In this paper,the geoecological information-modeling system(GIMS)is described as possible improvement of the Big Data approach.The main GIMS function is the use of algorithms and models that capture the fundamental pr...In this paper,the geoecological information-modeling system(GIMS)is described as possible improvement of the Big Data approach.The main GIMS function is the use of algorithms and models that capture the fundamental processes controlling the evolution of the climate-nature-society(CNSS)system.The GIMS structure includes 24 blocks that realize a series of models and algorithms for global big data processing and analysis.The CNSS global model is the basic block of the GIMS.The operational tools of GIMS are demonstrated by examining several scenarios associated with the reconstruction of forest areas.It is shown that significant impacts on forests can lead to global climate variations on a large scale.展开更多
Since the State Council issued the Action Plan on Promoting the Development of the Big Data Industry,big data-enabled information integration and processing applications have increasingly become the basic strategic re...Since the State Council issued the Action Plan on Promoting the Development of the Big Data Industry,big data-enabled information integration and processing applications have increasingly become the basic strategic resources for the building of a modern governance system in China.When it comes to poverty reduction,given that we are currently at a critical stage in the battle to eradicate poverty,it's important that we apply the big data way of thinking and big data technology to the development and integration of poverty alleviation resources.This paper examines the need to apply big data technology in targeted poverty alleviation and discusses how big data technology can be integrated into targeted poverty alleviation programs and how the big data way of thinking meshes with the idea of targeted poverty alleviation.It is believed that the application of big data technology can significantly improve the results of targeted poverty alleviation programs and that the building of big data-powered poverty alleviation platforms is a new approach to implementing the targeted poverty alleviation strategy.This paper calls for changing our way of thinking regarding targeted poverty alleviation and points out the directions for targeted poverty alleviation in the age of big data,with a view to promoting the extensive application of big data technology in the field of poverty reduction and improving the results of poverty alleviation and eradication programs.展开更多
Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Re...Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.展开更多
从18世纪首次获得人工杂交种到如今基因工程育种,作物育种技术发展迅速,同时几百年的育种历程积攒了大量育种数据,特别是近年来伴随高通量测序技术的发展,产生了海量作物育种相关基因及其表达数据,形成了育种大数据。2012年以来在商业...从18世纪首次获得人工杂交种到如今基因工程育种,作物育种技术发展迅速,同时几百年的育种历程积攒了大量育种数据,特别是近年来伴随高通量测序技术的发展,产生了海量作物育种相关基因及其表达数据,形成了育种大数据。2012年以来在商业、信息技术等领域发展迅猛的大数据技术,致力于解决大数据采集、存储及处理等壁垒,并在其他领域的应用初露端倪。本文利用创新方法 TRIZ(theory of inventive problem solving)流分析技术,综合分析了育种领域已有资源和目标达成的矛盾问题,提出大数据育种技术应用于作物育种的创新方案,明确了将大数据技术应用于育种领域的框架和实现目标。提出了基于大数据理念的育种技术,拟采集和整合已有育种数据资源,实现数据自动采集等,从而能够平衡育种数据膨胀/利用和育种需求产生的矛盾;构建基于大数据技术的育种数据信息化平台,实现作物育种方法理念的创新,可以为广大育种工作者提供数据支撑和一个育种新途径;为解析生物学数据与目标农艺性状的关系提供信息,加快育种现代化的进程。展开更多
基金This study was partly supported by the Russian Fund for Basic Researches[Project No.16-01-000213-a].
文摘In this paper,the geoecological information-modeling system(GIMS)is described as possible improvement of the Big Data approach.The main GIMS function is the use of algorithms and models that capture the fundamental processes controlling the evolution of the climate-nature-society(CNSS)system.The GIMS structure includes 24 blocks that realize a series of models and algorithms for global big data processing and analysis.The CNSS global model is the basic block of the GIMS.The operational tools of GIMS are demonstrated by examining several scenarios associated with the reconstruction of forest areas.It is shown that significant impacts on forests can lead to global climate variations on a large scale.
