Teaching Spatial Thinking and Geospatial Technologies Through Citizen Mapping and Problem-Based Inquiry in Grades 7-12

Our project introduced students in grades 7 through 12 to spatial thinking and geospatial technologies in the context of challenges in their community. We used a mix of levels of inquiry to advance learning from teacher- to student-guided through a citizen mapping group activity. Student-suggested problem-based topics included parks and community gardens, crime, housing, and youth employment opportunities. Qualitative methods were used to evaluate students’ knowledge of spatial thinking and geospatial technologies, including map interpretation, a case study, daily exit slips, and interviews. Overall, the students’ awareness of their community, spatial thinking, and geospatial technologies increased as a result of participation.     

Process and Contextual Factors Supporting Action-Oriented Learning: A Thematic Synthesis of Empirical Literature in Natural Resource Management

Despite a long-term focus on learning in natural resource management (NRM), it is still debated how learning supports sustainable real-world NRM practices. We offer a qualitative in-depth synthesis of selected scientific empirical literature (N?=?53), which explores factors affecting action-oriented learning. We inductively identify eight key process-based and contextual factors discussed in this literature. Three patterns emerge from our results. First, the literature discusses both facilitated participation and self-organized collaboration as dialogical spaces, which bridge interests and support constructive conflict management. Second, the literature suggests practice-based dialogs as those best able to facilitate action and puts a strong emphasis on experimentation. Finally, not emphasized in existing reviews and syntheses, we found multiple evidence about certain contextual factors affecting learning, including social-ecological crises, complexity, and power structures. Our review also points at important knowledge gaps, which can be used to advance the current research agenda about learning and NRM.     

县域经济发展时空差异和影响因素的地理探测——以甘肃省为例

县域作为中国经济发展的基本空间单元和产业承接载体,对其经济发展的空间差异及其影响因素的研究对理解区域经济格局及其演变具有重要意义。运用ArcGIS空间分析功能,以NICH指数和人均实际GDP为县域经济发展测度指标,以甘肃省为研究对象,对县域经济发展的空间集聚状态和时空演变进行动态分析,并对经济发展的影响因素进行地理探测。结果表明：2001—2015年,甘肃省县域经济发展活力与发展水平空间格局基本吻合;就经济发展活力而言,其县域与城区发展不平衡,且经济发展活力整体上呈现下降态势,县域经济逆势提升具有很大挑战;经济发展活力冷热点区保持相对稳定,重心向西北倾斜的“哑铃状”空间格局不断强化,热点区呈现明显的“点-轴”发展格局;甘肃省县域经济空间差异主导因子包括工业化水平、经济基础、市场规模,各影响因素之间具有明显的交互作用,增强了单一因子的贡献量;县域经济发展的主导影响因素存在明显的地域差异性,对不同分区主导因子驱动机制的分析,可以为科学制定四大分区县域经济发展定位及地区协调统筹发展提供参考。     

基于强化学习的锚泊辅助动力定位系统智能决策研究

针对半潜平台锚泊辅助动力定位系统的最优定位点问题,设计了基于强化学习中深度神经网络的Q学习(DQN)控制策略的锚泊辅助动力定位的智能决策系统。该决策系统中DQN方法与比例—积分—微分(PID)控制方法相结合使用,实现系统优化。在基于机器人操作系统(ROS)平台的动力定位时域模拟程序中进行数值仿真,仿真结果验证了该系统在定位点决策问题上的可靠性和有效性,从而使半潜平台在面对未知海况时,均能寻找到最优定位点,在保证锚泊辅助动力定位系统可靠性的同时降低功率消耗,提高经济性。     

基于长短时记忆神经网络的台风路径临近预报模型

It is of vital importance to reduce injuries and economic losses by accurate forecasts of typhoon tracks. A huge amount of typhoon observations have been accumulated by the meteorological department, however, they are yet to be adequately utilized. It is an effective method to employ machine learning to perform forecasts. A long short term memory(LSTM) neural network is trained based on the typhoon observations during 1949–2011 in China's Mainland, combined with big data and data mining technologies, and a forecast model based on machine learning for the prediction of typhoon tracks is developed. The results show that the employed algorithm produces desirable 6–24 h nowcasting of typhoon tracks with an improved precision.     

