A hybrid genetic algorithm with local optimiser improves calibration of a vegetation change cellular automata model

Cellular automata (CA) models are commonly used to model vegetation dynamics, with the genetic algorithm (GA) being one method of calibration. This article investigates different GA settings, as well as the combination of a GA with a local optimiser to improve the calibration effort. The case study is a pattern-calibrated CA to model vegetation regrowth in central Victoria, Australia. We tested 16 GA models, varying population size, mutation rate, and level of allowable mutation. We also investigated the effect of applying a local optimiser, the Nelder?Mead Downhill Simplex (NMDS) at GA convergence. We found that using a decreasing mutation rate can reduce computational cost while avoiding premature GA convergence, while increasing population size does not make the GA more efficient. The hybrid GA-NMDS can also reduce computational cost compared to a GA alone, while also improving the calibration metric. We conclude that careful consideration of GA settings, including population size and mutation rate, and in particular the addition of a local optimiser, can positively impact the efficiency and success of the GA algorithm, which can in turn lead to improved simulations using a well-calibrated CA model.     

基于GA-SVM封装算法的高光谱数据特征选择

封装型的特征选择算法相对于过滤算法而言更有助于提高分类精度,因此在当前计算技术及效率快速发展的背景下必将成为未来之趋势。本文以支持向量机(SVM)为分类器,遗传算法(GA)为特征子集的搜索算法,构建了封装型的特征选择算法GA-SVM,并用ENVI/IDL语言编程实现,最后以HYPERION高光谱数据为例对算法予以应用。结果表明,GA-SVM算法可从196个波段中选择出13个波段,同时分类精度较不做特征选择时提高了约4%。由此可见,GA-SVM封装型特征选择算法具有较好的同时优化特征子集和SVM核函数的性能,可为当前高光谱数据的特征选择提供一个较好的算法。     

Optimal spatial land-use allocation for limited development ecological zones based on the geographic information system and a genetic ant colony algorithm

Limited development ecological zones (LDEZs) are often located in poverty-stricken, ecologically vulnerable areas where ethnic minorities reside. Studies on optimal spatial land-use allocation in LDEZs can promote economic and intensive land use, improve soil quality, facilitate local socioeconomic development, and maintain environmental stability. In this study, we optimized spatial land-use allocations in an LDEZ using the geographic information system (GIS) and a genetic ant colony algorithm (GACA). The multi-objective function considers economic benefits and ecological green equivalents, and improves soil erosion. We developed the GACA by integrating a genetic algorithm (GA) with an ant colony algorithm (ACA). This avoids a large number of redundant iterations and the low efficiency of the GA, and the slow convergence speed of the ACA. The study area is located in Pengyang County, Ningxia, China, which is a typical LDEZ. The land-use data were interpreted from remote sensing (RS) images and GIS. We determined the optimal spatial land-use allocations in the LDEZ using the GACA in the GIS environment. We compared the original and optimal spatial schemes in terms of economic benefits, ecological green equivalents, and soil erosion. The results of the GACA were superior to the original allocation, the ACA, and the multi-objective genetic algorithm, in terms of the optimum, time, and robust performance indexes. We also present some suggestions for the reasonable development and protection of LDEZs.