Deep neural network algorithm for estimating maize biomass based on simulated Sentinel 2A vegetation indices and leaf area index

Accurate estimation of biomass is necessary for evaluating crop growth and predicting crop yield.Biomass is also a key trait in increasing grain yield by crop breeding.The aims of this study were(i)to identify the best vegetation indices for estimating maize biomass,(ii)to investigate the relationship between biomass and leaf area index(LAI)at several growth stages,and(iii)to evaluate a biomass model using measured vegetation indices or simulated vegetation indices of Sentinel 2A and LAI using a deep neural network(DNN)algorithm.The results showed that biomass was associated with all vegetation indices.The three-band water index(TBWI)was the best vegetation index for estimating biomass and the corresponding R2,RMSE,and RRMSE were 0.76,2.84 t ha−1,and 38.22%respectively.LAI was highly correlated with biomass(R2=0.89,RMSE=2.27 t ha−1,and RRMSE=30.55%).Estimated biomass based on 15 hyperspectral vegetation indices was in a high agreement with measured biomass using the DNN algorithm(R2=0.83,RMSE=1.96 t ha−1,and RRMSE=26.43%).Biomass estimation accuracy was further increased when LAI was combined with the 15 vegetation indices(R2=0.91,RMSE=1.49 t ha−1,and RRMSE=20.05%).Relationships between the hyperspectral vegetation indices and biomass differed from relationships between simulated Sentinel 2A vegetation indices and biomass.Biomass estimation from the hyperspectral vegetation indices was more accurate than that from the simulated Sentinel 2A vegetation indices(R2=0.87,RMSE=1.84 t ha−1,and RRMSE=24.76%).The DNN algorithm was effective in improving the estimation accuracy of biomass.It provides a guideline for estimating biomass of maize using remote sensing technology and the DNN algorithm in this region.     

System for quasi‐continuous simultaneous measurement of oxygen diffusion rate and redox potential in soil

Oxygen diffusion rate (ODR) and redox potential (E_H) are quantitative indices representing oxygen availability and redox status in soils, which is valuable information for better understanding causes and effects of soil aeration. Because these indices are spatially and temporally highly variable, continuous measurements and adequate numbers of repetitions are essential for accurate in situ monitoring. Here, we present a new, fully automated recording system for in situ measurements where ODR and E_H are measured at the same platinum electrode. The conflict between electrode polarization for ODR and the resulting biased E_H readings is solved by reducing the polarization time and introducing a recovery interval between two consecutive measurement cycles. The shorter polarization time ensures accurate E_H readings. It also results in moderately overestimated ODR readings, but this can be corrected before data analysis. The recovery interval restricts temporal resolution of the E_H‐ODR data pairs to 8 h. We illustrate the use of the system with measurements in a field experiment in Zürich, Switzerland. ODR curves at different depths ran roughly parallel to the corresponding curves of O₂ concentration in soil air but ODR was much more sensitive to precipitation. Low ODR was a necessary but not a sufficient condition for declining E_H. E_H ran parallel to O₂ concentration in soil air rather than to ODR. The fully automated system allows for time series of replicate measurements in multifactorial field studies with reasonable labor requirements. It may be particularly suitable for studies examining the effects of soil tillage, compaction, and irrigation, where structure‐related soil properties such as porosity, gas permeability, and soil aeration play a dominant role.     

围垦对滨海稻田土壤N2O还原潜力的影响

稻田湿地生态系统的N₂O还原消耗潜力对缓解大气温室气体效应具有重要意义，而滨海自然湿地围垦改造成稻田后耕层土壤的N₂O还原速率及其微生物机制却鲜有报道。选取崇明岛光滩湿地为对照（WK0），比较研究不同围垦年限（19、27、51、86 a）的围垦区稻田耕作层土壤N₂O还原速率演替规律及其微生物数量变异特征。结果表明，土壤总有机碳含量（TOC）随围垦年限增长而显著增加，而土壤pH值、SO₄^2-浓度和EC值则均随围垦年限增长而呈逐渐下降趋势。土壤N₂O还原速率随围垦年限增长而显著增加，其中围垦86 a稻田土壤达到25.5 μg N₂O·g^-1·d^-1，与光滩湿地相比增加了58.4%。定量PCR结果发现，功能基因nosZ Ⅰ和nosZ Ⅱ拷贝数也随着围垦年限增长而显著增加，其中围垦86 a的稻田土壤功能基因分别为1.72×10⁸ copies·g^-1和4.36×10⁸ copies· g^-1，比光滩湿地稻田高出一个数量级。相关性分析发现土壤N₂O还原速率与功能基因nosZ Ⅰ拷贝数呈显著正相关，而功能基因nosZ Ⅱ拷贝数随围垦年限的增加率远高于功能基因nosZ Ⅰ；N₂O还原速率、功能基因nosZ Ⅰ、nosZ Ⅱ拷贝数与3个土壤理化指标（pH、EC、SO₄^2-）均呈负相关。因此，围垦造田促进了滨海湿地土壤N₂O还原过程，而功能基因nosZ Ⅰ数量的大幅增加是N₂O还原速率增加的重要原因。     

