithm in this region.     

病害胁迫下玉米LAI遥感反演研究

为了在病害发生条件下进行玉米LAI的遥感估算,针对41个不同抗性的玉米自交系品种,通过人工接种方法,获得了不同病害严重程度(1～9级)的LAI数据,同时采集了地面高光谱和无人机多光谱数据,构建了K近邻算法、支持向量机、梯度提升分类树和决策分类树分类模型对病害进行分类,对玉米种质资源抗病性进行了划分。基于不同玉米病害胁迫程度分类结果,采用随机森林回归、梯度提升回归树、极端梯度增强算法、轻量梯度提升机4种机器学习模型对玉米LAI进行反演,讨论了不同模型在病害胁迫下的鲁棒性。研究结果表明,对不同生育期玉米病害程度进行划分,基于地面高光谱识别精度分别为84.72%(梯度提升分类树)、47.67%(支持向量机)、55.05%(K近邻算法)、83.02%(决策分类树)。基于病害分类结果,本文利用无人机多光谱数据估算了不同病情等级胁迫下的玉米LAI。构建了4种集成学习模型对不同病情等级的LAI进行估算,4个LAI反演模型的总体反演精度(rRMSE)分别为：19.11%(梯度提升回归树)、15.94%(轻量梯度提升机)、14.51%(随机森林回归)和15.45%(极端梯度增强算法)。其中极端梯度增强算...     

Estimating maize seedling number with UAV RGB images and advanced image processing methods

Precision Agriculture - Accurately identifying the quantity of maize seedlings is useful in improving maize varieties with high seedling emergence rates in a breeding program. The traditional...     

无人机多光谱影像辐射一致性自动校正

针对一个架次内无人机影像由于光照度变化、拍摄角度等原因引起的相同地物点在不同影像上的辐射信息不一致的问题,验证了利用SIFT(scale invariant feature transform)算法匹配同名点,然后利用同名点灰度值的相关关系建立校正模型,再用该校正模型校正整幅影像的辐射一致性校正方法。对比评价了基于直方图匹配的色彩一致性校正方法、原始色彩空间辐射一致性校正、针对三波段影像的HSV(hue,saturation,value)色彩空间亮度一致性校正以及双边滤波去噪的效果。试验结果表明:基于直方图匹配的色彩一致性校正能在视觉上达到很好的效果,但是会造成校正后影像的灰度级严重缺失;基于同名点灰度值相关关系的校正模型能够很好地恢复待校正影像与基准影像的辐射一致性;HSV色彩空间亮度一致性校正能够在色彩上和辐射信息上与基准影像均达到很好的一致性,但只适用于三波段影像;双边滤波在去除噪声的同时,能够保持甚至提高校正后影像与基准影像的辐射一致性。     

基于HJ-CCD数据的水稻洪涝灾情诊断分析及长势监测

It has great significance to study quick monitoring of rice flood disaster and applying timely remedial measures in the disaster area.LAI is a very important physiological parameter in crop growth characterization index, which can reflect the crop growing information objectively.The existing methods of flood monitoring using remote sensing technology rarely consider the damage and the post disaster growth of rice.The HJ-CCD data take advantage of high temporal resolution and high spatial resolution remote sensing image, which can be used for gathering rice growing information during the critical period.The growth situation after rice flood disaster in Anhui Province was monitored using 3 screens HJ-CCD data as the data source on 16th July, 19th August, 26th August, 2009, respectively.The semi-empirical function model based on Beer-Lambert laws was constructed for this inversion LAI.And LAI were acquired in each stage after flood disaster, the trend of growth diagnosis dynamic change was analyzed and assessed by rice flood disaster evaluation indicator.At the same time, the 40 field investigate data were used to verify the model and the R2=0.4251, RMSE=2.053.The results show that LAI can be well evaluated the degree of rice flood disaster growth based on HJ-CCD data, and it is effective for monitoring and diagnosing rice flood disaster.The results provide a theoretical basis for rice flood disaster research, post disaster rehabilitation and recovery, and provide a theoretical basis for the implementation of targeted remedial measures at the same time.     

基于无人机成像高光谱影像的冬小麦LAI估测

利用无人机Cubert UHD185 Firefly成像光谱仪和ASD光谱仪获取了冬小麦挑旗期、开花期和灌浆期的成像和非成像高光谱以及LAI数据。首先,对比ASD与UHD185光谱仪数据光谱反射率,评价两者精度;然后,选取7个光谱参数,分析其与冬小麦3个生育期LAI的相关性,并使用线性回归和指数回归挑选出最佳估测参数;最后利用多元线性回归、偏最小二乘、随机森林、人工神经网络和支持向量机构建了冬小麦3个不同生育期LAI的估测模型。结果表明:UHD185光谱仪光谱反射率在红边区域与ASD光谱仪趋势一致性很高,反射率在挑旗期、开花期、灌浆期的R^2分别为0.9959、0.9990和0.9968,UHD185光谱仪数据精度较高;7种光谱参数在挑旗期、开花期、灌浆期与LAI相关性最高的参数分别是NDVI(r=0.738)、SR(r=0.819)、NDVI×SR(r=0.835);LAI-MLR为冬小麦LAI的最佳估测模型,其中开花期拟合性最好,精度最高(建模R^2=0.6788、RMSE为0.69、NRMSE为19.79%,验证R^2=0.8462、RMSE为0.47、NRMSE为16.04%)。     

