电阻率二维神经网络反演   总被引：32，自引：4，他引：28       下载免费PDF全文

徐海浪  吴小平 《地球物理学报》2006,49(2):584-589

由于非线性特性地球物理反演一直以来都是一个比较困难的问题. 近十年来,非线性反演方法如人工神经网络、遗传算法在地球物理数据解释中得到越来越多的应用,但目前基本仍限于一维反演问题. 对于二维反问题,反演参数较多,神经网络反演运用较少. 本文利用BP神经网络优化方法,实现了电阻率二维非线性反演. 与传统线性化的迭代反演比较,神经网络反演能够克服传统方法的不足、获得更好的反演结果.  相似文献   

GPS高程拟合中神经网络法的基本思想     

于世岩  吉丽 《测绘与空间地理信息》2007,30(2):77-79

高程问题一直是困扰GPS的问题之一,而不同的GPS高程拟合方法都有其适用条件,并且精度不等。本文在对人工神经网络的基本原理、神经元模型、网络结构、数据结构和训练方式等研究的基础上,给出一种新的算法(新BP算法)。以“阜新控制网改造工程”作为一个具体实例,使用Matlab语言来完成GPS高程的拟合,并与其他方法作了比较,最后给出有益的结论。  相似文献   

基于大数据分析下的气候模型     

张宸豪  冯曦  冯卫兵  刘涛  丁坤 《海洋科学》2020,44(10):1-11

为研究全球变暖与极寒天气间的关系,对加拿大13个省代表性测站10年的观测数据进行时空变化趋势分析,采用经验正交函数（EOF）寻找海洋表面温度历史数据的变化规律。另外利用BP神经网络建立了年平均温度、日降水量与地球吸热、散热、海表面温度、当地纬度间的关系,预测未来25年气候的变化,并建立了“极寒天气”与气候变化的关系模型。研究表明：高纬度地区温度、降水量普遍较低,同经度地区的温度差异较小且降水量变化不大;加拿大地区温度呈周期性变化,符合北半球的季节变化特征;北大西洋的东部与其他海洋的温度是反相关的,西太平洋南北回归线附近的海洋表面温度升高;“极寒天气”出现频率与气候变化有一定关系,局地极寒现象与全球变暖的大趋势并不矛盾。本研究为人们认识和理解“全球变暖”提供了一个新的思路。  相似文献   

最优权组合预测法在采煤沉陷变形预测中的应用   总被引：1，自引：0，他引：1  

鲁小红 《测绘通报》2020,(4):111-115

煤矿地表沉降变形预测多基于煤矿开采沉陷预计理论展开,基于变形分析理论的变形预测模型目前多集中在单模型预测。本文基于组合预测思想,以非等间隔灰色预测模型与BP神经网络模型为预测单模型,以陕西北部某煤矿采煤工作面上方实测地表沉降值为数据源,以最优加权法对单模型预测结果开展了最优权组合,组合模型中两种单模型的权重分别为0.466 7、0.533 3。选取部分监测点的预测结果进行模型精度评价,结果表明：3种预测模型精度均达到了一级。经对比3种模型预测结果,最优权组合预测的模型精度较单模型明显提升,预测结果较非等间隔灰色预测模型与BP神经网络预测模型有明显增益。  相似文献   

Biogeochemical Variation in Dimethylsulfide, Phytoplankton Pigments and Heterotrophic Bacterial Production in the Subarctic North Pacific during Summer     

Kazushi Aranami  Shuichi Watanabe  Shizuo Tsunogai  Masato Hayashi  Ken Furuya  Toshi Nagata 《Journal of Oceanography》2001,57(3):315-322

Dimethylsulfide (DMS), chlorophyll a (Chl-a), accessory pigments (fucoxanthin, peridinin and 19-hexanoyloxyfucoxanthin), and bacterial production (BP) were measured in the surface layer (0–100 m) of the subarctic North Pacific, including the Bering Sea, during summer (14 July–5 September, 1997). In surface sewater, the concentrations of DMS and Chl-a varied widely from 1.3 to 13.2 nM (5.1 ± 3.0 nM, mean ± S.D., n = 48) and from 0.1 to 2.4 µg L^–1 (0.6 ± 0.6 µg L^–1, n = 24), respectively. In the subarctic North Pacific, DMS to Chl-a ratios (DMS/Chl-a) were higher on the eastern side than the western side (p < 0.0001). Below the euphotic zone, DMS/Chl-a ratios were law and the correlation between DMS and Chl-a was relatively strong (r ² = 0.700, n = 27, p < 0.0001). In the euphotic zone, DMS/Chl-a ratios were higher and the correlation between DMS and Chl-a was weak (r ² = 0.128, n = 50, p = 0.01). The wide variation in DMS/Chl-a ratios would be at least partially explained by the geographic variation in the taxonomic composition of phytoplankton, because of the negative correlation between DMS/Chl-a and fucoxanthin-to-Chl-a ratios (Fuc/Chl-a) (r ² = 0.476, n = 26, p = 0.0001). Furthermore, there was a positive correlation between DMS and BP (r ² = 0.380, n = 19, p = 0.005). This suggests that BP did not represent DMS and dimethylsulfoniopropionate (DMSP) removal by bacterial consumption but rather DMSP degradation to DMS by bacterial enzyme.  相似文献   

