基于遥感和机器学习的内陆水体水深反演技术

文章主要根据机器学习算法（随机森林算法和极端梯度提升算法）和遥感水深反演的原理,利用Sentinel_2多光谱卫星数据和无人船实测水深数据,对内陆水体——梅州水库建立了随机森林（RF）、极端梯度提升（XGBoost）和支持向量机（SVM）水深反演模型,并对反演结果进行对比分析。结果表明：1）RF的训练精度为97%,测试精度为0.80;XGBoost模型的训练精度为97%,测试精度为0.79;SVM的训练精度为90%,测试精度为0.78。说明了在水深预测方面RF模型和XGBoost模型比SVM模型表现更好,对各个区段的水深值较为敏感。2）根据运行时间考察各个模型的效率,其中RF模型从读取数据至输出结果耗时3.92 s;XGBoost模型4.26 s;SVM模型6.66 s。因此,在反演精度和效率上RF模型优于XGBoost模型优于SVM模型,且RF模型的预测结果图细节更加丰富,轮廓更加分明;XGBoost模型次之,但总体效果也较好;SVM模型表现最差。由此可知,机器学习水深反演模型获得的水深结果精度明显提高,解决了传统水深反演模型精度不高的问题。     

Modeling the Influence of Groundwater Exploitation on Land Subsidence Susceptibility Using Machine Learning Algorithms

Natural Resources Research - Groundwater over-exploitation in arid and semiarid environments has led to many land subsidence cases. Immense economic losses incurred from land subsidence occurrences...     

Prediction of Blast-Induced Ground Vibration Intensity in Open-Pit Mines Using Unmanned Aerial Vehicle and a Novel Intelligence System

Natural Resources Research - Predicting and reducing blast-induced ground vibrations is a common concern among engineers and mining enterprises. Dealing with these vibrations is a challenging issue...     

Computational Intelligence Model for Estimating Intensity of Blast-Induced Ground Vibration in a Mine Based on Imperialist Competitive and Extreme Gradient Boosting Algorithms

Natural Resources Research - In this paper, we developed a novel hybrid model ICA–XGBoost for estimating blast-produced ground vibration in a mine based on extreme gradient boosting (XGBoost)...     

Prediction of Blast-Induced Ground Vibration in Open-Pit Mines Using a New Technique Based on Imperialist Competitive Algorithm and M5Rules

Natural Resources Research - In this paper, blast-induced ground vibration (BIGV) was considered as the primary objective, and a new artificial intelligence system was proposed to predict BIGV with...     

The Digital Versatile Disc as a Learning Support Medium in the Teaching and Learning of Map Work

Abstract

This article describes the results of a study where the digital versatile disc (DVD) was used as a variant of Information and Communication Technology (ICT) in order to aid in the teaching and learning of map work in geography at secondary school level. A group of grade 10 learners of a previously disadvantaged school in South Africa comprised the target group for the project. A case study was conducted and data was gathered on the implementation of the DVD and the learners' perceptions thereof. Qualitative analysis techniques such as field notes, observation, interviews with the learners, and questionnaires were used to analyze the effectiveness of the implementation of the DVD as well as the learners' perceptions regarding the use of the DVD in geography education. The results of the study indicated that the geography learners demonstrated positive attitudes towards the implementation of the DVD as a learning support medium. To determine the contribution of the DVD project towards the achieved results of the learners in map work, both the experimental and control groups participated in a pre- and post-test at the beginning and conclusion of the project. Effect size was used to determine the significance of the differences between the two groups and indicates a strong practical significance regarding the contribution of the DVD project towards the achieved test results of the learners.     

基于改进遗传算法投影寻踪的大城市郊区耕地安全综合评价

针对耕地安全高维评价体系指标权重难以赋值、客观性差的问题,构建了实码加速的遗传算法投影寻踪（RAGA-PP）模型,对快速城市化的大城市郊区耕地安全进行综合评价。以广州城市发展的南拓与北优两个郊区——番禺区与从化市为例,建立4个子系统共32个指标的耕地安全评价指标体系,对大城市郊区耕地的数量结构安全、质量安全、经济社会安全和生态安全进行综合评价。结果表明:（1）RAGA-PP模型在多目标、多因素的耕地安全综合评价中取得了满意的效果;（2）广州市郊区耕地安全评价的影响因子权重在远郊区和近郊区存在较大差别,开展不同区域对比研究更适合采用总投影方向确定的权重值。（3）由于近郊区与远郊区发展定位与发展战略迥异,城市化进程速度不同,区域耕地安全等级差别较大,近郊的番禺区耕地综合安全水平低于远郊的从化市,其中番禺区仅耕地经济社会安全水平高于从化市,而耕地的质量安全、数量安全和生态安全方面均低于从化市。     

Remote Sensing Inversion of Saline and Alkaline Land Based on an Improved Seagull Optimization Algorithm and the Two-Hidden-Layer Extreme Learning Machine

Natural Resources Research - Through remote sensing inversion, the evolution and treatment of saline and alkaline land can be monitored on a large scale in real time. The spectral data and salt...     

