共查询到20条相似文献,搜索用时 203 毫秒
1.
《大豆科学》2020,(4)
为准确预测2020-2022年中国大豆的进口量及进口额,分别采用ARIMA模型、GM(1,1)模型以及ARIMA-GM组合模型对2016-2019年大豆进口量及进口额数据进行拟合,以降低预测风险,并根据拟合结果选择最优预测模型进行预测。研究表明:大豆进口量及进口额均可采用ARIMA-GM组合模型进行预测,预测结果显示,2020-2022年中国大豆进口量将分别为8.76×10~7,8.94×10~7和9.33×10~7 t;大豆进口额将分别为357.59×10~8,375.73×10~8和398.44×10~8 USD。研究结论科学、可靠,可为中国大豆产业的经营和管理提供一定的科学依据。 相似文献
2.
3.
本文介绍了灰色系统理论GM建模机理及方法,并以广西忻城县蔗区1991/92~1995/96榨季的甘蔗单产数据,建立了甘蔗单产GM(1,1)预测模型,统计结果表明,关联度r=0.7167>0.6,说明灰色系统理论的GM(1,1)模型应用于甘蔗单产的预测,模型精度高、方法简便、结果可信,与人工神经网络等其他方法相比更为准确可靠,不失为一理想的预测方法. 相似文献
4.
本文在Logistic和Markov理论的基础上,提出了kogistic—Markov联合预测模型的概念,并用此模型对通什垦区的橡胶单位面积产量进行印证预测.结果表明,用联合模型对1986和1987年两年橡胶单位面积产量的预测结果与实际吻合,其误差要比单一的Logistic模型小,效果较好.从而为橡胶单位面积产量的预测提供了一种较为准确的方法. 相似文献
5.
6.
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 总被引:2,自引:0,他引:2
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。 相似文献
7.
8.
9.
3S技术在新疆棉花精准种植中的应用 总被引:2,自引:1,他引:1
论述了 3S技术 ( GPS、RS、GIS)在新疆棉花精准种植试验研究中具体应用情况与取得的初步成果。利用 GPS实现了不同农田作业要求位置分辨力的精确定位进行准确播种、施肥、灌溉、采棉。利用 RS技术获取大量的田间时空变化信息 ,对棉花的长势动态进行监测。利用 GIS技术建立示范区历史产量数据库、土壤肥力数据库、气候资料数据库、棉花不同生长期的光谱数据库 ;研制适合本地区地膜植棉特点棉花生长模拟模型、平衡施肥系统、棉花病虫害预测预报系统、专家知识决策系统。 相似文献
10.
11.
12.
Ramana Narava Sai Ram Kumar D V Jagdish Jaba Anil Kumar P Ranga Rao G V Srinivasa Rao V Suraj Prashad Mishra Vinod Kukanur 《Journal of insect science (Online)》2022,22(3)
Helicoverpa armigera (Hübner) (Noctuidae: Lepidopetra) is a polyphagous pest of major crops grown in India. To prevent the damage caused by H. armigera farmers rely heavily on insecticides of diverse groups on a regular basis which is not a benign practice, environmentally and economically. To provide more efficient and accurate information on timely application of insecticides, this research was aimed to develop a forecast model to predict population dynamics of pod borer using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN). The data used in this study were collected from the randomly installed sex pheromone traps at International Crops Research Institute for the Semi-arid Tropics (ICRISAT), Patancheru, Hyderabad. Several ARIMA (p, d, q) (P, D, Q) and ANN models were developed using the historical trap catch data. ARIMA model (1,0,1), (1,0,2) with minimal BIC, RMSE, MAPE, MAE, and MASE values and higher R2 value (0.53) was selected as the best ARIMA fit model, and neural network (7-30-1) was found to be the best fit to predict the catches of male moths of pod borer from September 2021 to August 2023. A comparative analysis performed between the ARIMA and ANN, shows that the ANN based on feed forward neural networks is best suited for effective pest prediction. With the developed ARIMA model, it would be easier to predict H. armigera adult population dynamics round the year and timely intervention of control measures can be followed by appropriate decision-making schedule for insecticide application. 相似文献
13.
14.
开展作物发育期及产量预报对农业生产和粮食安全具有重要意义。本文选取1981-2012年大豆生长季
气象数据和发育期资料,结合生理指标,构建大豆气候适宜度模型,建立适用于内蒙古地区的发育期预报模型及以
旬为步长的产量预报模型,并应用2013-2015年资料进行预报检验。基于气候适宜度的大豆各发育期持续天数预
报模型均通过0.01极显著水平,准确率除鼓粒—成熟期稍低外,其余均在90%以上,模型预报精度较高;产量动态
预报模型大部分时段均通过显著性检验,基于气候适宜度法的10个代表站预报平均准确率为87.6%。文章基于气
候适宜度法建立的发育期及产量预报模型均能满足业务服务的需求,可供其他大豆主产区的发育期及产量预报方
法研究借鉴。 相似文献
15.
