Optimised use of data fusion and memory-based learning with an Austrian soil library for predictions with infrared data

Infrared spectroscopy in the visible to near-infrared (vis–NIR) and mid-infrared (MIR) regions is a well-established approach for the prediction of soil properties. Different data fusion and training approaches exist, and the optimal procedures are yet undefined and may depend on the heterogeneity present in the set and on the considered scale. The objectives were to test the usefulness of partial least squares regressions (PLSRs) for soil organic carbon (SOC), total carbon (C_t), total nitrogen (N_t) and pH using vis–NIR and MIR spectroscopy for an independent validation after standard calibration (use of a general PLSR model) or using memory-based learning (MBL) with and without spiking for a national spectral database. Data fusion approaches were simple concatenation of spectra, outer product analysis (OPA) and model averaging. In total, 481 soils from an Austrian forest soil archive were measured in the vis–NIR and MIR regions, and regressions were calculated. Fivefold calibration-validation approaches were carried out with a region-related split of spectra to implement independent validations with n ranging from 47 to 99 soils in different folds. MIR predictions were generally superior over vis–NIR predictions. For all properties, optimal predictions were obtained with data fusion, with OPA and spectra concatenation outperforming model averaging. The greatest robustness of performance was found for OPA and MBL with spiking with R² ≥ 0.77 (N), 0.85 (SOC), 0.86 (pH) and 0.88 (C_t) in the validations of all folds. Overall, the results indicate that the combination of OPA for vis–NIR and MIR spectra with MBL and spiking has a high potential to accurately estimate properties when using large-scale soil spectral libraries as reference data. However, the reduction of cost-effectiveness using two spectrometers needs to be weighed against the potential increase in accuracy compared to a single MIR spectroscopy approach.     

Improvement of boron soil test

Abstract

Boron soil tests often do not adequately reflect B plant uptake or deficiency levels in the Eastern United States. In an attempt to develop a better test, the following systems were studied: Silicic acid replacement of boron; B soil buffering power; and the addition of small quantities of boron (0.175 ugB/g‐soil) to each soil sample to overcome some of the stronger boron fixing sites prior to hot water extraction.

Boron extracted with B spiked hot water (r=0.80 for plant tissue B vs. extractable B, opposed to r=0.76 for nonspiked hot water) was the only new test that showed promise.

The results appear to explain why hot water extractable B correlates well with plant uptake for soils previously treated with boron fertilizer (e.g. alfalfa fields); but why, on the other hand, hot water extractable B fails to correlate well with plant boron uptake for soils not having a recent history of boron fertilization. . . in which some fixing sites apparently have to be satisfied before the hot water test will work well.     

光肩星天牛危害导致箭杆杨枯梢的数量指标初探

１９９６ 年８ 月底在宁夏对光肩星天牛危害导致枯梢的箭杆杨的解剖结果表明,解剖前调查的各种以危害状反映的天牛表征数量与解剖后的天牛实际数量并不一致．因有空刻槽,解剖前当年新刻槽数大于解剖后卵及初孵幼虫的数量,空槽率为４２－７ ％ ;解剖前当年新排粪孔数因有的天牛幼虫向树体外排粪的表征不甚明显而偏少;当年新羽化孔数解剖前后差别不大．导致箭杆杨枯梢的主要原因是树干上天牛坑道过多且集中,其坑道截面积占树干截面积的１０ ％ 左右,影响了树体向上的水分传导．在水肥条件良好且无其它病虫害的情况下,天牛传入后３ ａ 即可使箭杆杨枯梢．导致８ 年生箭杆杨枯梢时的光肩星天牛危害的主要数量指标为：株平均当年新羽化孔数１０ 个．     

Fault diagnosis of rotating machinery based on self-learning fuzzy spiking neural network

For fuzziness classific boundry of fault diagnosis of rotating machinery and traditional neural network algorithms difficulted to solve contradiction between application problems example scale and netwok scale,a methord of self-learning fuzzy spiking neural network is put forward. The methord overcomes unavailability of cluster analysis on classific boundry of fault diagnosis of rotating machinery by species encoding of pulse sequence and unsupervised learning. The method shows that it effectively solves boundary fuzziness problem on fault diagnosis of rotating machinery,and greatly improves efficiency of fault diagnosis.     

Spike/Leach Procedure to Prepare Soil Samples for Trace Metal Ecotoxicity Testing: Method Development Using Copper

Soil trace metal ecotoxicity testing requires a set of soil samples with increasing metal concentrations that are otherwise chemically similar. Leaching samples amended with soluble metal salts has been proposed as a means to reduce chemical artefacts of the spiking procedure (i.e., salt effect), thereby improving their environmental relevance. Demonstrating with copper (Cu), we proposed a spike/leach procedure whereby metal solutions were added to test soils over 5 days and subsequently leached with dilute nutrient solutions until the electrical conductivity in leachates stabilized. During the 5 days of Cu additions, pH in leachates from Cu-spiked samples decreased by up to 0.90 pH units and showed up to 30- and 25-fold increases in calcium (Ca) and magnesium (Mg) concentrations, indicative of the salt effect. Leaching removed the excess acidity and dissolved cations and minimized the differences in leachate pH, Ca, Mg, aluminum (Al), iron (Fe), manganese (Mn), and dissolved organic carbon (DOC) concentrations between control and Cu-spiked samples. Leaching also reduced dissolved Cu concentrations in spiked samples by up to an order of magnitude, resulting in more environmentally relevant concentrations than were achieved prior to leaching.     

肉鸡低血糖-尖峰死亡综合征调查研究

本研究对发生在华北地区的新型高致死性肉鸡疾病进行调查研究。发病主要集中在 8～ 18日龄 ,11～ 16日龄出现死亡尖峰。病鸡的血糖 (89.8± 7.9mg/dl)极显著低于正常鸡 (2 2 0 .3± 18.7mg/dl) (P<0 .0 1)。日死亡率高达 4 %～ 8%。典型症状表现为发病突然、头部震颤、运动失调、瘫痪、昏迷死亡。剖检可见肝脏弥漫性坏死 ,胰腺萎缩 ,十二指肠出血 ,胸腺、法氏囊、脾脏和盲肠扁桃体等免疫器官萎缩。泄殖腔聚集大量白色米汤样稀便。显微观察可见肝细胞坏死、淋巴滤泡排空、淋巴细胞坏死。依据国际诊断肉鸡低血糖 -尖峰死亡综合征 (HSMS)的标准 ,在国内首次确定我国有 HSMS发生 ,且在华北地区分布广泛 ,死亡率远高于国外报道的大于 0 .5 % ,而是高达 4 %～ 8%。已经成为危害肉仔鸡的重要疾病。采用控制光照和饮水中添加葡萄糖及多维等措施对 HSMS具有一定缓解作用     

玉米激振摘穗机理分析与参数试验优化

针对玉米立式激振摘穗缺乏相应摘穗机理的深入研究,开展了玉米摘穗机理的探讨,确定了适合玉米高效低损摘穗的激振波频特性曲线,建立了激振摘穗模型,分析了夹持位置、激振频率和振幅对玉米摘穗效果的影响规律;采用激振试验台开展了夹持位置、振幅、频率对其摘穗性能影响规律的单因素试验,确定了满足玉米果穗摘穗的参数取值范围;通过响应面分析试验,确定了适合玉米高效摘穗的最佳参数组合,即在籽粒含水率30.58%情况下,其夹持位置距离果穗重心10.8cm、激振波振幅0.6cm、激振波频率17.8Hz时,玉米摘穗断茎率为2%,摘穗成功率为98%,满足玉米收获的作业技术要求。