共查询到19条相似文献，搜索用时 62 毫秒
1.
2.
3.
赤潮预测的人工神经网络方法初步研究 总被引：13，自引：0，他引：13
赤潮是一种由多因素综合作用引发的生态异常现象,具有突发性及非线性等特点。对其进行预测预报一直是海洋科学研究的热点。探讨了应用人工神经网络原理进行赤潮预测的方法,简要介绍了BP和RBF算法的基本原理,用2种算法对不同海域赤潮生物与环境因子之间非线性和不确定性的复杂关系进行学习训练和预测检验,并与传统的统计方法进行了比较。结果表明：人工神经网络方法在模拟和预测方面优于传统的统计回归模型,具有较强的模拟预测能力及实用性,值得进一步探索。 相似文献
4.
用自回归预报黄渤海的底层水温 总被引：1，自引：0，他引：1
用自回归模型，对覆盖渤海标准水断面上的２９个站和北黄海的１０个站的底层海水温度进行了预报。均方误差为０．７５℃，结果较好，方法简便，能够满足渔业生产的需要。 相似文献
5.
气象卫星用于近海污染监测及赤潮预报方法探索 总被引：2，自引：0，他引：2
近年来，由于工农业和沿海养殖业的发展，我国近海污染逐年加重，赤潮发生频次增加，因此，监测近海污染和赤潮发生预报方法研究势在必行。本文用ＮＯＡＡ／ＡＶＨＲＲ数据，分析近海水域污染状况，并探索赤潮发生的预报方法。 相似文献
6.
7.
赤潮作为海洋灾害,对海洋渔业、生态、经济,以及人类生产、生活造成了严重影响。一直以来,赤潮受到研究者的广泛关注,但由于它的形成机制比较复杂,使得赤潮预报极具挑战性。针对赤潮预报的研究问题,本文收集了厦门海域赤潮发生前后的海洋监测数据,结合皮尔逊相关系数、散布矩阵、复相关系数方法,分析多环境因子与赤潮发生多要素的关联情况,重点采用基于深度学习的LSTM与CNN融合方法,挖掘环境因子的时序依赖,发现序列数据的局部特征,对赤潮发生进行预报。在厦门一号和厦门二号数据集中,本方法在预报未来12 h内的赤潮情况时,RMSE、MAE误差分别达到0.521 8、0.504 3。通过协同对比模型进一步确定赤潮发生的预报概率,在两个数据集上的最终预报准确率分别为67.58%和63.49%。本研究为赤潮的分析预报提供了探索经验,证明了将深度学习方法应用于赤潮预报的可行性。 相似文献
8.
9.
大鹏湾夜光藻赤潮的营养动力学模型 总被引：1，自引：0，他引：1
根据大鹏湾夜光藻Noctilucascintillans赤潮发生要素的结构关系，利用生物种群生态学和营养动力学的原理，提出夜光藻－硅藻－营养物质三者相关的动力学模型，模型中的参数将体现海况环境的有关因素。文中利用微分方程动力系统理论对模型作出定性分析，给出赤潮发生与否的某些判别条件；并根据1991年3月1日一4月30日大鹏湾所发生的夜光藻赤潮数据分别对1次赤潮全过程和有连续3次赤潮的情形进行了有效的数值模拟，所得结果对赤潮的预测预报研究有一定的参考价值。 相似文献
10.
大鹏湾夜光藻赤潮的营养动力学模型 总被引：11，自引：0，他引：11
根据大鹏湾夜光藻赤潮发生要素的结构关系，利用生物种群生态学和营养动力学的原理，提出夜光藻－硅藻－营养物质三者相关的动力学模型，模型中的参数瘵体现海况环境的有关因素。文中利用微分方程动力系统理论对模型作出定性分析，给出赤潮发生与否的某些判别条件；并根据１９９１年３月１日－４月３０日大鹏湾所发生的夜光藻赤潮数据地１次赤潮全过程和有连续３次赤潮的情形进行了有效的数值模拟，所得结果对赤潮的预测预报研究有一 相似文献
11.
Cheng-Wu CHEN Hsien-Chueh Peter YANG Chen-Yuan CHEN Alex Kung-Hsiung CHANG Tsung-Hao CHEN 《中国海洋工程》2008,22(1)
Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p＜0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions 1, 2 and 3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to check the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height (X1) and potential energy (X2) significantly impact (p＜0.0001) the amplitude-based reflected rate; the P-values for the deviance and Pearson are all ＞0.05 (0.2839, 0.3438, respectively). That is, the goodness-of-fit between ridge height (X1) and potential energy (X2) can further predict parameters under the scenario of the best parsimonious model.Investigation of 6 predictive powers (R2, Max-rescaled R2, Somers'D, Gamma, Tau-a, and c, respectively) indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model. 相似文献
12.
Evaluation of Inference Adequacy in Cumulative Logistic Regression Models： An Empirical Validation of ISW-Ridge Relationships 总被引：3，自引：0，他引：3
Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p<0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to check the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height (X1) and potential energy (X2) significantly impact (p<0.0001) the amplitude-based reflected rate; the P-values for the deviance and Pearson are all >0.05 (0.2839, 0.3438, respectively). That is, the goodness-of-fit between ridge height (X1) and potential energy (X2) can further predict parameters under the scenario of the best parsimonious model.Investigation of 6 predictive powers (R2, Max-rescaled R2, Somers'D, Gamma, Tau-a, and c, respectively) indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model. 相似文献
13.
Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p＜0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions 1, 2 and 3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to check the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height (X1) and potential energy (X2) significantly impact (p＜0.0001) the amplitude-based reflected rate; the P-values for the deviance and Pearson are all ＞0.05 (0.2839, 0.3438, respectively). That is, the goodness-of-fit between ridge height (X1) and potential energy (X2) can further predict parameters under the scenario of the best parsimonious model.Investigation of 6 predictive powers (R2, Max-rescaled R2, Somers''D, Gamma, Tau-a, and c, respectively) indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model. 相似文献
14.
针对半参数回归模型求解过程可能出现的法方程病态问题，提出了用岭估计原则改进半参数模型的求解。通过模拟算例将岭估计解法和其他方法进行了比较，结果表明，岭估计解法能较好地解决半参数回归模型求解过程中的病态问题。 相似文献
15.
利用雷雨、大风等灾害天气资料和电力事故历史数据资料,分析了电力事故发生的时空分布特征及其与雷雨、大风、日平均气温等天气要素之间的关系。进而利用事件概率回归(regression estimation of event probability,REEP)和Logistic回归分析方法,得到了日照市电力事故发生概率与雷雨、大风和日平均气温之间关系的预警模型。研究结果表明:1)雷雨、大风是造成日照市电力事故的重要气象因素。2)雷雨、大风和高温等灾害天气对电力事故的发生虽都有促成作用,但影响能力存在较大差距。3)两种回归分析模型对因子和变量之间关系均有较好的拟合效果,相较而言,REEP模型更为直观,Logistic回归分析方法更为客观,适用性更强。4)回归分析结果建立在客观资料基础上,回归模型具有准确性、实用性,可为电力事故预警发布系统提供理论和技术支持。 相似文献
16.
辽河口湿地生态景观格局形成机制分析 总被引：1，自引：0，他引：1
利用2007年景观格局图、DEM数据、人口、GDP等数据,运用地理信息系统(GIS)和Logistic回归分析模型相结合的分析方法,揭示辽河口湿地景观格局形成机制。结果表明:建筑用地、芦苇地、水稻田和养殖区的Logistic回归模型具有较好的拟合优度。模拟结果表明,转为建筑用地的Logistic回归模型的重要的解释变量是农村人口密度和城镇人口密度;转为芦苇地的Logistic回归模型的重要的解释变量是农村人口密度和过境水资源量;转为水稻田和养殖区的Logis-tic回归模型的重要的解释变量都是农村人口密度和第一产业值。在这4种生态景观格局的二元Logistic回归模型中最重要的解释变量都是农村人口密度,这表明辽河口湿地景观格局形成最主要的驱动因素是农村人口密度。 相似文献
17.
地图扫描数字化系统误差分析及对策探讨 总被引：1，自引：1，他引：0
较全面地分析了地图扫描数字化的系统误差来源及影响。在系统误差纠正模型的选取过程中所采用的数据存在粗差，纠正模型的误差和模型数据的粗差是值得讨论的问题。利用粗差拟准检定法探测粗差准确的优点和判断函数模型的准则理论，提出顾及粗差的系统误差回归函数分析，先确定回归函数，在此基础上进行粗差探测与剔出，然后再进行回归分析，以达到消弱系统误差最优的目的。 相似文献
18.
Combining a linear regression and a temperature budget formula, a multivariate regression model is proposed to parameterize and estimate sea surface temperature(SST) cooling induced by tropical cyclones(TCs). Three major dynamic and thermodynamic processes governing the TC-induced SST cooling(SSTC), vertical mixing, upwelling and heat flux, are parameterized empirically using a combination of multiple atmospheric and oceanic variables:sea surface height(SSH), wind speed, wind curl, TC translation speed and surface net heat flux. The regression model fits reasonably well with 10-year statistical observations/reanalysis data obtained from 100 selected TCs in the northwestern Pacific during 2001–2010, with an averaged fitting error of 0.07 and a mean absolute error of 0.72°C between diagnostic and observed SST cooling. The results reveal that the vertical mixing is overall the pre dominant process producing ocean SST cooling, accounting for 55% of the total cooling. The upwelling accounts for 18% of the total cooling and its maximum occurs near the TC center, associated with TC-induced Ekman pumping. The surface heat flux accounts for 26% of the total cooling, and its contribution increases towards the tropics and the continental shelf. The ocean thermal structures, represented by the SSH in the regression model,plays an important role in modulating the SST cooling pattern. The concept of the regression model can be applicable in TC weather prediction models to improve SST parameterization schemes. 相似文献
19.
基于浮标站海浪历史数据,利用回归分析方法建立了海浪数值模式有效波高预报产品的一元二次回归方程订正统计模型。通过2017年7月1日-2018年10月10日期间业务试运行结果发现:订正方程能有效改善有效波高数值预报产品的预报精度,且预报时效越短订正效果越显著。其中,第6~11 h预报时效内的订正前后平均绝对误差值减小0.17~0. 241 m,第6~18 h预报时效内订正前后均方根误差减小幅度为0.103~0. 28 m。这说明应用订正统计模型对海浪模式输出产品进行订正,也是改进海浪模式预报准确率的一种有效途径。 相似文献