Seasonal and spatial distribution of heavy metals in the Selenga River Delta

In order to estimate the present-day pollution levels in the ecosystem of the Selenga River Delta and to monitor the changes caused by the discharge of household refuse and industrial wastes,as well as the functioning of the agricultural and stock farming,a comprehensive study of the water and bottom sediments in the main branches of the Selenga River Delta was carried out.This study has determined the concentrations of heavy metals in river water and bottom sediments in its delta.

Comparative Analysis of Different Forest Ecosystems Response to Global Climate Change and Economic Activity

This article examines the impact of climate change on different ecosystems （boreal, tropical） APR on the territory of Russia, Mongolia, China, received in the course of research in key areas of investigated territory; provides a comparative analysis of the reaction of these ecosystems to global climate change. It is concluded, that there is some reaction of the forest ecosystem to climate change. This reaction is differently. It is noted the importance of socio-economic problems which have significant impact on ecosystems, along with climate change. Carried out researches allow to conclude, that it is necessary to investigate additionally how imposed climate-driven and direct human impacts to changes in forest and forest steppe ecosystems.

基于深度神经网络的蒙古国色楞格河流域水体信息提取

蒙古高原地处干旱半干旱地区,河流水系对该区域的资源环境格局及其生态环境影响重大。发源于蒙古国的色楞格河是蒙古高原最主要的水资源来源,准确掌握该流域的水体信息对东北亚地区生态环境问题及资源保护具有重要意义。本文以蒙古高原色楞格河流域为研究对象,基于谷歌地球引擎(Google Earth Engine,GEE)云平台,使用Sentinel-2多光谱卫星遥感影像,利用深度神经网络(Deep Neural Network,DNN)方法对色楞格河流域的水体信息进行提取,并与支持向量机方法进行对比;利用全球30 m SRTM数据生成水系分布矢量图,通过空间分析形成河流提取目标区,结合深度神经网络分类结果,绘制蒙古国色楞格河流域2019年河流分布图。研究结果表明:①该方法能够准确地完成大流域范围内的水体制图,提取结果能够体现色楞格河流域河流的空间分布,且能够减少河流断流、空洞现象;②深度神经网络模型中批量大小设置为8时,在处理数据速度与精度中达到最优,而神经网络结构中隐含层数达到4层时,在精度评价指标测试数据集上达到0.9666,保证了模型特征挖掘能力;③经样本点的验证,结果总体精度达到97.65%,可以满足实际应用需求。本研究预期可以为蒙古高原的水体提取提供方法支持和相关数据支持。