Extraction of soybean planting area based on feature fusion technology of multi-source low altitude unmanned aerial vehicle images

Soybean is an important food and oil crop in the world. It is of great significance to statics the planting scale accurately for optimizing the crop planting structure and world food security. The technology of accurately extracting the area of soybean planting areas at the field scale using UAV images combined with deep learning algorithms is important for the application. In this study, firstly, RGB images and multispectral images (RGN) were acquired simultaneously by the quad-rotor UAV DJ-Phantom4 Pro at a flying height of 200 m. And the features were extracted from the RGB and RGN images. Further, the fusion image of RGB + VIs and the fusion image of RGN + VIs were obtained by concatenating the band reflectivity of the original image with the calculated Vegetation Index (VI). Then, the soybean planting area was segmented from the feature fusion images by U-Net. And the accuracy of the two sensors was compared. The results showed that the Kappa coefficients obtained based on RGB image, RGN image, CME(the combination of CIVE, MExG, and ExGR), ODR(the combination of OSAVI, DVI, and RDVI), RGB + CME(the combination of RGB and CME), and RGN + ODR(the combination of RGN and ODR) were 0.8806, 0.9327, 0.8437, 0.9330, 0.9420, and 0.9238, respectively. The Kappa coefficient of the combination of the original image and the vegetation index was higher than the original image, indicating that the vegetation index calculation was beneficial to improving the soybean recognition accuracy of the U-Net model. Among them, the precision of the soybean planting area extracted from RGB + CME was the highest, and the Kappa coefficient was 0.9420. Finally, the soybean recognition accuracy of U-Net was compared with the results of DeepLabv3+, Random Forest, and Support Vector Machine. The accuracy of U-Net was the best. It can be concluded that this research proposed the method that was using U-Net trained the fusion image of the original image and vegetation index feature fusion image obtained by the UAV platform, which can effectively segment soybean planting areas. The conclusion of this work provided important technical support for farm level, family cooperatives, and other business entities to manage finely soybean planting and production at low cost.     

基于小波分析的大豆叶绿素a含量高光谱反演模型

 2003和2004年分别在长春市良种场和中国科学院海伦黑土生态实验站实测了大田耕作与水肥耦合作用下大豆（Glycine max）冠层高光谱反射率 与叶绿素a含量数据,对光谱反射率、微分光谱与叶绿素a含量进行了相关分析;采用归一化植被指数(Normalized diffe rence vegetation index, NDVI)、土壤调和植被指数(Soil-adjusted vegetation index, SAVI)、再归一植被指数(Renormalized difference vegetation index, RDVI)、第二修正比值植被指数(Modified second ratio index, MSRI)等建立了大豆叶绿素a反演模型;应用小波分析对采集的光谱反 射率数据进行了能量系数提取,并以小波能量系数作为自变量进行了单变量与多变量回归分析,对大豆叶绿素a进行了估算。研究结果表明,大 豆叶绿素a 与可见光光谱反射率相关性较好,并在红光波段取得最大值(R²>0.70),但在红边处,微分光谱与大豆叶绿素a的相关性较反射率好 得多,在其它波段则相反;由NDVI、SAVI、RDVI、MSRI等植被指数建立的估算模型可以提高大豆叶绿素a的估算精度（R²>0.75）;小波能量系 数回归模型可以进一步提高大豆叶绿素a含量的估算水平,以一个特定小波能量系数作为自变量的回归模型,大豆叶绿素a回归决定系数R²高达 0.78;多变量回归分析结果表明,大豆叶绿素a实测值与预测值的线性回归决定系数R²均高达0.85。以上结果表明, 小波分析可以对高光谱进 行特征变量提取,并可在一定程度上提高大豆生理参数反演精度。     

