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.     

基于机载LiDAR数据的玉米叶面积指数反演

以机载LiDAR离散点云数据为数据源,基于植被冠层孔隙率与叶面积指数的关系,提出一种反演大田玉米叶面积指数的方法。对反演LAI和实测LAI进行对比分析,结果表明:基于Axelsson改进的不规则三角格网加密方法可以将地面点和非地面点分开,结合高分辨率影像能够提取出玉米冠层点云;基于孔隙率反演LAI,尼尔逊参数的选择对结果影响很大,利用扫描天顶角模拟尼尔逊参数,LAI反演结果接近于真实情况。利用机载LiDAR点云数据能精确地反演大田玉米LAI,该研究方法适用于中等高度的农作物,可以扩展到甜菜、甘蔗等其他中等高度农作物。     

地下水埋深对夏玉米根冠生长和耗水量的影响

利用排水式蒸渗仪,借助自制的Mariotte瓶装置,通过设置6种地下水埋深控制处理(地下水位埋深分别为0.2、0.4、0.6、0.8、1.01、.2m),探讨了不同地下水埋深对夏玉米的地上部分、根系生物量及耗水量的影响。结果表明,夏玉米株高和冠层叶面积随地下水埋深减小有增加的趋势,但是当地下水埋深减小到一定程度时就会抑制株高、叶面积,地下水埋深0.6m处理株高和叶面积系数(LAI)最大。各土层根系及其总生物量随地下水埋深增大而增大;地上部总生物量与地下部根生物量的比值随地下水埋深的增大呈明显减少的趋势。夏玉米全生育期和各阶段耗水量分别与地下水埋深呈较好的负相关关系,达到极显著水平(P<0.01);地下水补给量占耗水量的比例随地下水埋深的增大而逐步降低。研究结果可为江淮丘陵区夏玉米灌溉制度的制定及农田排水工程的设计提供参考依据。     

西安市生态环境植被信息的遥感反演

西安市自然生态环境问题突出,植被信息作为地表生态环境评价与监测的重要参数之一,对区域生态环境的监测及生态环境建设具有重要意义。为此,通过LandsatTM影像提取的植被指数与叶面积指数关系的相关分析,确定适合反映研究区植被信息的VI。结果证明,用NDVI作参考来监测植被状况是合理的,相关系数为0.7205。基于此进一步分析了植被指数与生态环境参数的关系,为西安市的生态环境监测提供依据。     

冬小麦不同株型品种光谱响应及株型识别方法研究

以直立和平展2种株型的冬小麦品种为材料，研究了它们的光谱响应以及田间植被覆盖度的差异，探讨了利用冠层光谱反射率、光谱特征参量NDVI及植被覆盖度识别小麦株型的方法。结果表明，（1）小麦不同株型品种在近红外波段（700～1300 nm）光谱反射率有明显差异，生育前期平展型品种高于直立型品种，并以拔节期的差异为最显著，随着生育进程差异逐渐变小。拔节期是进行株型识别的最佳时期，并且此期冠层的敏感波段680 nm和760～900 nm的反射率在2种株型品种之间差异明显。（2）小麦冠层叶面积指数（LAI）与归一化差异植被指数NDVI(680,890)呈正相关，并且不同生育阶段其相关程度有差异，这是利用NDVI和植被覆盖度(COV)识别不同株型的基础。（3）相同COV条件下，直立型品种的NDVI高于平展型品种的NDVI，并且随着COV的增加，差异逐渐变小，二者的变化关系体现了直立型品种株型紧凑和平展型品种株型披散的特点，利用NDVI和COV的关系可以对株型进行识别，以小麦拔节期为最佳识别阶段，此期2种株型品种的NDVI具有显著差异（P＜0.05）。     

基于遥感技术的气象因素变化影响水稻单产定量研究

以黑龙江省五常市为研究区域，应用在水稻移栽期至成熟期选择的系列MODIS影像反演NDVI，通过NDVI间接反演LAI，并逐日拟合水稻全生育期的LAI，结合SIMRIW模型，计算研究区域2006年低温影响下的水稻单产。经演算，水稻单产值为5411．74kg／hm^2，是实际值的84％。研究结果表明应用高时间分辨率MODIS图像能够准确反演并拟合逐日LAI，可以为冷害影响下水稻单产的研究提供参考。     

