Real-time adaptive irrigation scheduling under a limited water supply

The problem of real-time irrigation scheduling under limited water supply is considered. The goal is to develop an irrigation operation policy which maximizes crop yields and is responsive to current season changes in weather and other variables. Because irrigation decisions are sequential and dependent on crop and soil water status, and also because crop yields can only be known at the end of the season, the decisions are arrived at by a two-stage process. In the first or the design stage, irrigations are planned for the entire season at weekly intervals using historical data and an optimal irrigation scheduling model. In the second stage, the decisions for the subsequent weeks are revised each week after updating the status of the system with real time data up to that week and solving the irrigation optimization model once again for the new conditions. Thus, each week an irrigation decision is made, the entire planning horizon is kept in view. The procedure is illustrated by application to a case study.     

5%马灵乳油防治稻飞虱的田间药效试验

稻飞虱(Nilaparvata lugens Stal)是以稻属为食的单食性昆虫,刺吸稻株汁液危害水稻。建瓯全市水稻种植面积约3.5万hm2,稻飞虱年发生面积0.9万hm2,近几年来已成为建瓯市水稻的主要害虫之一。     

基于迁移学习的葡萄叶片病害识别及移动端应用

为解决已有的卷积神经网络在小样本葡萄病害叶片识别的问题中出现的收敛速度慢,易产生过拟合现象等问题,提出了一种葡萄叶片病害识别模型(Grape-VGG-16,GV),并针对该模型提出基于迁移学习的模型训练方式。将VGG-16网络在ImageNet图像数据集上学习的知识迁移到本模型中,并设计全新的全连接层。对收集到的葡萄叶片图像使用数据增强技术扩充数据集。基于扩充前后的数据集,对全新学习、训练全连接层的迁移学习、训练最后一个卷积层和全连接层的迁移学习3种学习方式进行了试验。试验结果表明,1)迁移学习的2种训练方式相比于全新学习准确率增加了10～13个百分点,并在仅训练25轮达到收敛,该方法有效提升了模型分类性能,缩短模型的收敛时间;2)数据扩充有助于增加数据的多样性,并随着训练次数的增加,训练与测试准确率同步上升,有效缓解了过拟合现象。在迁移学习结合数据扩充的方式下,所构建的葡萄叶片病害识别模型(GV)对葡萄叶片病害的识别准确率能达到96.48%,对健康叶、褐斑病、轮斑病和黑腐病的识别准确率分别达到98.04%、98.04%、95.83%和94.00%。最后,将最终的研究模型部署到移动端,实现了田间葡萄叶片病害的智能检测,为葡萄病害的智能诊断提供参考。     

基于声学特性的西瓜糖度检测系统

该研究优化了由包裹橡皮的金属小球、压电式加速度传感器、电荷放大器、光电式触发电路、数据采集卡和计算机等组成的西瓜声学特性测试系统。由所获取的声波信号幅值谱计算出声透过率,采用TQ软件中SMLR(逐步多元线性回归)函数选取6个特征频率:752、869、1001、4556、322、3950Hz,由其对应的声透过率值建立了西瓜品质检测的多元线性回归模型。对47个西瓜样本的试验数据分析表明:将敲击点和接收点分别放置在西瓜自然生长状态的中部对侧可获得最佳的测定模型,模型的校正相关系数R、校正均方根误差RMSEC和预测均方根误差RMSEP分别是0.80753、0.646和0.655。实现了西瓜糖度检测目的,为声学无损检测西瓜成熟度提供了参考。     

