Simulation of future dissolved oxygen distribution in pond culture based on sliding window-temporal convolutional network and trend surface analysis

Dissolved oxygen (DO) is a key ecological factor to measure the quality of water in the aquaculture. As the pond water body is affected by the breeding environment, the spatial distribution of DO shows a certain law in the entire pond. Therefore, to simulate the distribution of DO in aquaculture waters and grasp the temporal and spatial variation of DO is the key to achieving precise regulation of DO. For this purpose, this paper proposed a method for simulating the temporal and spatial distribution of DO in pond culture based on a sliding window-temporal convolutional network together with trend surface analysis (SW-TCN-TSA). This paper first utilized SW to construct DO data sets with different prediction durations, and then used the improved TCN model to realize one-dimensional time series prediction for DO at single monitoring point. Based on the prediction results of DO, a TSA method was performed on the predicted values of DO at the extreme moments of all discrete monitoring points, so as to realize the simulation of the temporal and spatial distribution of DO in the pond. Experimental results show that the SW-TCN model has better prediction performance for one-dimensional time series prediction of DO. Compared with traditional deep networks, such as CNN, GRU, LSTM, CNN-GRU and CNN-LSTM, the values of evaluation indicators (MSE, MAE and RMSE) have been greatly improved. In the process of trend surface fitting, all fitting R² of DO at different water depths are higher than 0.9, indicating that the TSA can accurately reflect the temporal and spatial distribution of DO. This method can provide a basis for the prediction and early warning of DO in the three-dimensional space of the pond and has high practicability in aquaculture.     

兴仁小白壳薏苡不同播期对产量的影响

为探索适宜兴仁县薏苡种植的最佳播种时期，在兴仁县开展了薏苡不同播期对产量影响的试验。试验共设9个播期，梯度为7 d，播种时间从3月19日－5月14日。试验结果表明，兴仁小白壳薏苡的最佳播期是3月19日－4月16日，并且在此期间播种，薏苡产量较高。     

吉林莫莫格白鹤春季行为研究

白鹤属大型涉禽,仅分布于亚洲地区,其东亚种群数量为3 750只左右;由于环境变迁,种群数量越来越少,已被列为国家Ⅰ级重点保护动物。为阐明在沼泽湿地生态系统环境中白鹤春季的活动规律以及各种行为的时间分配,于2010年4月15日～5月13日,在吉林莫莫格国家级自然保护区对白鹤春季迁徙期行为进行了初步研究。白鹤的各种行为的时间分配依次为:觅食占64.34%、静栖占4.42%、警戒占13.92%、游走占4.57%、理羽占11.51%、其他(包括打斗、飞行、呜叫等情况)占2.56%。成体与亚成体白鹤、雄鹤与雌鹤在行为和时间分配上有明显差异,在觅食时间上雌鹤高出雄鹤10%左右,雄鹤的警戒时间高于雌鹤。     

内蒙古河套灌区节水工程改造效果分析与评估

以内蒙古河套灌区1982—2012年长系列农业净引水量和年降水量资料为基础,运用均值分析、方差分析、相关分析、时间序列分析和生存分析等数理统计学方法,并结合内蒙古河套灌区农业种植发展进程,分析了河套灌区多年农业净引水量变化趋势与影响因素,得出年降水量(超过211.76 mm时,即丰水年)和节水工程改造分别独立地与农业净引水量呈明显负相关关系的结论。运用时间序列法预测了2013、2014和2015年河套灌区的农业净引水量分别为44.5、44.18和43.86亿m3;同时运用生存分析法预测了在灌区现有节水改造规模条件下,河套灌区农业净引水量区间为35~55亿m3,平均为45亿m3。     

时滞半主动悬架模糊神经网络控制

建立了含时滞半主动悬架数学模型,分析了悬架系统产生时滞的原因,设计了含时滞补偿模糊神经网络自适应控制策略,开发了C8051单片机为内核的半主动悬架控制系统,仿真分析后,在全真半主动悬架试验台上进行了台架试验。结果表明,实施半主动悬架神经网络时滞补偿控制,解决了控制中的“不合拍”问题,较好地协调了车辆舒适性和安全性之间的矛盾。     

烯丙孕素片的制备及质量研究

对烯丙孕素片的制备及质量进行研究。以药物的崩解时限和溶出度为主要指标,应用正交设计法对其处方进行优化,制备一种延缓崩解开始时间的烯丙孕素片,以适应不同猪场和环境的湿法饲喂需求。考察烯丙孕素片的外观性状、硬度、片重差异、脆碎度、崩解时限、溶出度、含量测定等,重点对烯丙孕素片的溶出度方法进行了研究。结果表明,烯丙孕素片外观性状、硬度、片重差异、脆碎度、崩解时限、溶出度、含量测定等结果符合要求,含量测定为标示量的90.0%～105.0%。崩解时限和溶出度结果表明,烯丙孕素片在遇水后7～15分钟全部崩解完毕,溶出度大于90%。研究所得烯丙孕素片的崩解时限延长了5～10分钟,且溶出度和含量均达标。由此确定研制的烯丙孕素片处方工艺可行,质量可控,符合拟定的质量标准。     