基于无人机高清数码影像和高光谱遥感数据反演大豆典型生育期氮平衡指数

氮平衡指数(NBI)是反映作物长势的重要指标之一.通过测量NBI可以快速监测作物氮肥盈亏状况,为农业生产和管理提供精准信息.本文以无人机高清数码影像和高光谱遥感数据,以及地面实测大豆NBI数据为基础,分析大豆从开花期到成熟期,原始光谱和红外、近红外波段的导数光谱与NBI的相关性,筛选敏感波段并计算植被指数.采用经验模型法构建NBI反演模型,通过分析验证模型的决定系数(R^2)和均方根误差(RMSE),得出最佳反演模型.结果表明:大豆NBI与导数光谱反射率的相关性好于与原始光谱反射率的相关性;本文筛选的14个植被指数中,除了导数光谱光化学植被指数与大豆NBI呈不显著相关外,其余13个植被指数与大豆NBI呈极显著相关;利用13个植被指数构建NBI反演模型,并分析模型反演精度,结果显示,利用导数光谱差值植被指数构建NBI反演模型的精度最高,R^2和RMSE分别为0.771和3.077,利用该模型生成大豆典型生育期NBI分布图,能够反映大豆的长势状况.通过多载荷无人机获取的高清数码影像和高光谱遥感数据进行NBI估算,能够实时、动态、非破坏性、快速有效地监测大豆氮素营养状况,可为大豆氮肥精确管理提供简便实用的方法.     

大豆异黄酮微波干法辅助提取及其机理研究

考察大豆异黄酮的微波光波组合无溶剂提取方法,发现微波光波提取干法仅用9.4%的N,N-二甲基甲酰胺DMF作为能量传递介质,功率800 W(微波55%与光波45%)加热6 min后,乙醇萃取得总黄酮.大豆苷元的提取率为0.14%,与相应的常规提取法接近,该法有操作简单快速,成本低,环境污染小等优点.利用高倍荧光显微镜FM...     

UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest

Development of vegetation communities in areas of Antarctica without permanent ice cover emphasizes the need for effective remote sensing techniques for proper monitoring of local environmental changes. Detection and mapping of vegetation by image classification remains limited in the Antarctic environment due to the complexity of its surface cover, and the spatial heterogeneity and spectral homogeneity of cryptogamic vegetation. As ultra-high resolution aerial images allow a comprehensive analysis of vegetation, this study aims to identify different types of vegetation cover (i.e., algae, mosses, and lichens) in an ice-free area of  Hope Bay, on the northern tip of the Antarctic Peninsula. Using the geographic object-based image analysis (GEOBIA) approach, remote sensing data sets are tested in the random forest classifier in order to distinguish vegetation classes within vegetated areas. Because species of algae, mosses, and lichens may have similar spectral characteristics, subclasses are established. The results show that when only the mean values of green, red, and NIR bands are considered, the subclasses have low separability. Variations in accuracy and visual changes are identified according to the set of features used in the classification. Accuracy improves when multilayer information is used. A combination of spectral and morphometric products and by-products provides the best result for the detection and delineation of different types of vegetation, with an overall accuracy of 0.966 and a Kappa coefficient of 0.946. The method allowed for the identification of units primarily composed of algae, mosses, and lichens as well as differences in communities. This study demonstrates that ultra-high spatial resolution data can provide the necessary properties for the classification of vegetation in Maritime Antarctica, even in images obtained by sensors with low spectral resolution.     

微波提取苦荞麦麸皮总黄酮工艺研究

本文对苦荞麦麸皮总黄酮微波提取工艺进行了研究。试验结果表明:微波提取的最佳工艺条件为微波功率中档,微波加热120 s,乙醇浓度80%,料液比1:50,该工艺条件下总黄酮得率达5.51%;与传统提取方法相比,微波提取法具有节省时间、节约能量、提取效率高、控制方便等优点。     

基于地形因素的新疆荒漠植被-气候模型应用研究

本研究在新疆荒漠植被型分类的基础上,用植被与气候Holdridge生命带模型进行荒漠植被型的模拟,并用Kappa检验系数进行结果检验,模拟结果很差(0.19),将地形作为模拟模型具体考虑的一个因素,对重新分类的气候区进行二次植被模拟。二次模拟结果Kappa检验系数平均值为0.45,二次模拟整体荒漠植被型模拟结果的Kappa检验系数为0.64,极大地提高了模型模拟的准确度。模型模拟准确度的提高在于将影响新疆水分分配的地形因素作为改进Holdridge生命带模型的参数,该参数的引入为提高Holdridge生命带模型的准确度提供了新的思路,也为较准确地模拟新疆地区的植被提供了新途径。     

