Application of Differential Evolution for Irrigation Planning: An Indian Case Study

The present paper demonstrates the applicability of population based search optimization method, namely, Differential Evolution (DE) to a case study of Mahi Bajaj Sagar Project (MBSP), India. Ten different strategies of DE are employed to assess the ability of DE for solving higher dimensional problems as an alternative methodology for irrigation planning. The parameters considered in DE are population size, crossover constant and weighting factor. Linear Programming (LP) is utilized as a comparative approach to assess the ability of DE. Comparison of results of LP and the 10 DE strategies for the given parameters indicated that both the results are comparable even for high dimensional problems. Extensive sensitivity analysis studies, performed for 3,600 combinations of above parameters for the 10 DE strategies suggested that DE/rand-to-best/1/bin strategy is the best strategy giving maximum benefits taking minimum CPU time. It is concluded that DE can be utilized for efficient planning of any irrigation system with suitable modifications.     

Modelling the rate of secondary succession after farmland abandonment in a Mediterranean mountain area

Secondary succession after farmland abandonment has become a common process in north Mediterranean countries, especially in mountain areas. In this paper, a methodology is tested which combines Markov chains and logistic multivariate regression to model secondary succession after farmland abandonment in environments where abiotic constraints play a major role, like mountain areas. In such landscapes, a decay in the succession rate with time is usually found, as the best locations are progressively occupied. This is frequently addressed using non-stationary Markov chains. Here, we test if the combination of logistic multivariate regression with Markov chains, however, allows for spatially distributed transitions probabilities based on abiotic factors and therefore, it is able to reproduce the preferential colonization of the most favourable locations. The model is tested in the Ijuez Valley in the Spanish Pyrenees, which underwent generalized land abandonment during the 1950s. Results confirm a substantial improvement in the prediction success of the Markov-logistic model when compared to the standard Markov chain approach. As a result, the decay in the succession rate can be successfully modelled. The specific results for our study area are discussed further in an ecological context. The methodology proposed is applicable to any landscape where vegetation dynamics are constrained by environmental factors. However, the inclusion of land use as an explanatory factor would be necessary in human-managed landscapes.     

A mathematical model for predicting the soil nitrogen status under varying fertilizer practices in a continuous cropping sequence

A mathematical model has been proposed for predicting the changes in soil nitrogen status due to continuous fertilization in a continuous cropping sequence. The model also enabled the prediction of the steady state of soil nitrogen for a specified fertilizer practice.The model was applied to six years nitrogen availability data of four fertilizer practices in finger millet-maize-cowpea sequence followed in the Long Term Fertilizer Experiments conducted at Tamil Nadu Agricultural University, Coimbatore, India. The agreement between the predicted soil nitrogen status by the model and the actuals was proved by employing reliability index.     

The role ofAzolla in curbing ammonia volatilization from flooded rice systems

By the year 2020, an additional 300 million tons of rice are needed annually to meet the demands of a growing population. If our natural resource base is to be preserved, intensification strategies should rely on integrated nutrient management, making full use of biological nitrogen fixation. TheAzolla-Anabaena complex is amongst the most effective systems of fixing nitrogen. In this paper we present evidence from greenhouse studies on the potential ofAzolla to curb the volatilization of NH₃ following the application of urea to a mixedAzolla-rice culture, providing a new incentive for developing ways of integratingAzolla in intensive rice cultivation systems.The results of a series of short term greenhouse experiments show that a full cover ofAzolla can significantly reduce losses of applied urea-N from 45 and 50% to 20 and 13% for the 30 and 60 kg N ha^–1 treatments, respectively. About one-quarter of the applied N was tied up in theAzolla biomass. The applied N inhibitedAzolla growth as well as the amount of N fixed. Inoculation with smaller quantities ofAzolla allowing for more vigorousAzolla multiplication was equally effective in reducing NH₃ volatilization and doubled the amount of¹⁵N tied-up byAzolla. The reduction in NH₃ volatilization is largely related to the depression byAzolla of the floodwater pH, which in its absence may reach values between 9 and 10 as a result of algal activity.Early rice growth responded positively to urea as well as the large quantities of appliedAzolla and increased the yield potential of the crop. Smaller quantities ofAzolla alone were not effective in this regard. The conservation of fertilizer N byAzolla, particularly when it fully covered the water, was reflected in a synergistic effect on rice dry matter production, amounting to 9% at the 30 kg N rate and 16% at the 60 kg N rate. In all likelihood this interaction is attributable to the higher efficiency of the applied N. The benefits ofAzolla in conserving basal urea-N even in small quantities (200-500 kg fresh material ha^–1), outweighed competition for the applied N and may be as important as its BNF. The most promising integratedAzolla/rice management systems emerging from our studies should be given further attention under field conditions.     

Misleading the Colorado potato beetle with an odor blend

Walking tracks of Colorado potato beetles,Leptinotarsa decemlineata Say, were recorded on a locomotion-compensator in response to wind, odors of host plantsSolanum tuberosum L. and nonhost plantsLycopersicon hirsutum f.glabratum C.H. Mull, and to mixtures of these plant species. Host-plant odor induced positive anemotactic responses in starved females, whereas odor of the nonhostL. hirsutum was neither repellent nor attractive. The attractiveness of host-plant odor, however, was neutralized in the odor blend of plant species. Masking the attractive host-plant odor will hinder the beetle's searching for host-plant patches, and this principle may be exploited in pest control by mixed cropping.The locomotion-compensator was constructed with financial support from the Foundation for Fundamental Biological Research (BION), which is subsidized by the Netherlands Organization for the Advancement of Pure Research (ZWO), grant 14-02-02. The first author was supported by a grant from the French Ministry of Industry and Research.     

