Automated terrain feature identification from remote sensing imagery: a deep learning approach

ABSTRACT

Terrain feature detection is a fundamental task in terrain analysis and landscape scene interpretation. Discovering where a specific feature (i.e. sand dune, crater, etc.) is located and how it evolves over time is essential for understanding landform processes and their impacts on the environment, ecosystem, and human population. Traditional induction-based approaches are challenged by their inefficiency for generalizing diverse and complex terrain features as well as their performance for scalable processing of the massive geospatial data available. This paper presents a new deep learning (DL) approach to support automatic detection of terrain features from remotely sensed images. The novelty of this work lies in: (1) a terrain feature database containing 12,000 remotely sensed images (1,000 original images and 11,000 derived images from data augmentation) that supports data-driven model training and new discovery; (2) a DL-based object detection network empowered by ensemble learning and deep and deeper convolutional neural networks to achieve high-accuracy object detection; and (3) fine-tuning the model’s characteristics and behaviors to identify the best combination of hyperparameters and other network factors. The introduction of DL into geospatial applications is expected to contribute significantly to intelligent terrain analysis, landscape scene interpretation, and the maturation of spatial data science.     

贼鸥用于南极环境大型指示生物种的初步研究

对南极长城站附近棕贼鸥(C.s.lonnberg)、灰贼鸥(C.maccormicki)和两者的混合配对(hybrid)的食性与考察站环境质量的相关性进行研究,结果表明,贼鸥的食物结构受站区人类废弃物的直接影响。贼鸥食性构成同时与人类活动和动物生态习性相关而起到双重信息载体作用,可作为南极环境生态评价的重要指标之一,对推动实现南极环境生态评价的量化有重要意义。     

DEM流径算法的相似性分析

流径算法是分布式水文模型、土壤侵蚀模拟等研究中的关键技术环节,决定着汇水面积、地形指数等许多重要的地形、水文参数的计算。本文以黄土高原两个典型样区的不同分辨率DEM为研究对象,对常用的五种流径算法(D8、Rho8、Dinf、MFD和DEMON)通过相对差系数、累积频率图、XY散点分布图等进行了定量的对比分析。结果表明:算法的差异主要集中在坡面区域,汇流区域各类算法的差别较小;算法差异在不同DEM尺度下都有所体现,但高分辨率下的差异会更明显;在地形复杂区域,多流向算法要优于单流向算法。研究也进一步指出汇水面积、地形指数等水文参数对流径算法具有强烈的依赖性。     

基于遥感技术的土壤侵蚀研究现状及实例分析

通过介绍卫星和传感器在土壤侵蚀研究中的应用情况,讨论了用遥感图像探测土壤侵蚀特征、土壤侵蚀区域和土壤侵蚀沉积的很多应用实例,然后利用甘肃河西走廊黑河上游1987年的TM数据和1999年的ETM数据,计算出了两个时期的植被盖度,同时结合DEM数据得出的坡度值,然后根据水利部的土壤侵蚀分级标准,获得了两个时期的土壤侵蚀图,对比分析了1987年和1999年两个时期的不同等级侵蚀强度区域的面积变化.研究结果显示,甘肃河西走廊黑河上游存在中度侵蚀的区域位于坡度大于15°的地方,这些地方也是我国西部退耕还林还草的重点区域.     

基于ESA遥感影像的伊朗城镇空间时空演变分析

伊朗位于“丝绸之路经济带”与“海上丝绸之路”的交汇点,了解伊朗的发展格局有助于帮助“一带一路”倡议更好地执行和实施。而城市又是一国经济发展的载体,因此,研究伊朗城镇空间的时空变化能够从宏观上了解伊朗,进而为今后两国的合作提供参考依据。此研究基于2000—2015年伊朗影像数据,利用数学统计、核密度、标准差椭圆分析方法,对伊朗城镇空间演变进行时空分析。研究结果表明：1）伊朗城市扩张力度逐年增加,经济发展困境并未对城市扩张速度造成较大影响。2）伊朗西部49.35%的国土分布着81.62%的城镇建成区。全国城镇建成区呈现出形似“蟹钳”的集群-不规则轴线型分布,即“一片区、上钳线、中钳线、下钳线”的空间分布格局。3）伊朗城镇空间分布在整体方向即分布重心上向西北方迁移,但具体形态上东北方影响力度更大。4）伊朗城镇空间分布存在区域不均衡性,但是这种不均衡性在时间序列上逐渐弱化。     