基于多时相MODIS数据的东北地区一季稻面积提取

利用2007-2008年MODIS/Terra陆表反射率数据提取的归一化植被指数(NDVI)、增强植被指数(EVI)及陆表水分指数(LSWI),分析了东北地区水稻、旱田、林地、湿地和水体5种不同下垫面在作物生长季的动态变化,同时结合水稻发育期观测数据,建立了东北地区一季稻面积提取模型,并制作了东北地区水稻种植面积分布图.以辽宁盘锦为试验区,利用ALOS数据提取结果对该模型进行了试验,提取精度达到89.5％,结果表明该方法可以较高精度进行大范围的一季稻种植面积提取.     

浙江省植被NDVI动态及其对气候的响应

利用GIMMS和MODIS两种归一化植被指数(NDVI)资料反演了1982—2010年浙江植被覆盖状况,结合同期研究区63个气象站点的气温、降水和湿润指数等气候指标,分析了该地区植被年际变化、月际变化及其对气候要素的响应特征。结果表明:(1)研究期间,浙江气候总体呈暖干化趋势,植被覆盖缓慢下降,主要是由于森林植被遭破坏,农业生产活动受抑制影响所致,其中NDVI显著减少的地区约占全省陆域面积的29.1%,主要发生在6—11月;(2)降水量及干湿程度对浙江植被NDVI年变化起着决定性作用。植被与气候要素年变化相关分析发现,NDVI与湿润指数关系较降水、气温更为密切,两者相关及偏相关系数均通过0.05水平的置信度检验,这表明在年际尺度上,湿度的增加增大了植被的生长势,有利于植被生长;(3)植被与气候要素月变化分析表明冬季的热量供给是影响浙江植被生长的重要因子,而植被变化对夏季降水和干湿程度的最大响应为滞后两个月;(4)农业生产水平的提高使得农作物种植区NDVI有所增加,人类活动对浙江植被覆盖的影响不可忽视。     

大豆田银纹夜蛾系统控制研究

１９９３￣１９９６年以系统控制为基本技术原理,研究了豆田１１种可控因素对大豆银纹夜蛾,天敌和产量的综合效应,结果表明,对银纹夜蛾影响大的因素是种植方式,微肥,播期和钾素;对天敌影响最大的是种植方式;对大豆产量影响大的是种植方式;播期,品种和微肥。     

Optimization of dynamic-microwave assisted enzymatic hydrolysis extraction of total ginsenosides from stems and leaves of panax ginseng by response surface methodology

Abstract

Ginseng stems and leaves (GSAL) are abundant in ginsenosides compounds. For efficient utilization of GSAL and the enhancement of total ginsenosides (TG) compound yields in GSAL, TG from GSAL were extracted, using dynamic-microwave assisted extraction coupled with enzymatic hydrolysis (DMAE-EH) method. The extraction process has been simulated and its main influencing factors such as ethanol concentration, microwave temperature, microwave time and pump flow rate have been optimized by response surface methodology coupled with a Box-Behnken design(BBD). The experimental results indicated that optimal extraction conditions of TG from GSAL were as follows: ethanol concentration of 75%, microwave temperature of 60°C, microwave time of 20?min and pump flow rate of 38 r/min. After experimental verification, the experimental yields of TG was 60.62?±?0.85?mg?g^?1, which were well agreement with the predicted by the model. In general, the present results demonstrated that DMAE-EH method was successfully used to extract total ginsenosides in GSAL.     