近红外光谱变量筛选提高西瓜糖度预测模型精度

水果的内部品质是水果分级、保鲜及存储的一项重要指标,利用近红外光谱技术对西瓜内部品质进行快速无损检测研究有着非常重要的意义。为了研究变量筛选方法对西瓜糖度预测模型精度的影响,该文以麒麟瓜为研究对象,利用近红外漫透射光谱技术对麒麟瓜可溶性固形物含量（SSC）进行检测,采用偏最小二乘回归（PLSR）,多元线性回归（MLR）和主成分回归（PCR）建立麒麟瓜可溶性固形物数学模型,并探讨等间隔平均光谱和等间隔抽取光谱变量筛选结合连续投影算法（SPA）对预测模型精度的影响。研究结果表明：光谱经等间隔抽取（间隔5,115个变量）经归一化预处理,结合SPA优选出6个波长建立的PLSR预测模型的相关系数（rpre）为0.828、校正均方根误差（RMSEC）为0.589、预测均方根误差（RMSEP）为0.611。该模型预测效果相对较优,建模时间短,提高了模型的预测能力和预测精度。该研究为西瓜内部品质的在线无损检测提供研究基础。     

水肥耦合对当归产量和品质的影响效应研究

探索水肥耦合对当归品质和产量的影响效应,为当归GAP规范化种植中的水肥调控提供理论依据。采用水肥双因素试验,通过二元二次多项式拟合灌水量、施肥量与当归产量和主要品质指标（阿魏酸含量）的关系,建立影响效应模型,并对其进行检验分析和相关性分析。结果表明：在灌水一定的情况下,随着施肥量的增加,当归的产量先增加后减少;在施肥一定情况下,随着灌水量的增加,当归的产量也是先增加后减少,当归的最高产量出现在中水中肥区,即灌水量1073.97 m3/hm2,施肥量808.97 kg/hm2,最大产量为15804.36 kg/hm2;在灌水量一定的条件下,随着施肥的增加当归的阿魏酸含量先增加后降低,在施肥量一定的条件下,随着灌水量的增加当归的阿魏酸含量也是先增加后降低,当归的阿魏酸含量最高出现在中高水中高肥区,即灌水量1491.42 m3/hm2,施肥量863.55 kg/hm2,阿魏酸最高含量为2.41 mg/g。合理有效的灌溉施肥使当归达到优质高产。     

Discrimination of ‘San Marzano’ accessions: A comparison of minisatellite, CAPS and SSR markers in relation to morphological traits

‘San Marzano’ (SM) is one of the most widely known tomato (Solanum lycopersicum L.) cultivars, and is a classic example of a local variety with a premium value. Unfortunately, the original cultivated form is underrepresented in the Protected Denomination of Origin (PDO) area because of the incidence of contaminant and phenotypically similar genotypes. Our aim was to examine the ability of three DNA marker systems (minisatellite, cleaved amplified polymorphic sequence (CAPS) and simple sequence repeat (SSR)) to reveal the genetic diversity of tomato accessions that were, based on a morphological analysis, very similar. The data indicate that both minisatellites and SSRs can be used to genetically distinguish the analysed materials. Furthermore, these two marker systems depict relationships consistent with the hierarchal pattern obtained by the morphological data. As locally cultivated tomato accessions are often characterised by some degree of genetic variability, our results will be valuable in facilitating the purification, management and breeding of tomato germplasms. The differences between the marker systems employed are also discussed in relation to their usefulness in the agro-food chain.     

Agronomic traits of soybean cultivars released in different decades after grafting record‐yield cultivar as rootstock

Breeders have seldom considered the selection for root traits during the genetic improvement in soybean. It is hypothesized that grain yield would be increased by the root function improvement, especially for the current cultivars. The objective of this grafting experiment was to determine the effect of record‐yield cultivars L14 or Z35 as rootstocks on agronomic traits of cultivars released in different decades. A total of 11 cultivars, released in different decades, were used to graft onto L14 or Z35 rootstocks. The agronomic traits were measured in the pot‐culture experiments. Grafting cultivars released in different decades onto L14 or Z35 rootstocks resulted in higher yield, 100‐seed mass and apparent harvest index as compared with those of non‐grafted or self‐grafted plants. Grain yield gain of cultivars grafted onto record‐yield cultivar rootstocks was 0.40 g/plant/year from 1966 to 2006, which was larger than that of non‐grafts and self‐grafts (0.27 g/plant/year). The yield of current cultivars should increase more if their root functions were improved.