金纹细蛾幼虫在陇东苹果树冠层的空间分布研究

为掌握金纹细蛾幼虫在苹果树冠层不同部位的发生规律,为科学防治提供技术支持。以长富2号10年生富士苹果园为研究对象,通过对不同时期金纹细蛾幼虫发生规律、树冠分布特征和集聚性分析,研究了陇东金纹细蛾幼虫在苹果树冠上的空间分布结构。结果发现,金纹细蛾幼虫1 a发生5代。在世代重叠现象和苹果生长期药剂防控的双重影响下,第2代以后各世代之间未出现明显的高峰,在9月上旬之前幼虫数量虽有增长,但增长非常缓慢,而进入9月下旬之后越冬代数量成倍数骤增。从幼虫在树冠上的空间分布看,存在东向和北向＞南向和西向、下部 ＞ 上部、内膛 ＞ 外围的趋势,但是在统计学上却没有显著差异;幼虫在苹果树冠中的分布呈一定的聚集性分布,但聚集度比较小。在前期防控的基础上,加强9月下旬以后的防控,是减少翌年虫源的关键。药剂防控中,在保证树冠全方位防控的同时,树冠下部、内膛、南向和西向为重点防控的空间部位。     

黑龙港流域参考作物蒸散量的时序变化和分形特征

利用位于黑龙港流域的武强、深泽、饶阳、晋州、献县5站1957-2009年日最高气温、日平均气温、日最低气温、日平均相对湿度、日平均风速、日照时数资料,采用Penman-Monteith算法,计算各站不同时间尺度ET0,采用线性趋势分析法分析其趋势倾向,并应用滑动R/S分析方法研究该流域不同时间尺度ET0时间序列的分形特征。线性趋势分析显示,各站历史上自1957年以来的ET0年总值的气候倾向率在-33.81-10.79mm.10a^-1,即均呈下降趋势,但变化倾向率不同;各月ET0倾向率在-11.27-2.02mm.10a^-1,大多数为负值,其中5、6月份各站的下降趋势最大;春、夏、秋、冬季ET0倾向率为-15.87-1.30mm.10a^-1,且夏季各站之间的差异较大,尤以饶阳站与其他4站间的差异最大。气候要素倾向率的对比分析表明,5站参考作物蒸散量总体下降趋势的基本特征主要是由于风速下降、日照时数减少、日最高最低气温上升造成的;5、6月份下降趋势明显则主要是由于风速下降、日照时数减少、日平均气温上升减缓、相对湿度上升明显造成的;饶阳站与其他4站差异较大的主要原因在于2、3、11、12月风速下降和日照时数减少以及日最高最低气温上升趋势减缓、相对湿度和气压下降明显,以致这些月份的ET0倾向率大于0,形成秋季和冬季ET0倾向率大于0,年尺度ET0年际变化下降趋势不明显。R/S分析结果显示,5站全年和各季ET0时间序列的Hurst指数均大于0.5,相关系数均在0.98以上,分维数均小于1.5,说明各站全年和各季节ET0时间序列变化趋势在未来一段时间内具有持续性,即ET0在未来将呈较明显的下降趋势,这种趋势在除饶阳外的其他站月均有不同程度的表现。     

Physiological interpretation of a hyperspectral time series in a citrus orchard

Hyperspectral remote sensing for monitoring horticultural production systems requires the understanding of how plant physiology, canopy structure, management and solar elevation affect the retrieved canopy reflectance during different stages of the phenological cycle. Hence, the objective of this study was to set up and to interpret a hyperspectral time series for a mature and healthy citrus orchard in the Western Cape province of South Africa considering these effects. Based on the remotely sensed data, biophysical parameters at the canopy level were derived and related to known observed physiological and phenological changes at the leaf level and to orchard management. Fractions of mature fruit, flowers, and sunburnt leaves were considered, and indices related to canopy structure chlorophyll content and canopy water status were calculated.Results revealed small cover fractions of mature fruit, flowers and sunburnt leaves of respectively 2.1%, 3.1% and 7.0%, but the high spectral contrast between flowers and leaves allowed a successful classification of flowering intensity. Furthermore, it was shown that canopy level time series of vegetation indices were sensitive to changes in solar elevation and soil reflectance which could be reduced by applying an empirical soil line correction for the most affected indices. Most trends in vegetation indices at the canopy level could be explained by a combination of changes at the leaf level (chlorophyll, carotenoids, dry matter), changes in canopy structure (leaf area index and leaf angle distribution) and changes in cover fractions of vegetative flushes, flowers and sunburnt leaves. The transformed chlorophyll absorption ratio index over the optimised soil adjusted vegetation index (MCARI/OSAVI) was best related to leaf level trends in chlorophyll content. Seasonal changes in the photochemical reflectance index (PRI) were linked to inverse changes in the carotenoid-to-chlorophyll ratio. Canopy structure indices (the modified triangular vegetation index or MTVI2 and the standardized leaf area index determining index or sLAIDI) were sensitive to changes in leaf area index, average leaf angle as well to management interactions (pruning and harvest). Canopy water status was highly impacted during the spring flush due to expanding leaves that concealed trends in the underlying mature leaves. Seasonal trends in soil and weeds reflectance were related to changes in volumetric soil water content and to the earlier and reduced growth period of non-irrigated weeds.     

基于时空双序列分析的温室WSN故障诊断

根据温室无线传感器网络(WSN)所采集数据在时间和空间上具有很强的相关性,从温室无线传感器网络基本结构出发,在分析WSN原始数据的基础上,通过对时空序列样本信息的预处理,分别建立了时间和空间故障诊断数学模型,据此分析传感节点的工作状态,给出了温室WSN故障诊断的综合算法.研究结果表明,该故障诊断方法能够及时、有效地发现温室WSN的异常并诊断出故障节点,提高了WSN工作的可靠性.