青藏高原荒漠化遥感信息提取及演变分析

在青藏高原258万km2范围内,首次利用Landsat 7 ETM和Landsat3 MSS图像,对整个高原内的砂砾质荒漠化土地、盐碱质荒漠化土地和耕地、草地、林地、沼泽地、地表水体、基岩等土地类型的15种环境因子进行遥感信息提取,结合地面验证,查清了15种环境因子在20世纪70年代和21世纪初两个时期的实际分布面积。对荒漠化土地的遥感图像特征和演变规律进行了综合分析。指出了青藏高原目前在生态地质环境方面存在的突出问题主要是荒漠化程度严重、植被退化严重、水土流失严重、资源开发无序严重和水资源短缺等问题。     

基于多源遥感的聚落与多级人口统计 数据的关系分析

在四川省市州、区县和典型村等三级尺度上,探讨了基于多源遥感的聚落面积与多级人口统计数据的关系。首先,从LANSAT TM影像中提取农村和城镇聚落信息,从Quickbird 影像上提取农村聚落及其房屋地基信息。其次,通过叠加统计得到各级统计单元内的聚落面积;再次,在四川省市州和区县尺度上,分别对城乡聚落面积和总人口数、城镇聚落面积和非农业人口数、农村聚落面积和农业人口数等进行相关性分析, 城镇聚落和非农业人口数的相关系数最高,分别为0.962和0.791,并建立了基于城镇聚落面积的非农业人口数估算模型,其模型的判定系数分别为0.926和0.625;最后,在村级尺度上,对农村聚落及其房屋地基面积与农村人口数之间的相关性进行分析,其相关系数分别为0.806和0.825,分别建立基于农村聚落及其房屋地基面积的农村人口数估算模型,其模型的判定系数分别为0.65和0.68。研究表明,LANDSAT TM适用于大尺度的非农业人口估算,估算效果随尺度的降低而有所降低;Quickbird适合于精细尺度的农业人口估算。     

Using a Bayesian estimator to combine information from a cluster analysis and remote sensing data to estimate high-resolution data for agricultural production in Germany

In Germany, a county-resolution data set that consists of 35 land-use and animal-stock categories has been used extensively to assess the impact of agriculture on the environment. However, because such environmental effects as emission or nutrient surplus depend on the location, even a county resolution might produce misleading results. The aim of this article is to propose a Bayesian approach which combines two sorts of information, with one being treated as defining the prior and the other the data to form a posterior, used to estimate a data set at a municipality resolution. We define the joint prior density function based on (i) remote sensing data, thus accounting for differences in county data and missing data at the municipality level, and (ii) the results of a cluster analysis that was previously applied to the micro-census, whereas the data are defined by official statistics at the county level. This approach results in a fairly accurate data set at the municipality level. The results, using the proposed method, are validated by the national research data centre by comparing the estimates to actual observations. The test statistics presented here demonstrate that the proposed approach adequately estimates the production activities.     

