Big data-driven water research towards metaverse

Although big data is publicly available on water quality parameters,virtual simulation has not yet been adequately adapted in environmental chemistry research.Digital twin is different from conventional geospatial modeling approaches and is particularly useful when systematic laboratory/field experiment is not realistic(e.g.,climate impact and water-related environmental catastrophe)or difficult to design and monitor in a real time(e.g.,pollutant and nutrient cycles in estuaries,soils,and sediments).Data-driven water research could realize early warning and disaster readiness simulations for diverse environmental scenarios,including drinking water contamination.

Detection of landuse/landcover changes using remotely-sensed data

We evaluated the use of spatial sampling and satellite images to identify deforested areas in Wonju, South Korea. The changes in land cover were identified using a grid of sample points overlaid onto medium and high-resolution remote sensing （RS） satellite images. Deforestation identified in this way （hereafter, RSD） was compared to administrative data on deforestation. We also compared high-resolution satellite images （HR-RSD） and actual deforestation based on categories which were Intergovernmental Panel on Climate Change data. RSD generated by medium-resolution satellite images overesti- mated the amount of deforested area by 1.5-2.4 times the actual deforested area, whereas RSD generated by HR- RSD underestimated the amount of deforested area by 0.4-0.9 times the actual area. The highest degree of matching （90 %） was found in HR-RSD with a grid interval of 500 m and the accuracy of HR-RSD was the highest, at 67 %. The results also revealed that the largest cause of deforestation was the establishment of settlements followed by conversion to cropland and grassland. We conclude that for the identification of deforestation using satellite images, HR-RSD with a grid interval of 500 m is most suitable.

Using Boosted Regression Trees and Remotely Sensed Data to Drive Decision-Making

Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.

AN IMPROVED ALGORITHM FOR SUPERVISED FUZZY C-MEANS CLUSTERING OF REMOTELY SENSED DATA

This paper describes an improved algorithm for fuzzy c-means clustering of remotely sensed data, by which the degree of fuzziness of the resultant classification is de- creased as comparing with that by a conventional algorithm: that is, the classification accura- cy is increased. This is achieved by incorporating covariance matrices at the level of individual classes rather than assuming a global one. Empirical results from a fuzzy classification of an Edinburgh suburban land cover confirmed the improved performance of the new algorithm for fuzzy c-means clustering, in particular when fuzziness is also accommodated in the assumed reference data.

Extending self-organizing maps for supervised classification of remotely sensed data

An extended self-organizing map for supervised classification is proposed in this paper.Unlike other traditional SOMs,the model has an input layer,a Kohonen layer,and an output layer.The number of neurons in the input layer depends on the dimensionality of input patterns.The number of neurons in the output layer equals the number of the desired classes.The number of neurons in the Kohonen layer may be a few to several thousands,which depends on the complexity of classification problems and the classification precision.Each training sample is expressed by a pair of vectors: an input vector and a class codebook vector.When a training sample is input into the model,Kohonen's competitive learning rule is applied to selecting the winning neuron from the Kohonen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector,and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector.If the number of training samples is sufficiently large and the learning epochs iterate enough times,the model will be able to serve as a supervised classifier.The model has been tentatively applied to the supervised classification of multispectral remotely sensed data.The author compared the performances of the extended SOM and BPN in remotely sensed data classification.The investigation manifests that the extended SOM is feasible for supervised classification.

基于电流多特征融合的窄间隙P-GMAW摆动电弧传感焊缝跟踪方法

电弧传感是实现窄间隙焊接焊缝跟踪的主要方式之一。针对电弧传感稳定性差、可靠性低的问题,提出融合摆动周期内电流信息的多个统计学特征进行偏差提取的方法,克服单一数据特征容易受到电弧稳定性影响、导致传感精度下降的问题。首先,提取电流信号的多个时域特征,计算特征矩阵与偏差矢量相关性;然后,取相关性高的特征用主成分分析的方法进行融合,取前两个主成分作为观测数据;最后,基于多分类的支持向量机模型对其进行分类试验。试验结果表明最大误差为0.2 mm,0.1 mm以内的误差占93.75%。该方法对比传统方法精度有所提升,对比神经网络方法,所用训练样本少,训练过程更加简单。

