基于PCA-SVR-ARMA的狮头鹅养殖禽舍气温组合预测模型

为提高狮头鹅养殖禽舍气温预测精度,提出了基于主成分分析(Principal Component Analysis,PCA)、支持向量回归机(Support Vector Regression,SVR)融合自回归滑动平均(Autoregressive Moving Average,ARMA)模型的狮头鹅养殖禽舍气温组合预测模型。在建模过程中,运用主成分分析法筛选狮头鹅养殖禽舍气温的关键影响因子,消除变量之间冗余信息,约简预测模型结构;采用SVR-ARMA构建狮头鹅禽养殖舍气温组合预测模型,先通过SVR对气温进行预测,再由基于ARMA模型的残差预测值修正气温预测结果。利用该模型对广东省汕尾市2018年7月21日至2018年7月30日期间的狮头鹅养殖禽舍气温进行预测。结果表明,该组合预测模型取得了良好的预测性能,与标准BP神经网络、标准SVR、PCA-BPNN(反向传播神经网络,BackPropagationNeuralNetwork)、PCA-SVR和PCA-BPNN-ARMA等模型对比分析,其评价指标平均绝对误差、均方根误差和平均绝对百分比误差分别为0.183 2℃、0.454 0℃和0.005 9,均表明所提出的组合模型具有更高的预测效果,不仅能够满足狮头鹅养殖禽舍气温实际精准调控的需要,还为狮头鹅健康养殖和种苗繁育环境精细化管理提供决策。     

基于改进GM(1,N)模型的我国大豆价格影响因素分析及预测研究

大豆是我国重要的粮食作物和油料作物,其价格对于国民经济尤其是农业经济的影响意义深远。大豆价格的稳定对于我国大豆市场的健康发展有着重要的现实意义。在灰色理论的基础上,提出了一种改进GM(1,N)大豆价格预测模型,首先运用灰色关联分析法对我国大豆价格的影响因素进行分析,选择主要的影响因素;再将这些影响因素作为模型的相关因素变量,构建GM(1,N)大豆价格预测模型。采用2010-2015年的大豆数据进行实证研究,模型选取国内大豆自给量、世界大豆产量、国民消费价格指数、消费者信心指数4个变量作为相关因素变量;模型预测误差为2.10%,预测精度较高,能够较好地掌握大豆价格的变化规律,可以为大豆价格市场预测及国家宏观政策的制定提供理论指导。     

基于配合力和遗传距离的甜高粱杂种优势预测

【目的】对甜高粱主要农艺性状进行杂种优势、一般配合力及特殊配合力分析,同时,分析配合力、表型遗传距离以及分子遗传距离用于杂种优势预测的可行性,为甜高粱的种质创新和杂交种选育提供理论参考。【方法】采用不完全双列杂交设计,以8个甜高粱不育系为母本及8个甜高粱恢复系为父本配制64个杂交组合。对亲本及杂交后代进行2年的性状调查,包括：出苗至开花日数、生育期、株高、穗长、茎粗、分蘖、单穗粒重、千粒重、籽粒产量、单株重、生物产量和含糖量。分析不同性状的杂种优势、一般配合力、特殊配合力、表型遗传距离、分子遗传距离以及配合力、遗传距离与杂种优势的相关性。【结果】各性状的中亲优势由强到弱分别为单株重、籽粒产量、单穗粒重、生物产量、株高、穗长、千粒重、茎粗、生育期、至开花日数、分蘖和含糖量,其中,生育期、至开花日数、分蘖和含糖量等性状为负优势。不同性状的中亲优势和超亲优势由强到弱的顺序基本相同。配合力分析表明,每个性状中,不同亲本的一般配合力相差较大,且不同组合的特殊配合力也有很大差异。大多数特殊配合力高的组合,其亲本的一般配合力也较高。杂种优势与配合力和遗传距离的相关性为单株重、籽粒产量、单穗粒重、生物产量、穗长、千粒重、分蘖以及含糖量等性状的杂种优势与其亲本的一般配合力和特殊配合力均为极显著正相关。生育期的杂种优势与特殊配合力为极显著正相关,至开花日数与特殊配合力为显著正相关。亲本间的表型遗传距离为2.86—6.82,分子遗传距离为0.50—0.96。单株重、籽粒产量、单穗粒重、生物产量、株高、穗长、茎粗及含糖量等性状的杂种优势与分子遗传距离的相关性大于表型遗传距离,其中,生物产量、单株重、穗长和茎粗的杂种优势与分子遗传距离为极显著正相关。【结论】所有性状中,与产量相关性状的杂种优势较高,而含糖量和分蘖的杂种优势较低。在杂种优势预测上,利用亲本的配合力可有效预测杂种优势,预测效果优于遗传距离。与表型遗传距离相比,分子遗传距离对杂种优势的预测更有效。     