基于改进极限学习机的水体溶解氧预测方法

为了有效地指导水产养殖生产，提高溶解氧浓度预测的精度，提出了基于因子筛选和改进极限学习机（Extreme Learning Machine，ELM）的水产养殖溶解氧预测模型。首先，利用皮尔森相关系数法计算各影响因子与溶解氧浓度间的相关系数，提取强关联因子，降低预测模型的输入量维度；采用偏最小二乘算法（Partial Least Square, PLS）优化传统ELM神经网络，避免网络中隐含层共线性问题，保障输出权值的稳定性；然后，结合新型激活函数，构建水体溶解氧浓度预测模型。最后，将SPLS-ELM（Selection Based Partial Least Square Optimized Extreme Learning Machine）预测模型应用到江苏省无锡市南泉基地某试验池塘的水体溶解氧预测中。试验结果表明：该模型的预测均方根误差为0.3232，与最小二乘支持向量机（Least Square Support Vector Machine，LSSVM）、BP神经网络、粒子群（Particle Swarm Optimization，PSO）优化LSSVM和遗传算法（Genetic Algorithm, GA）优化BP神经网络相比分别降低40.98%、44.48%、34.73%和44.18%。且该模型的运行时间仅0.6231s，预测精度和运行效率明显优于其他模型。该模型的溶解氧预测曲线接近真实溶解氧变化曲线，能够满足水产养殖实际生产对水体溶解氧预测的要求。     

基于深度学习的大豆生长期叶片缺素症状检测方法

为了检测作物叶片缺素,提出了一种基于神经网络的大豆叶片缺素视觉检测方法。在对大豆缺素叶片进行特征分析后,采用深度学习技术,利用Mask R-CNN模型对固定摄像头采集的叶片图像进行分割,以去除背景特征,并利用VGG16模型进行缺素分类。首先通过摄像头采集水培大豆叶片图像,对大豆叶片图像进行人工标记,建立大豆叶片图像分割任务的训练集和测试集,通过预训练确定模型的初始参数,并使用较低的学习率训练Mask RCNN模型,训练后的模型在测试集上对背景遮挡的大豆单叶片和多叶片分割的马修斯相关系数分别达到了0.847和0.788。通过预训练确定模型的初始参数,使用训练全连接层的方法训练VGG16模型,训练的模型在测试集上的分类准确率为89.42%。通过将特征明显的叶片归类为两类缺氮特征和4类缺磷特征,分析讨论了模型的不足之处。本文算法检测一幅100万像素的图像平均运行时间为0.8 s,且对复杂背景下大豆叶片缺素分类有较好的检测效果,可为农业自动化生产中植株缺素情况估计提供技术支持。     

Variations of SOC and MBC observed in an incubated brown loam soil managed under different tillage systems for 12 years

To assess changes in organic carbon pools, an incubation experiment was conducted under different temperatures and field moisture capacity (FMC) on a brown loam soil from three tillage practices used for 12 years: no‐till (NT), subsoiling (ST) and conventional tillage (CT). Total microbial respiration was measured for incubated soil with and without the input of straw. Results indicated that soil organic carbon (SOC) and microbial biomass carbon (MBC) under ST, NT and CT was higher in soil with straw input than that without, while the microbial quotient (MQ or MBC: SOC) and metabolic quotient (qCO₂) content under CT followed the opposite trend. Lower temperature, lower moisture and with straw input contributed to the increases in SOC concentration, especially under NT and ST systems. The SOC concentrations under ST, with temperatures of 30 and 35°C after incubation at 55% FMC, were greater than those under CT by 28.4% and 30.6%, respectively. The increase in MBC was highest at 35°C for 55%, 65% and 75% FMC; in soil under ST, MBC was greater than that under CT by 199.3%, 50.7% and 23.8%, respectively. At 30°C, the lower qCO₂ was obtained in soil incubated under NT and ST. The highest MQ among three tillage practices was measured under ST at 55% FMC, NT at 65% FMC and CT at 75% FMC with straw input. These data indicate the benefits of enhancing the MQ; the low FMC was beneficial to ST treatment. Under higher temperature and drought stress conditions, the adaptive capacity of ST and NT is better than that of CT.     

