多形态崩塌智能监测系统在北京突发地质灾害监测预警工程中的应用

采用基于微纳技术(MEMS技术)的高性能三维运动姿态测量系统,主要包括三轴陀螺仪.三轴加速度计,三轴电子罗盘等运动传感器,实现多形态崩塌智能监测。     

智能学发的启迪

遵循智能学发展史,概略地考察古代智能学及其终结、近代和现代智能学的特点,以及一些知名学者的学术经历简要情况;对智能学与数学、哲学、心理学、信息科学等的关系和智能学发展规律和未来趋势作了分析。     

开展竞争情报研究工作的思考

文章介绍了竞争情报的一些基本概念,对在地勘单位中开展竞争情报工作的必要性和可行性进行论述,提出一些建议及地勘单位的情报工作在转轨过程中如何发展的思路     

Artificial Intelligence and headland-bay beaches

Headland-bay beaches are a typical feature of many of the world's coastlines. Their curved planform has aroused much interest since the early days of Coastal Engineering. Modelling this characteristic planform is a task of great interest, not least in relation to projects of coastal structures whose effects on the shoreline must be studied from the planning stages. In this work, Artificial Intelligence is applied to this task—in particular, artificial neural networks (ANNs). Unlike conventional planform models, they are not based on a given mathematical expression of the shoreline curve. Instead, they learn from experience (from a number of training cases) how the planform of a headland-bay beach is shaped, with due regard to the obliquity of incident waves. Three artificial neural networks, with different input/output structures, are implemented and subsequently trained with a number of bays. Once trained, they are tested for validation on other headland-bay beaches. Finally, the most performing neural network is compared with a state-of-the-art planform model.     

基于案例推理的东海区鲐鱼中心渔场预报

根据1998～2005年的东海区上海、宁波、江苏和舟山四大渔业公司的鲐鱼(Pneumatophorus japonicus)生产统计数据以及同期的卫星资料反演的海表温度、叶绿素a浓度数据,利用案例推理方法,设定了上级结果的相似距对下级检索的影响权重因子,进一步研究渔场渔情的分析预报.通过试验性预报实例的预报结果与实际情况比较表明,预测精度达到75%,可以较好地反映出渔场的分布,为渔业资源的开发利用服务.     

Classifiers vs. input variables—The drivers in image classification for land cover mapping

The study investigates the performance of image classifiers for landscape-scale land cover mapping and the relevance of ancillary data for the classification success in order to assess and to quantify the importance of these components in image classification. Specifically tested are the performance of maximum likelihood classification (MLC), artificial neural networks (ANN) and discriminant analysis (DA) based on Landsat7 ETM+ spectral data in combination with topographic measures and NDVI. ANN produced high accuracies of more than 75% also with limited input information, while MLC and DA produced comparable results only by incorporating ancillary data into the classification process. The superiority of ANN classification was less pronounced on the level of the single land cover classes. The use of ancillary data generally increased classification accuracy and showed a similar potential for increasing classification accuracy than the selection of the classifier. Therefore, a stronger focus on the development of appropriate and optimised sets of input variables is suggested. Also the definition and selection of land cover classes has shown to be crucial and not to be simply adaptable from existing land cover class schemes. A stronger research focus towards discriminating land cover classes by their typical spectral, topographic or seasonal properties is therefore suggested to advance image classification.     

尖紫蛤的人工育苗

1997年 7月开始进行尖紫蛤人工育苗的研究 ,1999年 11月培育出壳长 4 mm左右的幼苗近30万只 ,首次获得尖紫蛤人工育苗的成功     

Wave hindcasting by coupling numerical model and artificial neural networks

By coupling numerical wave model (NWM) and artificial neural networks (ANNs), a new procedure for wave prediction is proposed. In many situations, numerical wave modeling is not justified due to economical consideration. Although incorporation of an ANN model is inexpensive, such a model needs a long time period of wave data for training, which is generally inconvenient to achieve. A proper combination of these two methods could carry the potentials of both. Based on the proposed approach, wave data are generated by a NWM by means of a short period of assumed winds at a concerned point. Then, an ANN is designed and trained using the above-mentioned generated wind-wave data. This ANN model is capable of mapping wind-velocity time series to wave height and period time series with low cost and acceptable accuracy. The method was applied for wave hindcasting to two different sites; Lake Superior and the Pacific Ocean. Simulation results show the superiority of the proposed approach.     

Radiation of lamp and optimized experiment using artificial light in the Arctic Ocean

A winter optical experiment by an artificial lamp was conducted in the Amundsen Bay of Arctic Ocean from November of 2007 to January of 2008.The radiation field emitted from an artificial lamp was measured and is introduced in this paper ,and the optimized experiment project is discussed.It is demonstrated that the minimum size allowed of the lamp is determined by both the field of view(FOV) of optical instrument and the measuring distance from the lamp.Some problems that might influence on the experimen...     

Effects of prediction accuracy of the proportion of vegetation cover on land surface emissivity and temperature using the NDVI threshold method

Predicting land surface energy budgets requires precise information of land surface emissivity (LSE) and land surface temperature (LST). LST is one of the essential climate variables as well as an important parameter in the physics of land surface processes at local and global scales, while LSE is an indicator of the material composition. Despite the fact that there are numerous publications on methods and algorithms for computing LST and LSE using remotely sensed data, accurate prediction of these variables is still a challenging task. Among the existing approaches for calculating LSE and LST, particular attention has been paid to the normalised difference vegetation index threshold method (NDVI^THM), especially for agriculture and forest ecosystems. To apply NDVI^THM, knowledge of the proportion of vegetation cover (P_V) is essential. The objective of this study is to investigate the effect of the prediction accuracy of the P_V on the estimation of LSE and LST when using NDVI^THM. In August 2015, a field campaign was carried out in mixed temperate forest of the Bavarian Forest National Park, in southeastern Germany, coinciding with a Landsat-8 overpass. The P_V was measured in the field for 37 plots. Four different vegetation indices, as well as artificial neural network approaches, were used to estimate P_V and to compute LSE and LST. The results showed that the prediction accuracy of P_V improved using an artificial neural network (R²_CV = 0.64, RMSE_CV = 0.05) over classic vegetation indices (R²_CV = 0.42, RMSE_CV = 0.06). The results of this study also revealed that variation in the accuracy of the estimated P_V affected calculation results of the LSE. In addition, our findings revealed that, though LST depends on LSE, other parameters should also be taken into account when predicting LST, as more accurate LSE results did not increase the prediction accuracy of LST.