黄河未来输沙量态势及其适用性对策

[目的] 探索黄河输沙预测的新思路，预估黄河未来输沙态势与输沙量水平，为黄河流域生态治理规划提供参考。[方法] 结合黄河流域水土保持生态修复现状，采用单累积曲线法、滑动平均及频率分析方法，分析1950—2019年黄河主要来沙区间的实测输沙量变化特征及其未来态势。[结果] 1950—2019年黄河输沙量呈现阶梯式减少。1950—2019年黄河中游各站累积实测输沙量随时间的变化可用“左半抛物线”表征。黄河输沙量自1997年以来已进入相对稳定态势，目前已达企稳状态；黄河潼关站未来年输沙量在90%频率下为1.00×10⁸ t左右，在10%频率下为5.00×10⁸ t左右，未来多年平均输沙量为1.40×10⁸ t。[结论] 为了维持黄河输沙量低稳状态，提升水土保持措施质量与标准，补齐“后水土保持”短板，构建完善的水沙关系调控体系，维持黄河下游河道冲淤平衡，是黄河流域生态保护与高质量发展的保障。     

基于改进极限学习机的水体溶解氧预测方法

为了有效地指导水产养殖生产，提高溶解氧浓度预测的精度，提出了基于因子筛选和改进极限学习机（Extreme Learning Machine，ELM）的水产养殖溶解氧预测模型。首先，利用皮尔森相关系数法计算各影响因子与溶解氧浓度间的相关系数，提取强关联因子，降低预测模型的输入量维度；采用偏最小二乘算法（Partial Least Square, PLS）优化传统ELM神经网络，避免网络中隐含层共线性问题，保障输出权值的稳定性；然后，结合新型激活函数，构建水体溶解氧浓度预测模型。最后，将SPLS-ELM（Selection Based Partial Least Square Optimized Extreme Learning Machine）预测模型应用到江苏省无锡市南泉基地某试验池塘的水体溶解氧预测中。试验结果表明：该模型的预测均方根误差为0.3232，与最小二乘支持向量机（Least Square Support Vector Machine，LSSVM）、BP神经网络、粒子群（Particle Swarm Optimization，PSO）优化LSSVM和遗传算法（Genetic Algorithm, GA）优化BP神经网络相比分别降低40.98%、44.48%、34.73%和44.18%。且该模型的运行时间仅0.6231s，预测精度和运行效率明显优于其他模型。该模型的溶解氧预测曲线接近真实溶解氧变化曲线，能够满足水产养殖实际生产对水体溶解氧预测的要求。     

Comparison of selection methods among and within full-sibling progenies in Urochloa humidicola