《Field Crops Research》1999,62(1):85-95
Crop simulation models are receiving increasing use in agriculture and are recommended as multipurpose tools in research and farm management. Of one particular interest to crop growers is the possibility of applying crop models for real-time yield forecasting. This investigation evaluated the utility of the SUCROS model for site-specific real-time crop biomass and grain-yield forecasting. A stochastic forecasting approach was used combining generated weather data with observed data for model updating. The forecast procedure was tested with field data collected at four sites in the UK over two growing seasons. The results showed that across all site-years, the model is able to forecast the final biomass and grain yield with <10% bias. There was no significant difference between observed and forecasted biomass and grain yield for forecasts made at anthesis or milky grain stage although earlier forecasts did show significant differences. The ranking of the observed and forecast biomass and grain yield were also highly correlated for the later forecasts. 相似文献
16.
T. Boopathi S. B. Singh T. Manju Y. Ramakrishna R. S. Akoijam Samik Chowdhury N. Hemanta Singh S. V. Ngachan 《Journal of insect science (Online)》2015,15(1)
The most destructive enemy of the lychee, Litchi chinensis Sonn. (Sapindales: Sapindaceae), in India is a stink bug, Tessaratoma papillosa (Drury) (Hemiptera: Tessaratomidae). The population of T. papillosa on lychee trees varied from 1.43 ± 0.501 to 9.85 ± 3.924 insects per branch in this study. An increase in the temperature and a decrease in the relative humidity during summer months (April to July) favor the population buildup of T. papillosa. A forecasting model to predict T. papillosa incidences in lychee orchards was developed using the autoregressive integrated moving average (ARIMA) model of time-series analysis. The best-fit model for the T. papillosa incidence was ARIMA (1,1), where the P-value was significant at 0.01. The highest T. papillosa incidences were predicted for April in 2010, January in 2011, May in 2012, and February in 2013. A model based on time series offers longer-term forecasting. The forecasting model, ARIMA (1,1), developed in this study will predict T. papillosa incidences in advance, thus providing functional guidelines for effective planning of timely prevention and control measures. 相似文献
17.
玉米矮花叶病预测预报研究 总被引:1,自引:0,他引:1
为了较准确地预测玉米矮花叶病发生流行情况,对该病进行有效控制,根据历史资料和实际调查数据,应用生长模型预测法、马尔科夫链预测法和回归模型预测法对该病进行了预测预报研究,初步建立了玉米矮花叶病流行预测体系.生长模型预测法可对生长到一定阶段后的春玉米进行玉米矮花叶病短中期预测,对夏玉米出苗后即可进行短中期预测.马尔科夫链预测法可对发生程度作概率预测,可作为玉米矮花叶病长期发生趋势预测预报的一个参考.应用回归模型预测法可进行中期预测,预测一个生长季的最终病情。 相似文献
18.
在我国大豆单产光合潜力和"农业生态区划"(AEZ)潜力基础上,运用ARIMA(自回归单整移动平均)模型预测了2020年前我国大豆单产。结果表明:我国大豆单产最大潜力为3 400 kg·hm~(-2),而2017、2018、2019和2020年单产将分别为1 899,1 926,1 954和1 982 kg·hm~(-2),分别是最大潜力的55.85%、56.65%、57.47%和58.29%。这意味着:未来提高我国大豆单产尚有较大空间,应保持高产耕地生产力与改良中低产田土并重。研究结果旨在为我国大豆生产提供决策参考信息。 相似文献
19.
玉米当季产量预测对农民制定栽培管理方案和政府决策者制定粮食战略都至关重要,作物过程模型与天气预报策略结合实现作物当季产量预测已经被广泛应用,该方法缺少在农户实际生产中的检验。基于河北省曲周县2年(2017~2018年)农户跟踪数据和DSSAT模型,2017、2018年分别使用14个农户数据对当地主栽品种登海605的遗传参数进行校准和验证,通过动态时间规整(DTW)算法检验气象数据时间序列的相似性,筛选出与预测年份气象数据相似度最高的历史年份,使用当季实时天气数据与历史年份数据结合的天气预报策略生成完整的玉米季天气数据,实现当季玉米产量预测。结果表明,校准后的DSSAT-CERES-Maize模型能够准确模拟玉米开花期日期(ARE:2.19%,nRMSE:2.53%)、生物量(ARE:7.55%,nRMSE:9.50%)和产量(ARE:5.70%,nRMSE:6.60%),以DTW算法为基础的天气预报策略与DASST模型结合能够提前30~43 d获得准确的预测产量(±8%)。 相似文献
20.
灰色预测与马尔柯夫转移概率矩阵预测具有互补性质.两者的结合,有更广泛的应用范围和更高的预测精度。本文应用该组合模型,对黑龙江省大豆平均亩产量时间序列进行了分析,并预测了今后几年大豆的平均单产。 相似文献