Identification of geomorphic process units in Kärkevagge, northern Sweden, by remote sensing and digital terrain analysis

Sediment transport processes in the Kärkevagge are investigated concerning their spatial and temporal characteristics due to long–term monitoring. Within this study remote sensing techniques and GIS modelling in connection with geomorphic mapping are applied for identification and characterization of geomorphic process units. Relationships between geomorphometric parameters and slope processes like solifluction, talus creep and rockfall have been analysed. Multitemporal Landsat–TM5 scenes are used as source for landcover characteristics (Normalized Difference Vegetation Index) after preprocessing involving orthorectification and topographic normalization in order to remove possible terrain–induced effects. Additionally, a digital elevation model with a resolution of 20 m for the Kärkevagge catchment is developed and parameters like slope gradient, slope aspect and profile curvature are extracted as input for the analysis of the sediment transport system. The combination of landcover information, geomorphometrical and topological features allows the definition of areas for single process activities. They show specific sediment displacement characteristics depending on material conditions, topological and geometrical features. Geomorphic process units, which show a homogenous composition, are extracted from these available layers.     

Elementary forms for land surface segmentation: The theoretical basis of terrain analysis and geomorphological mapping

Land surface morphology is fundamental to geomorphological mapping and many GIS applications. Review and comparison of various approaches to segmentation of the land surface reveals common features, and permits development of a broad theoretical basis for segmentation and for characterization of segments and their boundaries. Within the context of defining landform units that maximise internal homogeneity and external differences, this paper introduces the concept of elementary forms (segments, units) defined by constant values of fundamental morphometric properties and limited by discontinuities of the properties. The basic system of form-defining properties represents altitude and its derivatives, constant values of which provide elementary forms with various types of homogeneity. Every geometric type of elementary form can be characterized by a defining function, which is a specific case of the general polynomial fitted function. Various types of boundary discontinuity and their connections and transformations into other types of morphological unit boundaries are analysed.The wealth of types of elementary forms and their boundaries is potentially unbounded and thus is sufficient to cover the real variety of landforms. Elementary forms in the basic set proposed here have clear potential for genetic and dynamic interpretation. A brief worked example documents the possibility of analytical computation of various models of ideal elementary forms for particular segments of landform. Ideal elementary forms can be considered as attractors, to which the affinity of surface segments can be measured by multivariate statistical methods. The use of the concept of elementary forms in landscape segmentation is promising and it could be adapted for elementary segmentation of various other spatial fields.     

Identification of geomorphic process units in Kärkevagge, northern Sweden, by remote sensing and digital terrain analysis

Sediment transport processes in the Kärkevagge are investigated concerning their spatial and temporal characteristics due to long–term monitoring. Within this study remote sensing techniques and GIS modelling in connection with geomorphic mapping are applied for identification and characterization of geomorphic process units. Relationships between geomorphometric parameters and slope processes like solifluction, talus creep and rockfall have been analysed. Multitemporal Landsat–TM5 scenes are used as source for landcover characteristics (Normalized Difference Vegetation Index) after preprocessing involving orthorectification and topographic normalization in order to remove possible terrain–induced effects. Additionally, a digital elevation model with a resolution of 20 m for the Kärkevagge catchment is developed and parameters like slope gradient, slope aspect and profile curvature are extracted as input for the analysis of the sediment transport system. The combination of landcover information, geomorphometrical and topological features allows the definition of areas for single process activities. They show specific sediment displacement characteristics depending on material conditions, topological and geometrical features. Geomorphic process units, which show a homogenous composition, are extracted from these available layers.     

Integration of nighttime light remote sensing images and taxi GPS tracking data for population surface enhancement

The population distribution grid at fine scales better reflects the distribution of residents and plays an important role in investigating urban systems. The recent years have witnessed a growing trend of applying the nighttime light data to the estimation of population at micro levels. However, using the nighttime light data alone to estimate population may cause the overestimation problem due to excessively high light radiance in specific types of areas such as commercial zones and transportation hubs. In dealing with this issue, this study used taxi trajectory data that delineate people’s movements, and explored the utility of integrating the nighttime light and taxi trajectory data in the estimation of population in Shanghai at the spatial resolution of 500 m. First, the initial population distribution grid was generated based on the NPP-VIIRS nighttime light data. Then, a calibration grid was created with taxi trajectory data, whereby the initial population grid was optimized. The accuracy of the resultant population grid was assessed by comparing it with the refined survey data. The result indicates that the final population distribution grid performed better than the initial population grid, which reflects the effectiveness of the proposed calibration process.     