Hedgerow species and environmental conditions effects on soil total C and N and C and N mineralization patterns of soils amended with their prunings

An important criterium in selecting species for alley cropping is themineralization pattern of their prunings. This study determined effects of 5years of hedgerow pruning applications on soil organic C and total N at threelocations in Haiti and mineralization patterns from soil amended with theprunings during an incubation using micro-lysimeters. Soils (0–5cm) under 5 hedgerows were collected at each site and analyzed fororganic C and total N. In the laboratory, ground leaves and stems (<1cm diameter) of the hedgerow species were mixed with soil at ratesof 3 and 1.5 Mg ha^–1, respectively, andaerobically incubated in the dark at 25 °C. A non-amended soilwas used as control. Soils were leached to determine mineral N at 1, 3, 7, 14,28, 42, 84 and 120 days of incubation. Evolved CO₂ was measuredfollowing each leaching procedure. At the calcareous site, application ofprunings from Leucaena leucocephala (Lam.) De Wit andDelonix regia (Boj. ex Hook. Raf.) resulted in 23 and 13%higher soil N than the control, respectively, after 5 years. There were nodifferences in total N at the other sites but soil N was highest underLeucaena hybrid and Acaciaangustissima (Mill.) Kuntze, respectively at the basaltic and highelevation sites. Soils under D. regia (calcareous) andA. angustissima and Leucaena hybrid(high elevation) had higher organic C than the respective controls. Carbon andNmineralization and C turnover were highest when soils were amended with leavesof Leucaena diversifolia (Schlecht.) Benth (calcareous andbasaltic soils) and A. angustissima (high elevation) andlowest in non-amended control soils. Stem-amended soils showed differences in Cmineralization for calcareous and high elevation soils whereas N mineralizationwas similar among treatments within sites. Carbon and N mineralization (highelevation soil) correlated positively with N concentrations of leaf prunings.Amendments with leaf prunings increased soil C and N mineralization andturnoverrates, suggesting greater nutrient availability for the crop during a shortperiod than in non-amended control soils.     

复种指数遥感监测研究进展

复种指数是对耕地资源利用状况的一种度量,其对于指导农业生产及研究气候变化等具有重要意义。利用遥感技术进行复种指数监测,不仅客观、高效、低成本,而且可以获取更佳的空间分布信息,近些年已成为农业遥感领域的研究热点。对复种指数遥感监测进展进行了综述:首先归纳和梳理了已有的几种复种指数遥感监测方法,并分析了各种方法的优缺点;然后在总结该领域研究现存关键问题的基础上,探讨了未来的发展趋势:(1)在内容上丰富,加强特殊的作物熟制信息监测;(2)在空间上拓展,加强地形复杂区域的复种指数监测;(3)在时间上延伸,加强复种指数长期的动态变化监测。     

针对栅格地图的快速鲁棒盲水印算法

为解决大数据量栅格地图的版权保护问题,提出一种快速、鲁棒的水印算法。该算法基于分块思想将水印嵌入到傅立叶频域的半圆形区域。在提取水印时,先进行预处理校正,再利用邻域均值法将大幅面图像的频谱图映射成为标准大小的频谱图,既做到了盲提取,又解决了分块嵌入与全图提取带来的问题。实验表明该算法占用内存小、运行效率高,对裁剪、旋转、对比度和亮度变化等攻击具有较好的鲁棒性。     

基于人脸关键特征提取的表情识别

自然场景下人脸表情由于受遮挡、光照等因素影响,以及表情局部变化细微,导致现有人脸表情识别方法准确率较低。提出一种人脸表情识别的新方法,以ResNet18为主干网络,利用残差连接模块加深网络结构,以提取更多深层次的表情特征。通过引入裁剪掩码模块,在训练集图像上的某个区域进行掩码,向训练模型中增加遮挡等非线性因素,提升模型在遮挡情形下的鲁棒性。分别从特征图的通道和空间两个维度提取表情的关键特征,并分配更多的权重给表情变化明显的特征图,同时抑制非表情特征。在特征图输出前加入Dropout正则化策略,通过在训练中随机失活部分神经元,达到集成多个网络模型的训练效果,提升模型泛化能力。实验结果表明,与L2-SVMs、IcRL、DLP-CNN等方法相比,该方法有效提高了表情识别准确率,在2个公开表情数据集Fer2013和RAF-DB上的识别准确率分别为74.366%和86.115%。     

Ruminations of an Editor-in-Chief

The Journal of Strategic Information Systems (JSIS) was first published December 1991 by Robert (Bob) D. Galliers, its Founding Editor-in-Chief (EiC). Early on Bob invited me to join the JSIS International Editorial Board¹ (the Board then being more operational, with members serving as quasi-AEs, an arrangement we’ve reinstituted more recently). I became Pacific Asia Region Editor in 2003, with JSIS shifting from region editors to Senior Editors in 2007, in which role I served the journal through the end of 2018. Mid-2018 Bob and Sirkka (Sirkka Jarvenpaa joined as co-EiC in 2000) jointly decided it was time; and announced they would both step down from their co-EiC roles at the end of that year. In September 2018, I was endorsed by Bob and Sirkka, the Senior Editors and Elsevier, to succeed Bob and Sirkka and assume the role of Editor-in-Chief of JSIS commencing 1 January 2019. I served as Editor-in-Chief through 1 July 2021 after which Yolande Chan and I served as co-Editors-in-Chief. Now the end of 2022, I am stepping down from operational involvement with the journal. In this my final editorial I focus on my time as EiC, also reflecting on my almost 3 decades with the journal. I much appreciate being invited to write these brief ruminations and am honoured to be included amongst the journal’s Emeritus, along with the esteemed Robert Galliers and Sirkka Jarvenpaa.