基于OCO-2卫星数据的中国CO_(2)浓度时空变化特征

大气CO_(2)浓度增加引起的全球变暖问题是国内外学者关注的热点议题,但对CO_(2)的监测一直存在较多的不确定性。利用2015—2022年OCO-2卫星观测的CO_(2)柱浓度混合比数据(XCO_(2)),基于克里金插值和标准差椭圆等方法,分析了中国CO_(2)浓度时空分布与变化特征,有以下3个结论。1)基于OCO-2卫星数据的XCO_(2)数据集精度较高,与地面监测站(瓦里关站、鹿林站)观测结果的均方根误差仅为1.75 ppm和1.58 ppm,相关系数分别为0.91和0.96。2)年际上,2015—2022年中国年均XCO_(2)由399.52 ppm增至417.64 ppm,年均增速为2.56 ppm/a,高于过去10年全球CO_(2)浓度平均增速(2.06 ppm/a),但在2019年之后XCO_(2)增速呈下降趋势。季节上,XCO_(2)具有明显的季节变化特征,春季XCO_(2)最高,夏季最低。3)空间分布上,XCO_(2)表现出东部高,西部、东北地区低的空间分布特征。XCO_(2)浓度高值区域集中在京津冀和长三角等城市群。中国东北、西南地区XCO_(2)增速较快,高于华东、华南等经济发达地区。

DCGAN Based Spectrum Sensing Data Enhancement for Behavior Recognition in Self-Organized Communication Network

Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.

Calibrating Remotely Sensed Ocean Chlorophyll Data: An Application of the Blending Technique in Three Dimensions (3D)

In this article, the extension to three dimensions (3D) of the blending technique that has been widely used in two dimensions (2D) to calibrate ocean chlorophyll is presented. The results thus obtained revealed a very high degree of efficiency when predicting observed values of ocean chlorophyll. The mean squared difference between the predicted and observed values of ocean chlorophyll when 3D technique was used fell far below the tolerance level which was set to the difference between satellite and observed in-situ values. The resulting blended field did not only provide better predictions of the in situ observations in areas where bottle samples cannot be obtained but also provided a smooth variation of the distribution of ocean chlorophyll throughout the year. An added advantage is its computational efficiency since data that would have been treated at least four times would be treated only once. With the advent of these results, it is believed that the modelling of the ocean life cycle will become more realistic.

The Identification and Geological Significance of Fault Buried in the Gasikule Salt Lake in China based on the Multi-source Remote Sensing Data

The salinity of the salt lake is an important factor to evaluate whether it contains some mineral resources or not,the fault buried in the salt lake could control the abundance of the salinity.Therefore,it is of great geological importance to identify the fault buried in the salt lake.Taking the Gasikule Salt Lake in China for example,the paper established a new method to identify the fault buried in the salt lake based on the multi-source remote sensing data including Landsat TM,SPOT-5 and ASTER data.It includes the acquisition and selection of the multi-source remote sensing data,data preprocessing,lake waterfront extraction,spectrum extraction of brine with different salinity,salinity index construction,salinity separation,analysis of the abnormal salinity and identification of the fault buried in salt lake,temperature inversion of brine and the fault verification.As a result,the study identified an important fault buried in the east of the Gasikule Salt Lake that controls the highest salinity abnormal.Because the level of the salinity is positively correlated to the mineral abundance,the result provides the important reference to identify the water body rich in mineral resources in the salt lake.

基于SSA-BGOMP的滚动轴承振动信号压缩重构方法

针对广义正交匹配追踪算法(GOMP)在进行滚动轴承振动信号压缩感知重构的迭代过程中无法剔除错误原子,重构效果较差的问题,提出了基于麻雀搜索算法-回溯广义正交匹配追踪(SSA-BGOMP)的轴承振动信号压缩重构方法,在GOMP的基础上引入具有自适应特性的改进回溯机制,通过麻雀搜索算法自动设置阈值,对支撑集原子进行二次回溯筛选,从而降低错误原子选入支撑集的概率,提升算法的抗噪性和重构效果。仿真信号以及CWRU,XJTU-SY轴承故障数据集的试验结果表明:在DCT和K-SVD字典上,SSA-BGOMP比GOMP的相对误差分别降低2%~12%与3%~13%,有效改善了滚动轴承振动信号的压缩重构效果。