水稻叶面积指数及产量信息的空间结构性分析

通过对水稻抽穗期叶面积指数及产量信息的采样研究,探讨了叶面积指数及产量信息的空间结构性,并建立了半方差函数模型,结果表明该变量具有明显的区域化变量特征和较好的空间结构特征.该文引入区域化变量理论,弥补了单纯采用经典概率统计法对作物信息进行分析的片面性.水稻抽穗期叶面积指数与产量信息之间呈抛物线关系,相关性达显著水平,说明可以通过对叶面积指数的科学调控,使一定尺度范围内的水稻产量获得全面提高.对作物信息进行空间结构性和定量化研究为精确农业的实施提供了必要的技术支撑.     

基于MODIS反演逐日LAI及SIMRIW模型的冷害对水稻单产的影响研究

该文旨在将遥感技术与水稻作物模型SIMRIW相结合,以黑龙江省五常市为例,研究冷害对水稻单产的影响。通过在水稻移栽期至成熟期选取的系列MODIS图像计算NDVI,进而反演水稻全生育期逐日LAI,结合SIMRIW模型计算水稻单产。计算结果表明2006年五常市水稻单产值为5411.74 kg/hm^2,为实际值的83%;而在4种用于LAI反演的统计模型中,抛物线模型精度最好;整体拟合法在逐日LAI计算中要优于分段拟合法。这说明应用MODIS能够准确反演并拟合逐日LAI,它可为冷害影响水稻单产的评价研究提供参考。     

基于夏玉米冠层内辐射分布的不同层叶面积指数模拟

为了模拟夏玉米冠层内各层叶面积指数垂直分布,光合有效辐射（photosynthetically active radiation, PAR）是研究作物群体光合作用和长势的重要特征参数,阐明冠层内PAR的垂直分布规律与冠层结构等参数之间的相关关系,可为遥感定量反演冠层结构参数提供模型基础。该文基于PAR在冠层内的辐射传输规律结合冠层结构模拟不同太阳高度角的PAR透过率垂直分布模型,并用地面冠层分析仪测量值进行验证,结果表明模型对封垄前玉米抽雄期冠层内PAR透过率垂直分布模拟精度较高。通过不同太阳高度角PAR透过率的垂直分布模型结合消光系数运用不同算法分别反演层叶面积指数（leaf area index, LAI）,并与不同高度层LAI实测值进行比较。结果显示：Bonhomme& Chartier算法反演不同高度层LAI精度较高,上层均方根误差（root mean square error,RMSE）为0.18,中层RMSE为0.55,下层RMSE为0.09。不同太阳高度角反演结果存在差异,30°和45°高度角均能较好地反演下层LAI,RMSE分别为0.11与0.09;30°高度角反演中层LAI精度较高,RMSE为0.30;45°高度角反演上层LAI精度较高,RMSE为0.18。结果表明基于不同太阳高度角构建的层LAI反演模型更适于实现夏玉米不同高度层LAI的遥感估算。该研究可为模拟垄行结构冠层内LAI垂直分布提供参考。     

Development of a ground truthing method for determination of rangeland biomass using canopy reflectance properties

Veld condition assessment and establishment of grazing capacity norms provide guidelines for the formulation of sustainable practices. However, conventional monitoring methods are becoming inadequate to meet future challenges, where quantification of spatial and temporal variation is required. This study proposes an on-site remote sensing method for monitoring above-ground biomass in rangelands. A preliminary model was formulated, based on simple regression relationships between canopy reflectance properties and aboveground biomass. This model was validated in semi-arid environments (Nama-karoo and Kalahari) within the framework of spatial and temporal experimental trials. Model accuracy was found to be primarily a function of canopy structure and vegetation composition where increases in dwarf shrub presence resulted in greater variations of both NDVI (Normalized Difference Vegetation Index) and LAI (Leaf Area Index) measurements. Temporal variation in model accuracy could also be observed which seemed to be associated with precipitation events. It was concluded that the proposed remote sensing method has potential as a ground truthing technique for determination of rangeland biomass. Indications are that this method is well suited for use in grass dominated veld types. With further refinement, implementation of this technique should also be possible in dwarf shrublands.