基于无人机数码影像的冬小麦叶面积指数探测研究

叶面积指数(LAI)是评价作物长势的重要农学参数之一,利用遥感技术准确估测作物叶面积指数(LAI)对精准农业意义重大。目前,数码相机与无人机系统组成的高性价比遥感监测系统在农业研究中已取得一些成果,但利用无人机数码影像开展作物LAI估测研究还少有尝试。为论证利用无人机数码影像估测冬小麦LAI的可行性,本文以获取到的3个关键生育期(孕穗期、开花期和灌浆期)冬小麦无人机数码影像为数据源,利用数字图像转换原理构建出10种数字图像特征参数,并系统地分析了3个生育期内两个冬小麦品种在4种氮水平下的LAI与数字图像特征参数之间的关联性。结果表明,在LAI随生育期发生变化的同时,10种数字图像特征参数中R/(R+G+B)和本文提出的基于无人机数码影像红、绿、蓝通道DN值以及可见光大气阻抗植被指数(VARI)计算原理构建的数字图像特征参数UAV-based VARIRGB也有规律性变化,说明冬小麦的施氮差异不仅对LAI有影响,也对某些数字图像特征参数有一定影响;在不同条件(品种、氮营养水平以及生育期)下的数字图像特征参数与LAI的相关性分析中,R/(R+G+B)和UAV-based VARIRGB与LAI显著相关。进而,研究评价了R/(R+G+B)和UAV-based VARIRGB构建的LAI估测模型,最终确定UAV-based VARIRGB为估测冬小麦LAI的最佳参数指标。结果表明UAV-based VARIRGB指数模型估测的LAI与实测LAI拟合性较好(R2=0.71,RMSE=0.8,P0.01)。本研究证明将无人机数码影像应用于冬小麦LAI探测是可行的,这也为高性价比无人机遥感系统的精准农业应用增添了新成果和经验。     

北京山区森林叶面积指数季相变化遥感监测

森林叶面积指数(LAI)遥感反演,对于区域环境生态监测具有重要意义。该文以北京市西北山区鹫峰国家森林公园为研究区,获取多时相Landsat5 TM数据,并利用半球形照相机(Hemispherical Photography)同步获取森林LAI。使用3种植被指数(归一化植被指数NDVI、增强植被指数EVI和三梯度差植被指数TGDVI),分别建立单个观测时期及整个时期的LAI反演模型,通过相关性分析筛选出最佳模型。研究表明利用整个时期的LAI建立的模型精度较高,其中最好的是基于NDVI的LAI指数模型。利用该模型反演森林LAI,生成基于时间序列的北京山区森林LAI分布图。该研究进一步分析了阔叶林、针叶林和混交林3种情况,结果表明,与不分植被类型的LAI反演模型精度比较,阔叶林和混交林有所提高,而针叶林稍微下降,但模型精度均达到显著水平。     

我国棉田残膜污染危害与治理措施研究进展

地膜覆盖技术的应用为我国棉花产量提升做出重大贡献。但随着聚乙烯地膜的长期使用,土壤残膜污染问题日益突出,影响棉田土壤环境和棉花可持续发展。综述了我国棉田地膜残留现状、分布特征及其对棉花生长的危害,从土壤结构变化、水分迁移状况、有害物质释放、土壤物质代谢、微生物种群结构等方面系统总结了棉田残膜污染的危害机制,归纳了现阶段我国棉田残膜污染防控技术的研究进展及优势与不足,并对残膜污染防控策略及发展趋势进行了展望,为我国棉田残膜污染治理技术的研究提供科学参考。     

基于无人机高光谱分数阶微分的马铃薯地上生物量估算

以马铃薯为研究对象，利用无人机得到现蕾期、块茎形成期、块茎增长期、淀粉积累期和成熟期的高光谱数据，实测了地上生物量（Above ground biomass，AGB）数据。首先，利用成像高光谱影像提取每个生育期马铃薯冠层高光谱反射率数据；然后，利用分数阶微分计算高光谱0~2阶微分（间隔0.2），将各阶微分下的光谱数据与地上生物量进行相关性分析，挑选出相关系数绝对值较大的前9个微分波段；最后，利用多元线性回归（Multiple linear regression，MLR）、随机森林（Random forest，RF）和人工神经网络（Artificial neural network，ANN）3种方法构建基于分数阶微分光谱的整体、不同品种、不同密度和不同施肥下的马铃薯AGB估算模型，并进行了对比。结果表明：各生育期相关系数绝对值最大值出现的阶数不同，现蕾期为0.8阶微分（470nm）；块茎形成期为1.8阶微分（710nm）；块茎增长期和淀粉积累期为1.6阶微分（718、722、766nm）；成熟期为1.0阶微分（622nm）。相较于整数阶微分，高光谱分数阶微分与AGB的相关性更高，分数阶微分可以提高马铃薯AGB的估算精度。分析了不同生育期整体、不同品种、不同密度和不同施肥下的马铃薯AGB估算模型，3种方法中以9个微分波段为因变量的AGB估算在块茎增长期表现效果最好，利用MLR方法得到的模型精度最高、稳定性最强，其次为RF模型，ANN模型表现效果最差。不同生育期利用3种方法构建的AGB估算模型精度由大到小依次为块茎增长期、块茎形成期、淀粉积累期、现蕾期、成熟期。