基于HHO-SVM的抗SSDF攻击协作频谱感知方法

针对认知无线电网络中的频谱感知数据伪造(spectrum sensing data falsification,SSDF)攻击问题,提出一种基于哈里斯鹰优化(Harris hawks optimization,HHO)算法和支持向量机(support vector machine,SVM)的抗SSDF攻击协作频谱感知方法。首先从报告信息矩阵中提取用于区分次用户(secondary users,SU)类别的特征向量。其次通过HHO算法优化SVM内核参数,通过优化的SVM模型检测恶意SU,提高了在复杂感知环境中对SU分类的准确率。最后根据优化的SVM模型计算获得SU的可信度,并以可信度为权重融合感知数据,进一步加强系统的抗攻击性。仿真结果表明,所提方法能够对不同的SSDF攻击场景实现有效防御,相比现有的方法具有更好的频谱感知性能。

EASE-Grid投影风云卫星产品地理信息写入方法

风云卫星遥感数据服务网的卫星遥感产品数据集中,风云三系列气象卫星遥感产品数据集中很多采用的是等面积可伸缩地球网格(EASE-Grid)投影方式进行处理,实际应用中对使用者具有较高的数据处理能力要求,不利于遥感产品数据集的省级应用。基于数据集使用中的这些问题,该文以FY3D雪水当量数据集产品为例,采用程序化方法对EASE-Grid投影产品数据集的地理信息进行写入,通过构建地理坐标系参考对象和地理信息目录,将数据矩阵中写入地理信息并以GeoTiff格式文件输出。结果表明,经过该方法处理过的产品数据可与矢量文件实现准确的经纬度信息的匹配,降低了数据分析处理的难度。该方法具有较好的适用性,对于EASE-Grid的三种不同的投影方式均适用,可在一定程度上提高卫星遥感产品数据集的省级科研与应用水平。

基于Mask R-CNN的试管-支架系统Data Matrix码识别方法

在试管-支架自动化系统的输入图像中,Data Matrix(DM)码呈现为多个小目标,图像存在成像模糊、边缘干扰严重等问题,使得传统方法难以达到良好的识别效果。为此,提出一种基于深度学习的Data Matrix码识别方法DeepDMCode,以Mask R-CNN模型为基础,通过内容差异化数据合成和同步自动化标注,实现训练数据的增强,提升模型的学习能力。在模型分割结果的基础上,提出一种旋转校正方法,确保可用标准解码库实现DM码的解码。以分辨率为1600×1200、支架容量为96的数据实验表明,由于该方法在前期码定位阶段最大程度地还原码边界信息,准确度可达0.92(mIoU),完成单张图像中所有DM识别的平均速度为5.2 s,优于YOLO、SegNet、CenterNet等主流工业基准算法。

Dynamics analysis and cryptographic implementation of a fractional-order memristive cellular neural network model

Due to the fact that a memristor with memory properties is an ideal electronic component for implementation of the artificial neural synaptic function,a brand-new tristable locally active memristor model is first proposed in this paper.Here,a novel four-dimensional fractional-order memristive cellular neural network(FO-MCNN)model with hidden attractors is constructed to enhance the engineering feasibility of the original CNN model and its performance.Then,its hardware circuit implementation and complicated dynamic properties are investigated on multi-simulation platforms.Subsequently,it is used toward secure communication application scenarios.Taking it as the pseudo-random number generator(PRNG),a new privacy image security scheme is designed based on the adaptive sampling rate compressive sensing(ASR-CS)model.Eventually,the simulation analysis and comparative experiments manifest that the proposed data encryption scheme possesses strong immunity against various security attack models and satisfactory compression performance.

基于Sentinel-2影像的果树提取方法及其空间分析研究——以甘肃省平凉市为例

利用遥感技术对果园进行快速监测,准确掌握苹果园地面积与空间种植分布状况,有助于促进当地经济的发展。目前针对丘陵区果园提取的研究较少,相关方法的有效性和可靠性仍然存在问题。以甘肃省平凉市为研究区域,采用NDVI,RVI,EVI,SIPI,LSWI,NDWI等指标对输入数据进行增强,通过基于数据增强的梯度提升树算法提取研究区苹果种植面积。为验证该方法的有效性,引入最小距离法、CART决策树法、支持向量机法和随机森林4种机器学习算法进行对比分析,结果表明,梯度提升树算法分类精度最高,总体分类精度(Overall Accuracy,OA)达到89.3%,Kappa系数为0.77,分类效果及一致性均最佳。此外,采用基于数据增强的梯度提升树法分别对2019—2023年的苹果园进行提取,获得平凉市苹果园种植变化情况,各区县苹果园种植面积除泾川县外整体呈现上升趋势,泾川县和静宁县种植面积最大,其次为庄浪县、灵台县和崆峒区,最小的为崇信县和华亭市。