1972-2019年萨雷兹堰塞湖遥感时序监测与水文特征过程分析

堰塞湖的水文特征过程对于库区洪水宏观调控、预报预警、安全防治等具有重要意义.为了及时掌握萨雷兹堰塞湖水文特征和历史演化过程,本文基于密集时间序列遥感数据,综合调查全面系统地分析了1972-2019年帕米尔高原萨雷兹堰塞湖的水文特征以及时空变化过程;并通过"面积-水位"关系模型重建了1972-2019年萨雷兹堰塞湖的历史...     

基于高分辨率遥感影像的2000-2015年中国省会城市高精度扩张监测与分析

21世纪以来,中国城镇化水平迅速提高,城市扩张监测成为地学应用研究的热点,但同时存在着城市区域概念不统一,城市边界提取精度较粗等问题。选取全国31个省会级城市为监测对象,利用高分辨率遥感影像进行统一标准、高精度的扩张监测及分析。基于高分辨率遥感影像数据进行2000年、2005年、2010年、2015年4期城市区域边界提取,与利用中低分辨率影像提取的成果进行比较,并开展城市规模分布和城市扩张分析。结果表明,与其他研究成果相比,本文拥有更高的精度和可靠性;2000-2015年,中国省会城市保持了高速增长趋势,总面积增加了90.15%;省会城市体系接近捷夫模式的等级规模分布;城市扩展情况地区差异显著,东部扩展速度逐步放缓,西部、东北地区加速扩张,中部地区稳步扩张;2010年确定建设的5个国家中心城市（北京、天津、上海、广州、重庆）在2015年城市区域面积位序中排名前5,15年间扩展了82.45%,单个城市年均扩展30.66 km²,其中北京扩展了三成以上,天津、上海扩展了一倍左右,广州扩展了近六成,重庆扩展了两倍以上。本研究成果为中国城镇体系的发展和规划提供了直观准确的数据,对国家全面认知城市扩张状况,掌握城镇建设方针政策实行效果,进行城市体系科学规划具有十分重要的指导意义。     

地形和遥感图像融合技术在冲沟参数提取中的应用——以栖霞市庵里水库东缘流域为例

受图像的空间分辨率和反立体现象等因素的影响,单纯基于二维遥感图像提取冲沟参数精度较低。以山东省栖霞市庵里水库东岸流域为研究区,建立一种地形和遥感图像融合技术,并用于提取沟沿线、坡底线等冲沟参数,以期为沟蚀参数的大量、快速提取提供一种新方法。结果表明：① 基于HSV变换,高斯标准化地表粗糙度作为地形图像融合的权重,建立了地形与遥感图像融合方法,增强和丰富了图像中的地形信息。② 基于融合数据,结合沟沿线和沟底线坡度阈值处理,在研究区内提取了144条冲沟,总面积为1.699 km²,占流域总面积的29.89%,为强烈侵蚀。③ 选择张家沟—北丁家沟流域作为检验区,以RTK-GPS实测数据为参照,地形融合法提取冲沟的准确率和沟头平均偏移量分别为98.413%和4.12 m,其精度明显高于传统的遥感图像目视解译法（73.016%和9.61 m）。     

山地高密度城市热岛效应的多约束因子格局分析与定量探测——重庆都市区案例研究

城市热岛受城市地表多因素影响,山地城市的情况则更为复杂.本文以典型山地城市重庆为例,基于Landsat8 OLI/TIRS影像、高精度矢量建筑等多源空间数据,采用城市地温反演、归一化植被指数、天空开阔度建模等方法,重点针对城市建成区,通过地理探测器分析各因子对城市热岛效应的约束力.研究表明:①在都市区全域,城市热场空间...