基于BP神经网络的人机联合率定SWMM研究

为解决雨洪管理模型(SWMM)在率定过程中参数复杂、过程繁琐等问题。以西宁市某地块为例建立SWMM模型,利用Morris筛选法进行参数灵敏度分析,并根据灵敏度分析的结果进行人工率定;另外利用BP神经网络对模型进行率定,并结合参数灵敏度对其进行优化。对3种率定方案进行分析,结果表明:水文水力模块参数的相对灵敏度基本一致,其中灵敏度较大的参数为子汇水区面积(Area)、不透水率(Imperv)和不透水区洼地蓄积量(Destore-Imperv),并且不同降雨条件下模型参数的灵敏度存在差异。经过优化后的BP神经网络参数率定方法的模型模拟效果最好,纳什系数最大。结合灵敏度优化BP神经网络的人机联合率定方法一方面能提高BP神经网络率定的准确性,另一方面又能提高传统人工率定的效率。     

镇江长江豚类省级自然保护区水域生态修复效果的监测与评价

自2006年以来,长江豚类极度濒危的生存状况得到广泛关注,在其自然保护区实施一系列生态修复工程,为镇江长江豚类省级自然保护区内的江豚提供良好的生存环境。于2015—2018年在和畅洲水域建设生态浮岛、人工鱼巢和放流底栖动物进行水域生态修复,对生态修复工程进行跟踪监测和效果评价。结果表明：生态浮岛的建设可提高区域内浮游植物和浮游动物的生物多样性和群落结构复杂程度;人工鱼巢对产黏性卵鱼类具有一定增殖效果,增殖种类主要为鲤、鲫、䱗和黄尾鲴;生态浮岛和人工鱼巢的建设对鱼类均有较好的聚集效果;底栖动物增殖放流显著增加了放流物种的丰度、生物量及保护区底栖动物群落生物量,增殖放流效果评价为中等。该自然保护区水域生态修复效果明显,为工程施工影响下水生生物保护区生态修复提供科学依据。     

纵条纹炭角菌的研究进展

纵条纹炭角菌具有镇静、催眠等药用价值,已实现工厂化、规模化栽培。为探究纵条纹炭角菌的研究进展,对其分类学地位、生物学特性、人工培养、化学成分和生理活性等方面的文献进行综述,并提出未来研究的方向和应用前景。     

基于部首嵌入和注意力机制的病虫害命名实体识别

为了解决农业病虫害命名实体识别过程中存在的内在语义信息缺失、局部上下文特征易被忽略和捕获长距离依赖能力不足等问题，以农业病虫害文本为研究对象，提出一种基于部首嵌入和注意力机制的农业病虫害命名实体识别模型(Chinese agricultural diseases and pests named entity recognition with joint radical embedding and self attention, RS-ADP)。首先，该模型将部首嵌入集成到字符嵌入中作为输入，用以丰富语义信息。其中，针对部首嵌入设计了3种特征提取策略，即卷积神经网络(Convolutional neural network, CNN)、双向长短时记忆网络(Bidirectional long short term memory network, BiLSTM) 和CNN-BiLSTM；其次，采用多层不同窗口尺寸的CNNs层提取不同尺度的局部上下文信息；然后，在BiLSTM提取全局序列特征的基础上，采用自注意力机制进一步增强模型提取更长距离依赖的能力；最后，采用条件随机场(Conditional random field, CRF)联合识别实体边界和划分实体类别。在包含11个类别和24715条标注样本的农业病虫害自制语料上进行了实验。结果表明，本文模型RS-ADP在该数据集上精确率、召回率和F1值分别为94.16%、94.47%和94.32%；在具体实体类别上，RS-ADP在作物、病害、虫害等易识别实体上F1值高达95.81%、97.76%和97.23%。同时，RS-ADP在草害、病原等难以识别实体上F1值仍保持86%以上。实验结果表明，本文所提模型能够有效识别农业病虫害命名实体，其识别精度优于其他模型，且具有一定的泛化性。     

Development of colchicine‐induced tetraploid St. Augustinegrass (Stenotaphrum secundatum) lines

St. Augustinegrass is well suited for lawns and commercial landscapes. While many genotypes are cross‐fertile, all cultivars are propagated vegetatively in sod production. To ensure varietal purity, development of sterile triploid hybrids by crossing tetraploid and diploid genotypes has been successfully used in other warm‐season turfgrasses. Applying this model in St. Augustinegrass would be beneficial to sod producers and turf managers who require purity for certification and uniformity for performance, respectively. This study was conducted to develop colchicine‐induced tetraploid lines of St. Augustinegrass. Seeds of cultivar ‘Raleigh’ were treated with four colchicine concentrations at four exposure times. A non‐treated control was included among the treatments. Seedlings that germinated were screened for genome size changes using flow cytometry. Line DSA 13005 and two progeny lines derived through selfing, DSA 16001 and DSA 16016, were corroborated as tetraploids (2n = 4x = 36) through chromosome counts. These lines will be used in future breeding efforts to attempt development of sterile triploid cultivars of St. Augustinegrass.     