面向边缘智能网络的通-感-算融合:架构、挑战和展望

通-感-算融合作为边缘智能网络的赋能手段,可以有效实现海量数据的实时采集、传输和处理,从而为各行各业提供高效、实时的智能服务。首先,基于边缘智能网络的特点,明确了通-感-算功能的定义,提出了通-感-算融合赋能的网络架构和系统架构,给出了通-感-算融合的典型应用场景。其次,重点分析了在边缘智能网络中实现通-感-算融合的关键挑战,包括海量数据处理、复杂干扰协调和联合资源管理,并提供了相应的解决方案。最后,展望了未来可行的研究方向。

Groundwater Resource Mapping through the Integration of Geology, Remote Sensing, Geographical Information Systems and Borehole Data in Arid-Subarid Lands at Turkana South Sub-County, Kenya

The integrated approach of various techniques which historically have been used independently is key to successful exploration, development, exploitation and management of the groundwater resources. The integration of Remote Sensing (RS), Geographical Information Systems (GIS) and Borehole data has been used in the study area to assess their applicability in groundwater investigation. The area of study lies in the arid and semi-arid lands (ASALs) where principally remote sensing data has been used in extraction of various thematic maps (lithology, lineament, drainage density, and Digital Elevation Model Maps) for groundwater assessment. The GIS platform was used in integrating the RS data and data of productive boreholes. The lineaments generated through remote sensing agree well with structural geology of the area, where high density lineament points overlays the points of intense faulting. Lineaments found in the area correlate well with fault zones, fractures, and lithological contrasts as supported by geological map and structural map. Weathering, faulting and fracturing of the rocks mean a possible increase or a reduction in specific capacities as observed in productive boreholes in sedimentary rocks or igneous/basaltic rocks of the area. Similarly, it is noted that the degree of faulting affects the degree of radius of influence of a borehole in a particular area. These analyses show that groundwater potential within the Sub-County varies spatially with high dependency on geological structures in the basement region and more on geology within the volcanic and younger sediments.

Reconstructive Mapping from Sparsely-Sampled Groundwater Data Using Compressive Sensing

Compressive sensing is a powerful method for reconstruction of sparsely-sampled data, based on statistical optimization. It can be applied to a range of flow measurement and visualization data, and in this work we show the usage in groundwater mapping. Due to scarcity of water in many regions of the world, including southwestern United States, monitoring and management of groundwater is of utmost importance. A complete mapping of groundwater is difficult since the monitored sites are far from one another, and thus the data sets are considered extremely “sparse”. To overcome this difficulty in complete mapping of groundwater, compressive sensing is an ideal tool, as it bypasses the classical Nyquist criterion. We show that compressive sensing can effectively be used for reconstructions of groundwater level maps, by validating against data. This approach can have an impact on geographical sensing and information, as effective monitoring and management are enabled without constructing numerous or expensive measurement sites for groundwater.

Multi-sensor data merging of sea ice concentration and thickness

With the rapid change in the Arctic sea ice,a large number of sea ice observations have been collected in recent years,and it is expected that an even larger number of such observations will emerge in the coming years.To make the best use of these observations,in this paper we develop a multi-sensor optimal data merging(MODM)method to merge any number of different sea ice observations.Since such merged data are independent on model forecast,they are valid for model initialization and model validation.Based on the maximum likelihood estimation theory,we prove that any model assimilated with the merged data is equivalent to assimilating the original multi-sensor data.This greatly facilitates sea ice data assimilation,particularly for operational forecast with limited computational resources.We apply the MODM method to merge sea ice concentration(SIC)and sea ice thickness(SIT),respectively,in the Arctic.For SIC merging,the Special Sensor Microwave Imager/Sounder(SSMIS)and Advanced Microwave Scanning Radiometer 2(AMSR2)data are merged together with the Norwegian Ice Service ice chart.This substantially reduces the uncertainties at the ice edge and in the coastal areas.For SIT merging,the daily Soil Moisture and Ocean Salinity(SMOS)data is merged with the weekly-mean merged CryoSat-2 and SMOS(CS2SMOS)data.This generates a new daily CS2SMOS SIT data with better spatial coverage for the whole Arctic.