基于信息量模型和机器学习方法的滑坡易发性评价研究——以四川理县为例

以阿坝藏族羌族自治州地质灾害频发的理县为研究区,从地形地貌、地质环境、水文条件和人类工程活动等方面选取11个影响因子,通过皮尔森相关系数研究各因子之间的相关性,从而构建滑坡易发性评价指标体系。利用信息量模型计算各影响因子的信息量值,从信息量模型得出的极低和低易发性分区中选取非滑坡样本,在此基础上将样本数据代入随机森林和径向基函数神经网络2种机器学习模型开展滑坡易发性评价,并通过接收灵敏度（Receiver Operating Characteristic,ROC）曲线进行精度验证。结果显示：随机森林模型预测出的高易发区单位面积内分布的滑坡点数量更为集中,在仅占6.666%的区域分布了74.026%的灾害点,评价结果优于径向基函数神经网络模型。ROC曲线中两模型AUC（Area Under Curve）值分别为0.893、0.874,说明随机森林模型具有更高的可靠性,比径向基函数神经网络在该区域地质灾害易发性评价中更具优势。     

Disaster-Triggering Mechanisms Based on Interaction of Various Factors in Structured Gas Migration in Coal Seams Under Loading and Unloading Conditions

Natural Resources Research - On the premise that the point of the maximum abutment pressure is the demarcation point of gas migration, an experimental research was conducted on gas-bearing coal by...     

Reservoir Characterization Using Multi-component Seismic Data in a Novel Hybrid Model Based on Clustering and Deep Neural Network

Natural Resources Research - Effective use of the difference between longitudinal and converted shear waves in reservoir sensitivity analysis is a key component to reduce the multi-solution problem...     

基于无人机影像的北部湾典型岛群红树林生态系统净初级生产力估算

提出以无人机季节航拍影像为数据源,采用ENVI5.3软件中的CART方法对广西北部湾的典型岛群红树林景观类型进行解译,借助于Python语言实现CASA模型并将其引入到对岛群红树林生态系统的研究中,得出了不同海岛和红树林生态系统净初级生产力（NPP）的空间分布特征。结果表明：1）可见光波段差异性植被指数（VDVI）可以很好地区分海岛及红树林植被等典型地物,可应用在岛群红树林生态系统NPP的估算上;2）研究区NPP的总量为127.09 t·C/a,NPP的年均碳密度值介于0~1 437.12 g·C/m²,年均碳密度为399.85 g·C/m²。红树林生态系统的NPP值较高,而海岛生态系统的NPP值较低;3）季节尺度上NPP碳密度的大小与年内太阳辐射有直接的关系,夏季的NPP碳密度最大,冬季最小;4）白骨壤的单位面积NPP最大,为1 123.09 g·C/m²,而桐花树最小,为649.65 g·C/m²。红树林生态系统NPP平均碳密度低于实测样地和深圳福田红树林计算结果,这与不同红树林群落的植被光谱特征有关。     

WebGIS在线数据平台探究式地理教学案例设计与思考--以气象灾害台风为例

《普通高中地理课程标准(2017年版)》中强调"要充分利用地理信息技术,营造直观、实时、生动的地理教学环境",将WebGIS技术引入中学地理课程教学,有着便捷、快速、轻巧等传统GIS不可比拟的优势,有利于提升学生的地理核心素养。本文选取两个不同功能的WebGIS在线数据平台,以气象灾害台风为例,设计探究式地理教学案例,并对所选取的案例进行深入数据分析,以期为高中地理教师提供教学资源和平台参考,提升教学技能。     

中国公众对全球气候变化认知与支持减缓气候变化政策研究——基于全球调查数据和与美国比较视角

公众对气候变化的认知影响个人和家庭限制温室气体排放、支持减缓气候变化的政策措施等。基于5次全球调查数据和与美国的对比,分析了中国公众对气候变化的认知、减缓气候变化支付意愿和对气候政策的支持。分析表明中国大部分公众听说过气候变化,认为人类活动是气候变化的重要原因,但对气候变化深层原因了解不够;大部分公众认为气候变化对自然灾害的发生、降水和水资源、食物种类等带来了很大不利影响,进而担忧气候变化,认为气候变化问题很严重;大部分公众认为限制温室气体排放是国际社会共同的责任,应该立即采取行动限制温室气体排放,包括改变生活方式、接受较高的能源价格、保护森林、取消政府对私家车的补贴、提高机动车的能效等。最后讨论了进一步需要研究的问题。     