基于随机森林算法的大尹格庄金矿床三维成矿预测

大数据及机器学习技术在解决各行各业的复杂非线性关系问题方面已经体现出巨大的优势。本文尝试将随机森林(RF)算法引入三维成矿预测领域来开展研究,以胶东大尹格庄金矿为研究对象,在构建招平断裂(地质体)三维模型的基础上,通过各种空间分析方法提取控制矿体形成的若干控矿地质因素特征值,进而获取成矿空间中控矿地质因素分布值,最后将矿区钻孔立体单元化形成采样数据集并利用RF算法对矿区开展三维矿体定位预测,结果表明:决策树棵数M=800、属性个数K=7是最优参数,能获得总体精度97.32%和kappa系数0.6292的综合分类精度;RF算法的分类精度要优于支持向量机(SVM)算法和多层感知器(MP)算法。RF算法对大尹格庄金矿开展的三维矿体定位预测取得了较好效果,并在矿区深边部预测了7个三维找矿靶区,证明大数据技术在矿产资源定位预测方面具有巨大的应用前景。     

深度学习在煤层气测井解释中的应用研究

将常规储层测井解释方法应用于煤层气储层测井解释,其效果存在一定的折扣。为了改善传统方法在煤层气测井解释中出现的问题,将深度学习的思想引入测井解释,提出受限玻尔兹曼机的数量、受限玻尔兹曼机隐含层神经元数量、分类阈值的确定方法,利用深度信念网络进行煤层识别及煤层气含气量的预测。实验结果表明：首先,在交会图法效果不好的情况下,通过深度信念网络进行煤层识别,继而对识别结果进行适当校正,煤层识别成功率可达到90%以上;其次,经过多种方法的对比,利用深度信念网络进行煤层气含气量预测的效果,要好于BP神经网络、多元回归统计以及Langmuir方程三种方法。深度学习改进了传统的BP神经网络,具备更强的复杂函数泛化能力,适用于煤层气测井解释,并具有进一步的推广价值。     

Volcano video data characterized and classified using computer vision and machine learning algorithms

Video cameras are common at volcano observatories,but their utility is often limited during periods of crisis due to the large data volume from continuous acquisition and time requirements for manual analysis.For cameras to serve as effective monitoring tools,video frames must be synthesized into relevant time series signals and further analyzed to classify and characterize observable activity.In this study,we use computer vision and machine learning algorithms to identify periods of volcanic activity and quantify plume rise velocities from video observations.Data were collected at Villarrica Volcano,Chile from two visible band cameras located～17 km from the vent that recorded at 0.1 and 30 frames per second between February and April 2015.Over these two months,Villarrica exhibited a diverse range of eruptive activity,including a paroxysmal eruption on 3 March.Prior to and after the eruption,activity included nighttime incandescence,dark and light emissions,inactivity,and periods of cloud cover.We quantify the color and spatial extent of plume emissions using a blob detection algorithm,whose outputs are fed into a trained artificial neural network that categorizes the observable activity into five classes.Activity shifts from primarily nighttime incandescence to ash emissions following the 3 March paroxysm,which likely relates to the reemergence of the buried lava lake.Time periods exhibiting plume emissions are further analyzed using a row and column projection algorithm that identifies plume onsets and calculates apparent plume horizontal and vertical rise velocities.Plume onsets are episodic,occurring with an average period of～50 s and suggests a puffing style of degassing,which is commonly observed at Villarrica.However,the lack of clear acoustic transients in the accompanying infrasound record suggests puffing may be controlled by atmospheric effects rather than a degassing regime at the vent.Methods presented here offer a generalized toolset for volcano monitors to classify and track emission statistics at a variety of volcanoes to better monitor periods of unrest and ultimately forecast major eruptions.     

基于Siamese卷积神经网络的影像瓦片变化检测技术

针对地理信息变化较快而传统更新方式效率不高的问题,目前许多学者提出了各类变化检测的方法,但这些方法大都是基于影像数据进行试验,对影像预处理要求较高,且检测精度的稳定性较差,受数据源质量影响较大。而天地图、百度地图、谷歌地图等地图中均可免费下载各种级别的影像瓦片,因此本文提出利用天地图影像瓦片进行试验,采用Siamese卷积神经网络（SCNN）和深度学习技术,开发基于SCNN的高精度变化监测算法,以快速发现变化区域,实现地理信息变化信息检测。