基于贝叶斯优化机器学习超参数的滑坡易发性评价

利用机器学习模型进行滑坡易发性评价时,不同的超参数设置往往会导致评价结果的不同.采用贝叶斯算法对4种常见机器学习模型(逻辑回归LR、支持向量机SVM、人工神经网络ANN和随机森林RF)的超参数进行了优化,探索了该算法对滑坡易发性机器学习模型的优化效果.以湘中地区4县(安化县、新华县、桃江县和桃源县)滑坡易发性评价为例说...     

Residents&rsquo|perspectives and responses to environmental degradation in the upper Dadu River, eastern Tibetan Plateau?

1. Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China; 2. College of Resources and Environment, Southwest University, Chongqing 400716, China; 3. Institute of Tibetan Plateau Research, CAS, Beijing 100085, China)     

裂缝性致密砂岩气藏水相毛管自吸调控

钻井、完井、增产改造工作液滤液、边底水或凝析水在井筒或裂缝面附近发生毛管自吸行为和滞留效应诱发水相圈闭损害,妨碍气藏的及时发现、准确评价和经济开发.以我国四川、鄂尔多斯盆地典型致密砂岩气藏为例,基于致密气藏天然气产出机理,分析了致密气藏经济开发的水平井钻井完井、水力压裂、采气等作业环节中水相自吸过程及其对作业效果的影响.钻井完井过程中水相快速自吸进入基块,驱替出非润湿相油气,打破裂缝壁面力学—化学平衡,诱发井壁失稳;进入裂缝的工作液要快速返排,以免自吸侵入基块降低基块—裂缝传质效率;裂缝中水相高速流动,不易毛管自吸进入基块,造成边底水沿裂缝快速推进,造成水淹.矿场工程技术实践证明,裂缝致密气藏勘探开发全过程,选用合理水基工作流体体系,改善采气工艺措施,调控毛管自吸,进而达到防治水相圈闭损害的目的,是经济开发致密气藏的关键.     

Research on Forest Phenology Prediction based on LSTM and GRU Model

Research on forest phenology is an important parameter related to climate and environmental changes. An optical camera was used as a near-earth remote sensing satellite device to obtain forest images, and the data of Green excess index (GEI) in the images were calculated, which was fitted with the seasonal variation curve of GEI data by double Logistic method and normalization method. LSTM and GRU deep learning models were introduced to train and test the GEI data. Moreover, the rationality and performance evaluation of the deep learning model were verified, and finally the model predicted the trend of GEI data in the next 60 days. Results showed: In the aspects of forest phenology training and prediction, GRU and LSTM models were verified by histograms and autocorrelation graphs, indicating that the distribution of predicted data was consistent with the trend of real data, LSTM and GRU model data were feasible and the model was stable. The differences of MSE, RMSE, MAE and MAPE between LSTM model and GRU model were 0.0014, 0.013, 0.008 and 5.26%, respectively. GRU had higher performance than LSTM. The prediction of LSTM and GRU models about GEI data for the next 60 days both showed a trend chart consistent with the change trend of GEI data in the first half of the year. GRU and LSTM were used to predict GEI data by deep learning model, and the response of LSTM and GRU deep learning models in forest phenology prediction was realized, and the performance of GRU was better than that of LSTM model. It could further reveal the growth and climate change of forest phenology in the future, and provide a theoretical basis for the application of forest phenology prediction.     

Evolutionary process and development implications of traditional trade routes in the Himalayan region

Journal of Geographical Sciences - Traditional trade routes that penetrate the natural barrier of the Himalayas are critical for connecting major Chinese and South Asian markets. Research on these...     

基于县域尺度的青藏高原牧区积雪雪灾风险分析(英文)

Snow disaster is one of the top ten natural disasters worldwide, and the most severe natural disaster to affect the pastoral areas of the Qinghai-Tibet Plateau. Based on the hazard harmfulness data collected from historical records and data collected from entities affected by this hazard in 2010, a comprehensive analysis of the 18 indexes of snow disaster on the Qinghai-Tibet Plateau was conducted, encompassing the hazard harmfulness, the amount of physical exposure the hazard-bearing entities face, the sensitivity to the hazard, and the capacity to respond to the disaster. The analysis indicates that:(1) areas at high-risk of snow disaster on the Qinghai-Tibet Plateau are located in certain areas of the counties of Yecheng and Pishan in the Xinjiang region;(2) areas at medium-risk of snow disaster are found between the Gangdise Mountains and the Himalayas in the central-western part of the Qinghai-Tibet Plateau, and the southeastern part of the southern Qinghai Plateau;(3) the risk of snow disaster is generally low throughout the large area to the south of 30°N and the region on the border of the eastern Qinghai-Tibet Plateau. Overall, the risk of snow disaster in high-altitude areas of the central Qinghai-Tibet Plateau is higher than that at the edge of the plateau.     

青藏高原气候系统变化及其对东亚区域的影响与机制研究进展

青藏高原地区特殊的大气圈、水圈、冰冻圈、生物圈等多圈层相互作用过程及其变化,不仅对青藏高原及其周边地区的气候格局和变化有重要影响,而且对东亚、北半球乃至全球的环流形势和异常产生深远影响。为此,全球变化研究重大科学研究计划于2010年9月启动了"青藏高原气候系统变化及其对东亚区域的影响与机制研究"项目,旨在开展青藏高原环境、地表过程、生态系统对全球变化的响应及其对周边地区人类生存环境影响的综合交叉研究,以揭示青藏高原气候系统变化及其对东亚区域的影响机制,提出前瞻性的应对气候变化与异常的策略,减少其导致的区域自然灾害的损失。项目实施近3年来,开展了青藏高原首次"星—机—地"综合立体协同观测试验和大规模地气相互作用综合观测试验。在遥感结合地面观测估算青藏高原地表特征参数和能量通量方法,高原地区上对流层和下平流层结构,高原季风与东亚季风和南亚季风之间的内在联系,中国及青藏高原地区太阳辐射和风速的年代际变化趋势,青藏高原春季感热源减弱及其对亚洲夏季风和中国东部降水的影响,以及极高海拔地区土地覆被格局等方面取得了一些突出进展。