新郑农村经济发展与土地使用制度的关系

考察了新郑农村经济变革的历程后，发现农村经济的发展变化与土地使用制度有密切关系。研究认为这种关系的内在机制是土地收益的分配方式；当前土地使用中存在的主要问题是土地浪费和利用粗放；原因仍是土地制度中存在着弊端。文章最后提出了完善土地使用制度的对策是搞活土地使用权，试行农用土地租赁制。     

Estimating the spatial and temporal impacts of climate change on rainfall reliability: An example in a Mediterranean agricultural region

Rainfall is the major driver of crop growth in Mediterranean agricultural regions and its spatial and temporal distributions determine yield potential. This study uses a long term spatial archive of rainfall observations for the Eyre Peninsula (South Australia) to estimate the spatial and temporal impacts of climate change on wheat yield. The three step process involved: (1) cluster analysis and statistical comparison to spatially distinguish heterogeneous “hazardscapes” (places that represent the physical susceptibility to hazards (Khan, 2012)); (2) using historical rainfall reliabilities to estimate the probability of receiving rainfall within a range of predefined thresholds and season for each hazardscape; (3) applying 2030 and 2070 climate change projections to determine the potential future impacts on rainfall. Nine hazardscapes were spatially differentiated each having temporally different historical seasonal rainfall reliabilities. Variations over space and time mean that the impacts of climate change will be spatially explicit. Projected rainfall reductions for 2030 showed marginal impact on hazardscapes with low seasonal reliabilities, primarily in winter and spring. The 2070 projections showed that some hazardscapes were unlikely to receive past rates of rainfall thus limiting the ongoing prospects of current and perhaps the potential adoption of alternative rain-fed land uses. Reductions in rainfall for hazardscapes with higher historical rainfall reliabilities will cause negative impacts on crop development. The ability to quantify the potential spatial and temporal impacts of climate change on seasonal trends will inform land managers' climate change mitigation and adaptation pathways.     

行动者网络视域下世界遗产地的空间生产——以广东开平碉楼与村落为例

行动者网络理论（Actor-Network Theory,ANT）通过把人与非人的、物质的和社会的要素并置在行动者网络内,为地理学家审视“空间”提供了一个强大的理论工具,在人文地理学各分支学科的应用日益增多。文章以开平碉楼与村落世界遗产地为研究对象,使用ANT研究了开平碉楼与村落从偏僻乡野向世界遗产地的空间生产过程。研究发现,开平碉楼与村落的行动者主要包括联合国教科文组织世界遗产委员会、国家各级政府、开平碉楼与村落专项基金会、旅游企业、旅游者、碉楼华侨业主、碉楼当地业主、其他非业主居民和开平碉楼与村落环境。开平碉楼与村落所处区域的经济衰落呈现出的行动者集体的问题是行动者转译原因,也是开平碉楼空间再生产的起点;申遗与旅游开发成为行动者利益赋予、征召与动员的过程,也同时阐述了空间再生产过程的机理,由部分业主对网络提出的异议则指涉了新的空间再生产。     

基于MapX和Oracle Spatial建立矿区土地复垦信息系统探讨

煤炭资源的开采破坏了大量的土地,加剧了人地矛盾,土地复垦是矿区可持续发展的重要内容之一.矿区土地复垦是一个边缘交叉学科,所需处理的数据涉及采矿、地质、地理、土壤、农林、生物、社会经济等众多领域,具有数据信息量大、相互关系复杂等特点.传统的数据处理方法已难以适应土地复垦发展的要求.主要研究了矿区土地复垦信息系统的主要功能,并分析了基于MapX和Oracle Spatial进行系统开发的关键技术.     

基于WebGIS的南海历史地理情势分析系统设计与实现

结合当前南海严峻形势以及GIS系统开发的特点,研究设计了基于Arc GIS Engine组件、采用SQL Server数据库与Arc SDE空间数据引擎、以Visual Studio 2010为开发平台、C#为开发语言的南海历史地理情势分析系统;该系统包括了历史情势分析、岛礁分析、油气分析和系统管理4个模块,可用于统筹分析南海历史情势、岛礁情势和油气情势的发展状况及趋势。