Hybridization in the Urochloa humidicola breeding programme allowed to explore the genetic variability of the apomictic sources and, thus, to obtain new sexual and apomictic parents with compatible ploidy and/or superior progenies. However, given the high variability arising from crosses, there is a need to adopt efficient selection strategies among and within progenies. The aim of this study was to compare the selection methods among U. humidicola progenies with (t-BLUP) and without (BLUP) the weighting based on prediction error and subsequent selection within progenies by individual simulated (BLUP_IS) or optimal individual BLUP. We evaluated seventy-one U. humidicola full-sib progenies from biparental crosses between nine sexual and ten apomictic parents. The experiment was set up in an incomplete block design with 64 blocks of 15 plots each, consisting of individual plants. Seven consecutive cuts were made and the traits total dry-matter, leaf dry-matter and regrowth scores were measured. Genetic variance was expressive for all traits. The selection procedure among progenies of U. humidicula based on t-BLUP proved to be more advantageous regarding the use of BLUP not weighted by the prediction error, resulting in higher selection gains, taking as reference the optimal procedure of the individual BLUP. Furthermore, the use of BLUP_IS allowed an optimized selection of hybrids, allowing the breeder to explore with variable selection intensity the genetic variability within the selected full-sib progenies based on relative genetic merit.     

Analysis on Target Genes with Mutation in microRNA of Blue-shelled Chicken and White Leghorn

The study was conducted to explore the potential different characters between Blue-shelled chicken and White leghorn.Global genome microRNA was combined the identified microRNA with complementary lab-predicted microRNA.Then the two breed chicken's SNP data got by GGRS were mapped to the microRNA and focused on SNP that deliberately located in mature-microRNA.Bioinformatics method was adopted for target prediction on microRNA which had SNPs.By further gene enrichment analysis,the study found these genes enriched in 22 GO terms,10 KEGG pathways,and 3 IPA important networks.And they enriched in traits which associated with growth,such as mTOR signaling pathways,Wnt signaling pathways,growth hormone receptor networks and insulin-like growth factor Ⅰ receptor networks.And they also enriched in some laying traits,such as oocyte meiotic signaling pathways and progesterone mature oocytes signaling pathways.The methods and the results might provide references for further studies.     

基于CA-Markov模型的甘州区土地利用变化预测分析

研究以张掖市甘州区为例,以黑河流域2000年和张掖市2007年土地利用/土地覆盖(LUCC)数据集的矢量数据、2014年Landsat 8 OLI_TIRS 8月份遥感影像和Google Earth影像为数据源,以Arc GIS10.1、ENVI 4.8和IDRISI 17.00为计算平台,利用CA-Markov模型对2014年土地利用变化进行模拟和预测,并将预测结果与2014年甘州区LUCC解译数据作对比分析,其Kappa系数为87.87%,表明预测与现实一致性较佳。最后对2021年甘州区土地利用分类进行模拟和预测。从预测结果可以看出:2000—2021年间甘州区耕地面积和建设用地面积呈现较快的增长趋势,未利用地面积呈现较快的减少趋势;林地和水域呈现缓慢地增长趋势;草地面积变化较小。简要分析了其变化原因主要归因于政策、社会经济、人口和科学技术几方面。对2021年甘州区土地利用变化的预测研究结果可为该区土地利用合理规划管理及经济发展政策的制定提供科学的决策依据。     

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.     

花龄期棉花虫害的电子鼻检测

棉花害虫具有隐蔽性、迁飞性和突发性特点，并且影响因素众多，棉花虫害准确地诊断是农业领域的难点问题。该研究以受到棉铃虫侵害的花铃期棉花为研究对象，采用电子鼻对不同处理的棉花挥发物进行检测。研究表明，主成分分析（Principal Component Analysis, PCA）和聚类分析结果显示健康棉花释放的挥发物具有明显的昼夜节律性，健康棉花与虫害棉花差异性显著。径向基函数神经网络（Radial Basis Function Neural Network, RBFNN）对8个不同时间的4组虫害棉花处理进行分析，测试集判别总的正确率为73.4%，健康棉花对照组测试集判别正确率100%，误判样本出现在3个虫害处理之间。当不考虑时间因素建立虫害棉花统一的预测模型，RBFNN模型对健康棉花对照组的预测正确率均达到了100%，分析结果可以作为花铃期棉花是否遭受棉铃虫侵害的依据，说明电子鼻可以作为棉花虫害发生的有效监测手段，在农作物虫害监测领域具有潜在的应用价值。