基金part of the"Study on Improving the Results of Targeted Poverty Alleviation Programs in Guangxi,Guizhou and Yunnan"(15BMZ057)a 2015 general research program funded by the National Social Sciences Fund of China+3 种基金"Exploring the Implementation of the Targeted Poverty Alleviation Strategy and Study on Improving the Implementation Methods in Guangxi"(XBS16035)a program funded by the Guangxi University Research Fund"Study on Dynamic Management Model for Targeted Poverty Alleviation in the Age of Big Data"(201610593296)a program funded by Guagnxi’s College Student Innovation and Entrepreneurship Training Project
文摘Since the State Council issued the Action Plan on Promoting the Development of the Big Data Industry,big data-enabled information integration and processing applications have increasingly become the basic strategic resources for the building of a modern governance system in China.When it comes to poverty reduction,given that we are currently at a critical stage in the battle to eradicate poverty,it's important that we apply the big data way of thinking and big data technology to the development and integration of poverty alleviation resources.This paper examines the need to apply big data technology in targeted poverty alleviation and discusses how big data technology can be integrated into targeted poverty alleviation programs and how the big data way of thinking meshes with the idea of targeted poverty alleviation.It is believed that the application of big data technology can significantly improve the results of targeted poverty alleviation programs and that the building of big data-powered poverty alleviation platforms is a new approach to implementing the targeted poverty alleviation strategy.This paper calls for changing our way of thinking regarding targeted poverty alleviation and points out the directions for targeted poverty alleviation in the age of big data,with a view to promoting the extensive application of big data technology in the field of poverty reduction and improving the results of poverty alleviation and eradication programs.
文摘Challenges in Big Data analysis arise due to the way the data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address Big Data challenges to drive decision making. The challenge of this study is lack of interoperability since the data, a collection of GIS shapefiles, remotely sensed imagery, and aggregated and interpolated spatio-temporal information, are stored in monolithic hardware components. For the modelling process, it was necessary to create one common input file. By merging the data sources together, a structured but noisy input file, showing inconsistencies and redundancies, was created. Here, it is shown that BRT can process different data granularities, heterogeneous data and missingness. In particular, BRT has the advantage of dealing with missing data by default by allowing a split on whether or not a value is missing as well as what the value is. Most importantly, the BRT offers a wide range of possibilities regarding the interpretation of results and variable selection is automatically performed by considering how frequently a variable is used to define a split in the tree. A comparison with two similar regression models (Random Forests and Least Absolute Shrinkage and Selection Operator, LASSO) shows that BRT outperforms these in this instance. BRT can also be a starting point for sophisticated hierarchical modelling in real world scenarios. For example, a single or ensemble approach of BRT could be tested with existing models in order to improve results for a wide range of data-driven decisions and applications.
文摘从18世纪首次获得人工杂交种到如今基因工程育种,作物育种技术发展迅速,同时几百年的育种历程积攒了大量育种数据,特别是近年来伴随高通量测序技术的发展,产生了海量作物育种相关基因及其表达数据,形成了育种大数据。2012年以来在商业、信息技术等领域发展迅猛的大数据技术,致力于解决大数据采集、存储及处理等壁垒,并在其他领域的应用初露端倪。本文利用创新方法 TRIZ(theory of inventive problem solving)流分析技术,综合分析了育种领域已有资源和目标达成的矛盾问题,提出大数据育种技术应用于作物育种的创新方案,明确了将大数据技术应用于育种领域的框架和实现目标。提出了基于大数据理念的育种技术,拟采集和整合已有育种数据资源,实现数据自动采集等,从而能够平衡育种数据膨胀/利用和育种需求产生的矛盾;构建基于大数据技术的育种数据信息化平台,实现作物育种方法理念的创新,可以为广大育种工作者提供数据支撑和一个育种新途径;为解析生物学数据与目标农艺性状的关系提供信息,加快育种现代化的进程。