基于卷积神经网络的拖拉机工况识别

农机工况识别在细化农机作业状态和帮助掌握区域污染物排放趋势方面有着重要的研究价值。基于拖拉机不同运行状态下的行驶速度、发动机转速以及实时油耗等时间序列,首次提出将图像识别方法引入到拖拉机工况识别中的思路,并分别应用参数优化的支持向量机与卷积神经网络对实际作业拖拉机工况进行研究。结果表明:(1)基于参数优化的支持向量机可以较好地实现样本点的工况识别且识别准确度达到99.851 9%,但无法实现农机工况的连续性识别,同时无法对农机工况转换阶段进行有效识别。(2)以拖拉机运行速度与发动机转速等信息构建样本图像来描述农机工况变化的数据表达,并在此基础上应用卷积神经网络可以有效实现农机工况的连续性识别,且识别准确率可以达到93.3%。本研究在农机工况识别方面具有一定参考价值,并为后续农机不同工况下区域污染物排放研究提供技术支持。     

面向养殖水体分布差异的COD光谱法检测研究

面向养殖水体，传统光谱法对化学需氧量（Chemical Oxygen Demand，COD）检测模型构建的基础：源域（现有样本库）与目标域（检测地水体）间光谱数据独立同分布。但是当源域与目标域分布间存在差异时，由源域得到的低误差模型常在目标域上表现下滑。针对该问题，提出面向UV Vis光谱的域对抗训练网络（DAUVwpNet），将分布不同的源域和目标域数据映射至相同分布的特征空间中，使其在该空间的分布距离尽可能接近，从而在特征空间中对源域训练的目标函数也可以迁移至目标域上，以降低模型在目标域的误差。试验表明：面向同一批测试数据，DAUVwpNet的预测误差为0.78，要低于传统模型的预测误差（0.85）；DAUVwpNet预测值与实测值间相关系数为0.95，要高于传统模型的相关系数（0.89）。表明了该网络能够较好对齐两域特征空间数据分布，降低因分布差异带来的COD检测误差。     

A comparison of the effects of carbon dioxide and medical air for abdominal insufflation on respiratory parameters in xylazine-sedated sheep undergoing laparoscopic artificial insemination

AIMS: To determine if abdominal insufflation with medical air will improve oxygenation and ventilation parameters when compared to insufflation with CO₂ in xylazine-sedated sheep undergoing laparoscopic artificial insemination (AI).

METHODS: Forty-seven sheep underwent oestrus synchronisation and were fasted for 24 hours prior to laparoscopic AI. Each animal was randomised to receive either CO₂ or medical air for abdominal insufflation. An auricular arterial catheter was placed and utilised for serial blood sampling. Respiratory rates (RR) and arterial blood samples were collected at baseline, after xylazine (0.1?mg/kg I/V) sedation, 2 minutes after Trendelenburg positioning, 5 minutes after abdominal insufflation, and 10 minutes after being returned to a standing position. Blood samples were collected in heparinised syringes, stored on ice, and analysed for arterial pH, partial pressure of arterial O₂ (PaO₂), and CO₂ (PaCO₂). The number of ewes conceiving to AI was also determined.

RESULTS: Repeated measures ANOVA demonstrated temporal effects on RR, PaO₂, PaCO₂ and arterial pH during the laparoscopic AI procedure (p<0.001), but no difference between insufflation groups (p>0.01). No sheep experienced hypercapnia (PaCO₂>50?mmHg) or acidaemia (pH<7.35). Hypoxaemia (PaO₂<70?mmHg) was diagnosed during the procedure in 14/22 (64%) ewes in the CO₂ group compared with 8/23 (35%) ewes in the medical air group (p=0.053). Overall, 15/20 (75%) ewes in the CO₂ group conceived to AI compared with 16/22 (72.7%) in the medical air group (p=0.867).

CONCLUSIONS AND CLINICAL RELEVANCE: There were no statistical or clinical differences in RR, PaO₂, PaCO₂, pH, or conception to AI when comparing the effects of CO₂ and medical air as abdominal insufflation gases. None of the sheep experienced hypercapnia or acidaemic, yet 42% (19/45) of sheep developed clinical hypoxaemia, with a higher percentage of ewes in the CO₂ group developing hypoxaemia than in the medical air group. Based on the overall analysis, medical air could be utilised as a comparable alternative for abdominal insufflation during laparoscopic AI procedures.     

基于深度学习的牛肉大理石花纹等级手机评价系统

大理石花纹是影响牛肉品质等级的重要指标,目前中国牛肉加工企业对大理石花纹的评价是由专业分级人员参照标准图谱完成,具有主观性强、耗费人工的缺点。针对上述问题,该研究提出了基于深度学习的智能分级方法,设计一种具有4层卷积的神经网络结构,实现了大理石花纹特征的自动提取,并基于智能手机开发了牛肉大理石花纹检测软件。该研究共采集样本图像1 800张,按3:1:1分为校正集、验证集和测试集。为进一步验证模型,将该方法与传统机器视觉方法进行了比较,提取了牛肉大理石花纹的大、中、小脂肪颗粒个数,脂肪总面积和脂肪分布均匀度5个参数,并建立了多元线性回归模型。试验结果表明,该研究所用方法大理石花纹检测准确率更高,验证集检测正确率为97.67%。最后编写了手机软件,将模型移植入Android手机,在手机平台上调用模型进行大理石花纹检测。试验表明,该软件对测试集样本的检测准确率为95.56%,单张检测时间低于0.5 s。该研究结合卷积神经网络分类能力强和智能手机运行速度快等优点,开发了牛肉大理石花纹的手机评价系统,具有较好的实用性和便携性,可提高牛肉大理石花纹检测效率,有助于提高农畜产品检测的智能化水平。