Search

Reliable information about the geographic distribution and abundance of major plant functional types (PFTs) around the world is increasingly needed for global change research. Using remote sensing techniques to map PFTs is a relatively recent field of research. This paper presents a method to map PFTs from the Moderate Resolution Imaging Spectroradiometer (MODIS) data using a multisource evidential reasoning (ER) algorithm. The method first utilizes a suite of improved and standard MODIS products to generate evidence measures for each PFT class. The multiple lines of evidence computed from input data are then combined using Dempster''s Rule of combination. Finally, a decision rule based on maximum support is used to make classification decisions. The proposed method was tested over the states of Illinois, Indiana, Iowa, and North Dakota, USA where crops dominate. The Cropland Data Layer (CDL) data provided by the United States Department of Agriculture were employed to validate our new PFT maps and the current MODIS PFT product. Our preliminary results suggest that multisource data fusion is a promising approach to improve the mapping of PFTs. For several major PFT classes such as crop, trees, and grass and shrub, the PFT maps generated with the ER method provide greater spatial details compared to the MODIS PFT. The overall accuracies increased for all the four states, with the biggest improvement occurring in Iowa from 51% (MODIS) to 64% (ER). The overall kappa statistic also increased for all the four states, with the biggest improvement occurring in Iowa from 0.03 (MODIS) to 0.38 (ER). The paper concludes with a discussion of several methodological issues pertaining to the further improvement of the ER approach. [Copyright &y& Elsevier]

Relational databases are the most popular repository for structured data, and is thus one of the richest sources of knowledge in the world. In a relational database, multiple relations are linked together via entity-relationship links. Multirelational classification is the procedure of building a classifier based on information stored in multiple relations and making predictions with it. Existing approaches of Inductive Logic Programming (recently, also known as Relational Mining) have proven effective with high accuracy in multirelational classification. Unfortunately, most of them suffer from scalability problems with regard to the number of relations in databases. In this paper, we propose a new approach, called CrossMine, which includes a set of novel and powerful methods for multirelational classification, including 1) tuple ID propagation, an efficient and flexible method for virtually joining relations, which enables convenient search among different relations, 2) new definitions for predicates and decision-tree nodes, which involve aggregated information to provide essential statistics for classification, and 3) a selective sampling method for improving scalability with regard to the number of tuples. Based on these techniques, we propose two scalable and accurate methods for multirelational classification: CrossMine-Rule, a rule-based method and CrossMine-Tree, a decision-tree-based method. Our comprehensive experiments on both real and synthetic data sets demonstrate the high scalability and accuracy of the CrossMine approach. [ABSTRACT FROM AUTHOR]