网络对农业高校大学生学习的影响及对策

网络现已成为大学生日常生活中不可或缺的一部分。网络所具有的资源丰富、快速便捷等特点给大学生带来了很多积极影响,但是网络所带来的消极影响也不容小觑。通过对农业院校大学生学习情况的调查,研究并总结了网络对大学生学习的积极和消极影响。针对网络对大学生学习的负面影响提出了几点应对之策。     

基于产品空间理论的中国林业产业升级特征分析

林业产业如何进行转型升级是实现林业现代化与高质量发展中的重要一环。本文基于产品空间理论，使用聚类热图和复杂网络方法，构建1962—2017年中国林业产业产品空间，从产品复杂度和优势林产品变化两个角度分析林业产业升级特征。结果表明，新获得优势林产品复杂度高，为0.31，传统失势林产品较低，为-0.21，表征林业产业已朝附加值更高的有利方向升级，但传统优势林产品复杂度较低，说明林业产业已有优势产品竞争激烈不利于升级。产品复杂度较高的潜在优势林产品是林业机械、机械零件和林化产品，优势林产品在产品空间中的变化存在一定路径依赖，先扩散后收敛于产品空间的中心位置，政府制定的林业产业政策与全球化背景可能促进了优势林产品升级。因此，政府制定产业政策时，应对不同优势类型林产品采取差异化策略，应完善产品复杂度低的传统优势林产品市场退出机制；减少与优势林产品距离较近的潜在优势林产品政策干预，对距离较远的复杂度高的潜在优势林产品使用补贴等方式引导升级。     

便携式XRF仪现场快速测定土壤中Pb的可行性研究

便携式XRF分析仪具有轻便、快速和可测对象较多与测量元素较广等特点而广泛应用于矿石、土壤等方面快速检测,但土壤的现场快速测定结果的准确性有待进一步研究与探讨。以安宁河谷平原土壤中Pb为研究对象,通过对便携式XRF仪现场快速检测结果与实验室分析结果的对比和影响因素的分析,建立基于安宁河谷平原表层土壤快速测定结果的线性函数为y=1.170 9x-17.326 0(R~2=0.992 9,x为现场检测结果),探讨其影响因素,为该区域表层土壤中Pb快速检测结果提供依据。     

原味型斗烟原料作用分析

【目的】明确原味型斗烟原料烤烟、白肋烟、百里科、东方烟草、拉塔基亚、黑板烟的特性及其在配方中的作用,为原味型斗烟的配方设计提供参考。【方法】对6种斗烟原料常规化学成分、中性致香物质含量进行测定,并对6种斗烟原料及其按1∶1组成的7种配方斗烟(烤烟(对照)、烤烟/白肋烟、烤烟/东方烟草、烤烟/拉塔基亚、烤烟/百里科、烤烟/黑板烟、烤烟/东方烟草/拉塔基亚)进行感官特性分析,研究原料内在化学成分与感官评价之间的相关性。【结果】6种斗烟原料中烤烟的叶绿素降解产物含量高、氮碱比低;白肋烟总糖、还原糖含量低,烟碱含量高;拉塔基亚总氮和类胡萝卜素降解产物含量高;东方烟草(土耳其AG级)总糖、还原糖含量及糖碱比高;黑板烟烟碱含量低、中性致香物质总量低。感官评价结果表明,白肋烟具有坚果香味,可使配方劲道力量、层次变化和室韵嗅香得分升高;东方烟草香气芳香,可使配方层次变化得分升高;百里科刺激性稍大,可使配方劲道力量、层次变化和室韵嗅香得分升高;黑板烟具有焦糖风味,可使配方层次变化得分升高;拉塔基亚具有焚香风味,可使配方室韵嗅香得分升高,但会降低层次变化得分。相关性分析结果表明,烟碱含量与劲道力量呈极显著正相关,氮碱比与劲道力量呈显著负相关;钾含量与层次变化呈显著正相关,类胡萝卜素降解产物含量与层次变化呈显著负相关;总糖含量、还原糖含量、棕色化反应产物含量与室韵嗅香呈显著负相关。【结论】白肋烟、百里科的烟碱含量高、氮碱比低,可使配方劲道力量变强;黑板烟、白肋烟的加入可丰富配方的层次变化;烤烟、东方烟草的总糖、还原糖、棕色化反应产物含量相对较高,要设计室韵嗅香较浓的配方应减少这2种原料的使用量。