胶束介导联合超声—微波辅助法提取喜树叶中喜树碱及羟基喜树碱

为了寻找一种新的方法从喜树叶中提取喜树碱和羟基喜树碱,充分利用喜树资源,以喜树叶粉末作为提取原料,采用超声—微波辅助提取技术提取喜树叶中活性成分喜树碱和羟基喜树碱。采用响应面优化方法设计,分别考察微波时间、料液比、微波功率、表面活性剂的浓度4个因素对总提取率的影响,优化得到最佳提取工艺条件。研究结果表明：当微波时间为10.5 min、料液比为1∶60、微波功率为850 W、表面活性剂浓度为 8.5 g·L^-1时总提取率达到最佳。最佳工艺下总提取率为0.056 4%。     

中国大豆品种生态区划的修正Ⅱ.各区范围及主要品种类型

根据我国各地256份代表性大豆地方品种在南京分期播种,延长或缩短光照长度各处理条件下的生育期表现,结合供试材料来源地的地理与气候条件,播种季节类型,熟期组类型以及光温反应特性等因素,将我国大豆品种生态区划分为：北方一熟制春作大豆品种生态区（Ⅰ）,黄淮海二熟制春夏作大豆品种生态区（Ⅱ）,长江中下游二熟制春夏作大豆品种生态区（Ⅲ）,中南多熟制春夏秋作大豆品种生态区（Ⅳ）,西南高原二熟制春夏作大豆品种生态区（Ⅴ）,华南热带多熟制四季大豆品种生态区（Ⅵ）等六大区,10亚区,并阐述各区的一般生态条件及代表生态类型。     

微波法提取枸杞叶甜菜碱工艺的研究

研究微波法提取枸杞叶中甜菜碱的最佳工艺,考察工艺参数对枸杞叶中甜菜碱提取率的影响.以甜菜碱提取率为指标,通过L9(3(4))正交实验与方差分析优选出枸杞叶中甜菜碱最佳提取工艺条件.结果表明,最佳工艺为固液比为(g:ml)1:10,20 min,微波功率200 w.枸杞叶中甜菜碱最佳提取率平均值可高达4.48%.该工艺简...     

Noncrop features and heterogeneity mediate overwintering bird diversity in agricultural landscapes of southwest China

Farmland birds are of conservation concerns around the world. In China, conservation management has focused primarily on natural habitats, whereas little attention has been given to agricultural landscapes. Although agricultural land use is intensive in China, environmental heterogeneity can be highly variable in some regions due to variations in crop and noncrop elements within a landscape. We examined how noncrop heterogeneity, crop heterogeneity, and noncrop features (noncrop vegetation and water body such as open water) influenced species richness and abundance of all birds as well as three functional groups (woodland species, agricultural land species, and agricultural wetland species) in the paddy‐dominated landscapes of Erhai water basin situated in northwest Yunnan, China. Birds, crop, and noncrop vegetation surveys in twenty 1 km × 1 km landscape plots were conducted during the winter season (from 2014 to 2015). The results revealed that bird community compositions were best explained by amounts of noncrop vegetation and compositional heterogeneity of noncrop habitat (Shannon–Wiener index). Both variables also had a positive effect on richness and abundance of woodland species. Richness of agricultural wetland species increased with increasing areas of water bodies within the landscape plot. Richness of total species was also greater in the landscapes characterized by larger areas of water bodies, high proportion of noncrop vegetation, high compositional heterogeneity of noncrop habitat, or small field patches (high crop configurational heterogeneity). Crop compositional heterogeneity did not show significant effects neither on the whole community (all birds) nor on any of the three functional groups considered. These findings suggest that total bird diversity and some functional groups, especially woodland species, would benefit from increases in the proportion of noncrop features such as woody vegetation and water bodies as well as compositional heterogeneity of noncrop features within landscape.     