Application of an ecosystem model for the environmental assessment of the reclamation and mitigation plans for seagrass beds in Atsumi Bay   总被引：1，自引：0，他引：1  

Akio Sohma  Yasuyuki Sekiguchi  Kisaburo Nakata 《Estuarine, Coastal and Shelf Science》2009

An ecosystem model was used to evaluate the effects of reclaiming seagrass beds and creating artificial shallows with seagrass beds to mitigate the effects of the reclamation. The applied model can simulate the pelagic and benthic ecosystems including seagrass beds and tidal flats. The objectives of this study were (a) to investigate the likelihood of cultivating and maintaining seagrass beds in artificial shallows (Part 1), and (b) to understand the effects of the reclamation of seagrass beds and the creation of artificial shallows on the water quality in the estuary (Part 2). In Part 1, first, the nutrient turnover rates due to both biochemical and physical processes in the natural seagrass beds where reclamation is proposed were analyzed. Biological processes rather than physical processes were the most significant driving forces of nutrient cycles in seagrass beds. Second, the effects of filter feeding benthic fauna (suspension feeders) in the seagrass beds were analyzed. The scenario with suspension feeders resulted in higher transparency of the water column (8.7% decrease in the light attenuation coefficient) and an increase in nutrient supply (24.9% increase in NH₄-N in the water column) contributing to the high specific growth rate of seagrass. Third, the specific growth rate of seagrass on the proposed artificial shallows was measured. The value on the artificial shallows set at a depth of datum line minus 0.8 m (D.L. − 0.8 m) was approximately the same as that of the natural seagrass beds. In Part 2, first, water quality in the estuary was compared among the scenarios with/without natural seagrass beds and artificial shallows. Then, the defined values of the water purification capability of (a) artificial shallows with/without seagrass beds, and (b) natural seagrass beds per unit area were evaluated. The reclamation of the natural seagrass beds resulted in a decrease of the removal of phytoplankton and detritus from the pelagic system (i.e. resulted in a loss in the purification rate). In contrast, the creation of artificial shallows resulted in an increase of the removal of phytoplankton and detritus from the pelagic system (i.e. resulted in a gain in the purification rate). Based on an annual average, approximately twice as much phytoplankton was removed from the artificial shallows at the depth D.L. − 0.8 m, than at the depth, D.L. − 1.5 m, and the artificial shallows with seagrass beds removed pelagic DIN and DIP at a rate 120% higher than that without seagrass beds.  相似文献   

���ڻز�ǿ�ȵĺ��׵��ʷ���ϵͳ�ؼ�����     

何林帮  冯杰 《大地测量与地球动力学》2015,35(1):140-144

???????????????????????????????????????????????????ALL????????????????洢????????????????????????ALL???????????????????????????????????????????е???????????γ?????????????????????????????????????????BP?????????????????????к????????????????????????????????Ч????????????????ò??????????????????  相似文献   

BP�����������Ǽ�������Զ��ָ����ģ�е�Ӧ��     

朱程广  郭唐永  邹彤  李世鹏  林强  王雅杰 《大地测量与地球动力学》2013,33(5):150-153

????????????????????????????????????BP???????????????????人???????????????????????????????????BP??????????????????г????????????????????????о??????????BP????????????????????????????????????????????????  相似文献   

基于改进BP神经网络的海底底质分类   总被引：2，自引：0，他引：2       下载免费PDF全文

唐秋华  刘保华  陈永奇  周兴华 《海洋测绘》2009,29(5):40-43

通过采用遗传算法优化神经网络初始权值的方法,将GA算法与BP神经网络有机结合,应用于海底底质分类。基于多波束测深系统获取的反向散射强度数据,应用改进的BP神经网络分类方法,实现对海底基岩、砾石、砂、细砂和泥等底质类型的快速、准确识别。通过实验比较,GA-BP神经网络分类精度明显高于BP神经网络,证明了该方法的有效性和可靠性。  相似文献   

基于贝叶斯正则化BP神经网络的DEM趋势面逼近   总被引：2，自引：0，他引：2       下载免费PDF全文

陈再辉  江丽钧  朱晓燕  江伟勇 《海洋测绘》2009,29(4):32-34

趋势面从宏观上揭示了研究对象的特性,在各领域发挥着重要作用。BP神经网络可以对复杂系统进行无限逼近,进而进行预测。建立了基于贝叶斯正则化BP神经网络的数字高程模型趋势面,与二次多项式建立的数字高程模型趋势面进行比较分析,证明了该方法的可行性和有效性。  相似文献