Deep neural network for complex open-water wetland mapping using high-resolution WorldView-3 and airborne LiDAR data

Wetland inventory maps are essential information for the conservation and management of natural wetland areas. The classification framework is crucial for successful mapping of complex wetlands, including the model selection, input variables and training procedures. In this context, deep neural network (DNN) is a powerful technique for remote sensing image classification, but this model application for wetland mapping has not been discussed in the previous literature, especially using commercial WorldView-3 data. This study developed a new framework for wetland mapping using DNN algorithm and WorldView-3 image in the Millrace Flats Wildlife Management Area, Iowa, USA. The study area has several wetlands with a variety of shapes and sizes, and the minimum mapping unit was defined as 20 m² (0.002 ha). A set of potential variables was derived from WorldView-3 and auxiliary LiDAR data, and a feature selection procedure using principal components analysis (PCA) was used to identify the most important variables for wetland classification. Furthermore, traditional machine learning methods (support vector machine, random forest and k-nearest neighbor) were also implemented for the comparison of results. In general, the results show that DNN achieved satisfactory results in the study area (overall accuracy = 93.33 %), and we observed a high spatial overlap between reference and classified wetland polygons (Jaccard index ∼0.8). Our results confirm that PCA-based feature selection was effective in the optimization of DNN performance, and vegetation and textural indices were the most informative variables. In addition, the comparison of results indicated that DNN classification achieved relatively similar accuracies to other methods. The total classification errors vary from 0.104 to 0.111 among the methods, and the overlapped areas between reference and classified polygons range between 87.93 and 93.33 %. Finally, the findings of this study have three main implications. First, the integration of DNN model and WorldView-3 image is useful for wetland mapping at 1.2-m, but DNN results did not outperform other methods in this study area. Second, the feature selection was important for model performance, and the combination of most relevant input parameters contributes to the success of all tested models. Third, the spatial resolution of WorldView-3 is appropriate to preserve the shape and extent of small wetlands, while the application of medium resolution image (30-m) has a negative impact on the accurate delineation of these areas. Since commercial satellite data are becoming more affordable for remote sensing users, this study provides a framework that can be utilized to integrate very high-resolution imagery and deep learning in the classification of complex wetland areas.     

长乐—南澳构造带泉港临头片麻状英云闪长岩中岩浆绿帘石的发现及其地质意义

岩浆绿帘石能够作为压力计反映岩体侵位深度,进而可估算地壳抬升剥蚀速率及地壳演化历史,因而引起了人们的研究关注。在长乐—南澳构造带泉港临头地段发现了片麻状英云闪长岩中的岩浆绿帘石。该地段是我国当前报道岩浆绿帘石的第5处产出地,但在东南沿海地区尚属首次发现。含岩浆绿帘石的片麻状英云闪长岩形成于早白垩世(K₁),以钙性(C,Peacock碱钙指数)、中钾钙碱性系列(MKCA)、准铝质和弱过铝质、钙碱性系列(CA,Miyashiro SiO₂-FeO^*/MgO)为主,具镁安山岩系列(MA)性质,呈奥长花岗岩演化趋势(Tdj);轻稀土(LREE)较富集,铕负异常不明显;微量元素呈现较大的钽(Ta)、磷(P)和钛(Ti)负异常,显示出造山带火山弧花岗岩的特征。片麻状英云闪长岩中绿帘石岩相学特征显示,黑云母和自形的绿帘石分布于斜长石的隙间,为典型的填间结构;绿帘石与黑云母相互接触、相互包裹,是一起从富水的晚期岩浆中结晶出来的原生矿物,不是交代斜长石的岩浆期后的次生矿物。绿帘石电子探针分析结果显示Ps值为24~29,TiO₂含量均小于0.1%。综合绿帘石岩相学与化学特征知悉,泉港临头片麻状英云闪长岩中的绿帘石为岩浆绿帘石。岩浆绿帘石形成压力约870 MPa,深度为25~32 km,而现今东南沿海陆壳厚度约30 km,据此推测,早白垩世(K₁)时东南沿海陆壳厚度为55~62 km;早白垩世(K₁)之后,地壳可能经历了多次抬升。     

内蒙古双尖子山银多金属矿床大规模铜矿化的发现及意义

巴林左旗双尖子山超大型银多金属矿床位于大兴安岭成矿带南段, 是亚洲最大银矿。早期研究认为双尖子山矿床主要为中低温热液成矿, 主要经济金属是银铅锌; 随着研究的深入, 发现了少量中高温铜锡矿化。2021年新施工钻孔首次揭露了大规模铜矿化。矿石主要为块状、角砾状、细脉状及稠密浸染状; 矿物组合主要是黄铜矿、黄铁矿、方铅矿、闪锌矿、毒砂和含银矿物。双尖子山矿床大规模铜矿化的发现, 证实了双尖子山矿床是一个从中高温到低温的完整演化序列的大规模岩浆热液型多金属矿床, 铜也可能成为该矿的新增工业矿种。成矿特征和矿体分布规律显示, 该矿区铜矿体尚未完全探明, 深部存在较大铜找矿潜力。     

湖南新发现的银矿床及找矿方向

湖南新发现的１０处理矿都是硫化物型矿床，可分为银多金属，银铅锌和银锑矿床。其中小七宝山，南风坳矿区已勘探，吊马垅矿区完成了详查，选矿效果都比较好，本文简要介绍了１０个新银矿床特征，指出了我省银矿找矿方向，说明湖南银矿的找矿前景是比较好的。     

我国首次发现的多水钼铀矿

多水钼铀矿属铀酰钼酸盐类矿物。我国首次发现的多水钼铀矿产于北方某火山岩型铀钼矿床的氧化带，为非晶质矿物，在显微镜下呈均质性，电子探针分析既含铀又含钼等是其主要特征。     

THE GEOGRAPHICAL DISCOVERY OF THE NANSHA ISLANDS

TheNanshalslandsarethesouthetnmostterritoriesinChina.TheIslandsconsistof230islands,redandbeaches.Inthehistoricalperiod,theChineseancestorsovercamedifficutiesandfOundtheIslands2,0OOyearsago.Agreatmanyofhistoricalliteraturesindicatethatheeariiestrecords,mpa…     

E-monitoring the nature of water

ABSTRACT

The critical need for hydrological observations in support of water resources management, particularly during extreme events, has transformed traditional methods of hydrological data management. This transformation has given rise to a framework of e-monitoring the hydrological cycle, the aim of which is to improve understanding of the nature of water. New trends in data science, coupled with increasing technological evolution, make the new generation of data systems more agile and responsive to the needs and expectations for efficient and effective data sharing and service delivery. The WMO Hydrological Observing System was designed around the integration of observations, data exchange, research, data processing, modelling and forecasting, in such a way that societal needs for disaster risk reduction, improved sustainability of environmental resources, climate resilience and economic growth can be effectively met. With its implementation of conceptual functionalities for sustainable data management, the WHOS operational architecture is hydrology’s system for the future.     

粗集在知识发现中的应用

介绍了粗集的基本概念,包括粗集的定义、“属性－值”系统、属性依赖与归约及粗集概念的若干推广,最后指出粗集理论在知识发现（KDD）中的一个可能应用途径。