不同种植模式对西南坡地水土保持及作物产值的影响

通过3年定位监测试验研究了小麦/玉米/大豆全程免耕全程秸秆覆盖、小麦/玉米/大豆半程免耕半程秸秆覆盖、小麦/玉米/大豆全程翻耕不覆盖秸秆和小麦/玉米/甘薯全程翻耕不覆盖秸秆4种不同种植模式对西南坡地水土保持、土壤肥力及作物产值的影响.结果表明：在水土保持方面,小麦/玉米/大豆全程免耕全程秸秆覆盖模式的3年平均土壤侵蚀量和地表径流量最低,分别为1189 kg·hm^-2和215 m³·hm^-2,显著低于其他处理,比小麦/玉米/甘薯全程翻耕不覆盖秸秆模式分别低10.6%和84.7%.在土壤肥力方面,3种小麦/玉米/大豆模式都能增加土壤有机质、全氮、速效钾和碱解氮含量,以小麦/玉米/大豆全程免耕全程秸秆覆盖模式增加幅度最大,分别增加15.7%、18.2%、55.2%和25.9%,显著高于其他模式,小麦/玉米/大豆半程免耕半程秸秆覆盖模式次之,小麦/玉米/甘薯全程翻耕不覆盖秸秆模式最低.在作物产值方面,以小麦/玉米/大豆全程免耕全程秸秆覆盖模式的3年平均总产值和纯收入最高,分别为18809元·hm^-2和12619元·hm^-2,比其他几个处理分别增加2.2%～20.6%和3.8%～32.9%,总体效益最好.总之,小麦/玉米/大豆模式比传统的小麦/玉米/甘薯模式能更好地保持水土,减少土壤侵蚀量和地表径流量,增加土壤肥力和作物产值.     

A field study on heavy metals phytoattenuation potential of monocropping and intercropping of maize and/or legumes in weakly alkaline soils

The study focused on the phytoattenuation effects of monocropping and intercropping of maize (Zea mays) and/or legumes on Cu, Zn, Pb, and Cd in weakly alkaline soils. Nine growth stages of monocropping maize were chosen to study the dynamic process of extraction of heavy metals. The total content of heavy metals extracted by the aerial part of monocropped maize increased in a sigmoidal pattern over the effective accumulative temperature. The biggest biomass, highest extraction content, and lowest heavy metals bioaccumulation level occurred at physiological maturity. Among the different planting patterns, including monocropping and intercropping of maize and/or soybean (Glycine max), pea (Pisum sativum), and alfalfa (Medicago sativa), the extraction efficiency of Cu, Zn, Pb, and Cd varied greatly. Only intercropping of maize and soybean yielded relatively higher extraction efficiency for the four metals with no significant difference in the total biomass. Moreover, the heavy metals concentrations in dry biomass from all the planting patterns in the present study were within China's national legal thresholds for fodder use. Therefore, slightly polluted alkaline soils can be safely used through monocropping and intercropping of maize and/or legumes for a range of purposes. In particular, this study indicated that intercropping improves soil ecosystems polluted by heavy metals compared with monocropping.     

微波辅助提取灰树花多糖工艺研究

采用提取时间、微波功率、液料比的单因素试验和正交试验法优化微波辅助提取灰树花多糖条件.结果表明,以净多糖得率为指标,影响微波辅助提取灰树花多糖的主次因素为:提取时间＞微波功率＞液料比,并且提取时间和微波功率的影响达到了极显著水平.灰树花多糖最佳提取工艺条件为:提取时间为10 min,微波功率为80%(全功率为800 W),液料比为25∶1.创立了一种用苯酚-硫酸法测定多糖时排除蛋白质干扰的方法.     

An Improved Method to Detect Allozymes of Spl and Ti Loci in Soybean Seed Proteins

In order to exploit and conserve the genic resources in soybean, it is necessary to analyse the genetic structure of soybean population. The modified procedures detecting the allozymes of Sp 1 (coding β-amylases) and Ti (coding soybean trypsin inhibitors) are summarized as follows: After proteins of soybean seed were separated by using 7% polyacrylamide slab gel electrophoresis (Davis system), gel was soaked in starch solution for half an hour. After that, gel was washed by distilled water twice. Finally, gel was stained by using I2-KI solution (in 0.05N HCl) for 2–3 h. The blank bands in blue back-ground are β-amylases. The products of Sp1a and Sp 1b located at Rf=0.38–0.40 and Rf=0A4–0.47 respectively. The dark blue bands are proteins. The altozymes of Ti can be identified by co-electrophoresis with standard soybean trypsin inhibitors.     

两种方法提取香菇多糖的比较研究

采用正交试验比较研究热水浸提法和微波提取法提取香菇多糖。热水浸提法的最佳工艺为:提取温度70℃、提取时间4h、料液比1∶15,提取率3.243%;微波提取法的最佳工艺为:微波功率560W、微波处理时间60s、料液比1∶10,提取率4.771%。微波提取法效率高、时间短,是理想的香菇多糖提取方法。