Soil enzymes play a vital role in biogeochemical cycling and ecosystem functions.In this study,we examined the response of six soil enzymes to changes in physicochemical properties resulting from changes in season and...Soil enzymes play a vital role in biogeochemical cycling and ecosystem functions.In this study,we examined the response of six soil enzymes to changes in physicochemical properties resulting from changes in season and vegetation and geological conditions.Catalase,urease,acid phosphatase,invertase,amylase,and cellulase not only promote carbon,nitrogen,and phosphorus cycling,but also participate in the decomposition of harmful substances.Thirty-six soil samples were collected from karst and non-karst areas in two different seasons and from three different types of vegetation in Yunnan province,southwest China.Both vegetation types and season had significant effects on soil physicochemical properties and enzyme activities.In the same plot,soil water content,electrical conductivity,organic carbon,total nitrogen,and total phosphorus increased in the rainy season,indicating enhanced microbial metabolic activity.With the exception of urease activity,the remaining five enzymes showed higher activity in the rainy season.Changes in activities between the two seasons were significant in all samples.In the same season,activity levels of soil enzymes were higher in karst areas than in non-karst areas,and higher in natural forest than in artificial forests.The transformative abilities of soil elements are higher in karst areas than in non-karst areas,and higher in natural forests than in artificial forests.Correlation analysis showed that the activities of the six enzymes correlated significantly;however,soil physical and chemical indices,such as organic matter,pH,and moisture,which are essential for enzyme activity,differed by season.Redundancy analysis also revealed that the main factors influencing enzyme activity differed between the two seasons.The results from this study provide a theoretical basis for further research on the restoration of natural ecological systems in karst landscapes.展开更多
A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. However, what emerges as missing in many applications is actionability, i.e., the ability t...A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. However, what emerges as missing in many applications is actionability, i.e., the ability to turn prediction results into actions. Existing effort in deriving such actionable knowledge is few and limited to simple action models while in many real applications those models are often more complex and harder to extract an optimal solution. In this paper, we propose a novel approach that achieves actionability by combining learning with planning, two core areas of AI. In particular, we propose a framework to extract actionable knowledge from random forest, one of the most widely used and best off-the-shelf classifiers. We formulate the actionability problem to a sub-optimal action planning （SOAP） problem, which is to find a plan to alter certain features of a given input so that the random forest would yield a desirable output, while minimizing the total costs of actions. Technically, the SOAP problem is formulated in the SAS＋ planning formalism, and solved using a Max-SAT based ap- proach. Our experimental results demonstrate the effectiveness and efficiency of the proposed approach on a personal credit dataset and other benchmarks. Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.展开更多
基金This work was supported by the National Key Research and Development Program of China(2016YFC0502500,2016YFC0502504)the National Natural Science Foundation of China(315005831008509)the Special fund for basic scientific research expenses of central public welfare scientific research institutes(CAFYBB2014ZD006,CAFYBB2016QB020).
文摘Soil enzymes play a vital role in biogeochemical cycling and ecosystem functions.In this study,we examined the response of six soil enzymes to changes in physicochemical properties resulting from changes in season and vegetation and geological conditions.Catalase,urease,acid phosphatase,invertase,amylase,and cellulase not only promote carbon,nitrogen,and phosphorus cycling,but also participate in the decomposition of harmful substances.Thirty-six soil samples were collected from karst and non-karst areas in two different seasons and from three different types of vegetation in Yunnan province,southwest China.Both vegetation types and season had significant effects on soil physicochemical properties and enzyme activities.In the same plot,soil water content,electrical conductivity,organic carbon,total nitrogen,and total phosphorus increased in the rainy season,indicating enhanced microbial metabolic activity.With the exception of urease activity,the remaining five enzymes showed higher activity in the rainy season.Changes in activities between the two seasons were significant in all samples.In the same season,activity levels of soil enzymes were higher in karst areas than in non-karst areas,and higher in natural forest than in artificial forests.The transformative abilities of soil elements are higher in karst areas than in non-karst areas,and higher in natural forests than in artificial forests.Correlation analysis showed that the activities of the six enzymes correlated significantly;however,soil physical and chemical indices,such as organic matter,pH,and moisture,which are essential for enzyme activity,differed by season.Redundancy analysis also revealed that the main factors influencing enzyme activity differed between the two seasons.The results from this study provide a theoretical basis for further research on the restoration of natural ecological systems in karst landscapes.
基金This work was supported in part by the National Natural Science Foundation of China （Grant Nos. 61502412, 61379066, and 61402395）, Natural Science Foundation of the Jiangsu Province （BK20150459, BK20151314, and BK20140492）, Natural Science Foundation of the Jiangsu Higher Education Institutions （15KJB520036）, United States NSF grants （IIS-0534699, IIS-0713109, CNS-1017701）, Microsoft Research New Faculty Fellowship, and the Research Innovation Program for Graduate Student in Jiangsu Province （KYLX16 1390）.
文摘A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. However, what emerges as missing in many applications is actionability, i.e., the ability to turn prediction results into actions. Existing effort in deriving such actionable knowledge is few and limited to simple action models while in many real applications those models are often more complex and harder to extract an optimal solution. In this paper, we propose a novel approach that achieves actionability by combining learning with planning, two core areas of AI. In particular, we propose a framework to extract actionable knowledge from random forest, one of the most widely used and best off-the-shelf classifiers. We formulate the actionability problem to a sub-optimal action planning （SOAP） problem, which is to find a plan to alter certain features of a given input so that the random forest would yield a desirable output, while minimizing the total costs of actions. Technically, the SOAP problem is formulated in the SAS＋ planning formalism, and solved using a Max-SAT based ap- proach. Our experimental results demonstrate the effectiveness and efficiency of the proposed approach on a personal credit dataset and other benchmarks. Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.
