Predicting land cover using GIS, Bayesian and evolutionary algorithm methods

Modelling land cover change from existing land cover maps is a vital requirement for anyone wishing to understand how the landscape may change in the future. In order to test any land cover change model, existing data must be used. However, often it is not known which data should be applied to the problem, or whether relationships exist within and between complex datasets. Here we have developed and tested a model that applied evolutionary processes to Bayesian networks. The model was developed and tested on a dataset containing land cover information and environmental data, in order to show that decisions about which datasets should be used could be made automatically. Bayesian networks are amenable to evolutionary methods as they can be easily described using a binary string to which crossover and mutation operations can be applied. The method, developed to allow comparison with standard Bayesian network development software, was proved capable of carrying out a rapid and effective search of the space of possible networks in order to find an optimal or near-optimal solution for the selection of datasets that have causal links with one another. Comparison of land cover mapping in the North-East of Scotland was made with a commercial Bayesian software package, with the evolutionary method being shown to provide greater flexibility in its ability to adapt to incorporate/utilise available evidence/knowledge and develop effective and accurate network structures, at the cost of requiring additional computer programming skills. The dataset used to develop the models included GIS-based data taken from the Land Cover for Scotland 1988 (LCS88), Land Capability for Forestry (LCF), Land Capability for Agriculture (LCA), the soil map of Scotland and additional climatic variables.     

基于LCS的应急决策文本相似性比对分析模型

作为应急管理中的主要工作内容,应急决策在整个应急管理工作中具有战略意义,为了对危机情境下的应急决策主体进行聚类分析,定量计算不同决策主体之间相应决策文本的区别。借鉴最长公共子序列模型（LCS）的原理,从决策文本中提取主题词,根据决策文本的特点将其分为“目标”和“行动”2级,结合样本总体确定替换矩阵、空位罚分规则和目标函数,构建高层应急决策文本相似性比对分析模型;运用Needleman Wunsch算法对该模型进行求解;通过对得到的地震情景下的高层应急决策文本的分析,证明模型的有效性和可行性;为了避免序列长度差过大对聚类分析的结果影响,在此基础上提出相对相似性得分的概念,并通过与VSM算法得到的结果进行比较,证明该模型在应急决策文本相似性分析中的优越性。     

Modeling soil and plant phosphorus within DSSAT

The crop models in the Decision Support System for Agrotechnology Transfer (DSSAT) have served worldwide as a research tool for improving predictions of relationships between soil and plant nitrogen (N) and crop yield. However, without a phosphorus (P) simulation option, the applicability of the DSSAT crop models in P-deficient environments is limited. In this study, a soil-plant P model integrated to DSSAT was described, and results showing the ability of the model to mimic wide differences in maize responses to P in Ghana are presented as preliminary attempts to testing the model on highly weathered soils. The model simulates P transformations between soil inorganic labile, active and stable pools and soil organic microbial and stable pools. Plant growth is limited by P between two concentration thresholds that are species-specific optimum and minimum concentrations of P defined at different stages of plant growth. Phosphorus stress factors are computed to reduce photosynthesis, dry matter accumulation and dry matter partitioning. Testing on two highly weathered soils from Ghana over a wide range of N and P fertilizer application rates indicated that the P model achieved good predictability skill at one site (Kpeve) with a final grain yield root mean squared error (RMSE) of 535 kg ha⁻¹and a final biomass RMSE of 507 kg ha⁻¹. At the other site (Wa), the RMSE was 474 kg ha⁻¹ for final grain yield and 1675 kg ha⁻¹ for final biomass. A local sensitivity analysis indicated that under P-limiting conditions and no P fertilizer application, crop biomass, grain yield, and P uptake could be increased by over 0.10% due to organic P mineralization resulting from a 1% increase in organic carbon. It was also shown that the modeling philosophy that makes P in a root-free zone unavailable to plants resulted in a better agreement of simulated crop biomass and grain yield with field measurements. Because the complex soil P chemistry makes the availability of P to plants extremely variable, testing under a wider range of agro-ecological conditions is needed to complement the initial evaluation presented here, and extend the use of the DSSAT-P model to other P-deficient environments.