深海环境海洋生态系统监测与修复新技术

The United Nations(UN)’s call for a decade of“ecosystem restoration”was prompted by the need to address the extensive impact of anthropogenic activities on natural ecosystems.Marine ecosystem restoration is increasingly necessary due to increasing habitat degredation in deep waters(>200 m depth).At these depths,which are far beyond those accessible by divers,only established and emerging robotic platforms such as remotely operated vehicles(ROVs),autonomous underwater vehicles(AUVs),landers,and crawlers can operate through manipulators and multiparametric sensor arrays(e.g.,optoacoustic imaging,omics,and environmental probes).The use of advanced technologies for deep-sea ecosystem restoration can provide:①high-resolution three-dimensional(3D)imaging and acoustic mapping of substrates and key taxa,②physical manipulation of substrates and key taxa,③real-time supervision of remote operations and long-term ecological monitoring,and④the potential to work autonomously.Here,we describe how robotic platforms with in situ manipulation capabilities and payloads of innovative sensors could autonomously conduct active restoration and monitoring across large spatial scales.We expect that these devices will be particularly useful in deep-sea habitats,such as①reef-building cold-water corals,②soft-bottom bamboo corals,and③soft-bottom fishery resources that have already been damaged by offshore industries(i.e.,fishing and oil/gas).

基于Faster R-CNN的野外环境中蝗虫快速识别

蝗虫是常见的害虫之一,对农作物和生态系统具有很大的危害,采用常规的方法对蝗虫进行监测存在一定局限性,为了有效应用海量野外影像数据实现对蝗虫实时监测,本文建立了一种基于深度学习网络的蝗虫自动识别模型。利用手机模拟摄像头获取的内蒙古锡林浩特附近草原的280张蝗虫的RGB图像,采用深度学习算法中的Faster R-CNN(Faster Region-based Convolutional Neural Network)网络结构建立了蝗虫识别模型。经验证该模型的精确度为0.756,可以较准确地将蝗虫从野外复杂环境中识别出来,与以往同类研究相比,在识别结果和实用性方面均有较大的进步。该模型是建立蝗虫实时监测系统的基础,可以为蝗虫的防治提供辅助信息,同时该网络结构还可以应用于其他害虫的识别,具有较强的推广性,拓宽了深度学习算法的应用领域。

机械伤根对玉米生长和产量的影响

针对玉米机械化中耕追肥作业过程中入土部件造成玉米根系损伤的问题,通过人为断根方式模拟开沟条施追肥造成玉米根系受损的情况,2015-2016年采用正交设计方法进行大田试验,研究断根时期(拔节期和大喇叭口期)、断根方式(单侧断根和双侧断根)、断根侧距(5 cm、10 cm和15 cm)和断根深度(5 cm、10 cm和15 cm)对玉米生长及产量的影响。试验结果表明:1)断根初期各处理玉米生长受抑制;2)拔节期断根后,玉米茎粗和株高均小于对照(CK),但20 d左右能赶上或超过CK;3)大喇叭口期断根后,玉米茎粗和株高始终小于CK;4)差异最大的处理是T8(大喇叭口期断根、双侧断根、断根侧距5 cm、断根深度15 cm),达到极显著水平(p<0.01)。不同断根处理影响玉米根系在土层中的垂直分布和总干重,拔节期断根后根系总干重增加,0-10 cm土层深度根系比例提高5%,总干重增量最大的处理为T2(拔节期断根、双侧断根、断根侧距10 cm、断根深度10 cm),增幅为11.6%;大喇叭口期断根后根系总干重减少,10-20 cm土层深度根系比例上升15%左右,根干重降低幅度最大的处理是T8,达到53%。断根对产量的影响主要通过影响穗粒数和百粒重实现,总体上降低了玉米产量,减产最大的处理是T8,减产19.1%,处理T3(拔节期断根、单侧断根、断根侧距15 cm、断根深度15 cm)的产量最大,与CK相比增产0.43%。结果表明,于大喇叭口期或之前断根,断根侧距越小、断根深度越大,对玉米生长及产量的影响越大,且双侧断根比单侧断根影响大。通过研究不同断根处理对玉米生长和产量的影响,为适宜机械化中耕追肥方式提供参考。

Effects of mechanical operation-induced root injury on maize growth and yield

A 2-year field experiment was conducted in 2015 and 2016 by using artificial root pruning to simulate mechanical root injury caused by agricultural machinery components and reveal its effects on maize growth and yield.Quasi-level orthogonal experimental design was employed to create orthogonal tables with four factors of interest,namely,pruning time(jointing stage,JS;big trumpet period,BTP),pruning method(unilateral pruning,UNP;bilateral pruning,BIP),pruning distance(5,10,and 15 cm)and pruning depth(5,10,and 15 cm).Results revealed that (1)maize growth was inhibited at the beginning of root pruning;(2)stem diameter(SD)and plant height(PHE)were smaller than those of the control check(CK)but exceeded the latter after 20 d of root pruning in JS;(3)SD and PHE were always smaller than those of the CK under root pruning in BTP;(4)T8(BTP,BIP,5 cm of pruning distance and 15 cm of pruning depth)can reach to a significant level(p<0.01).The vertical distribution and total dry weight(TDW)of maize roots in soil were affected by different root pruning treatments.When pruning in JS,the root ratio in 0-10 cm soil was 11.6%in T2(JS,UNP,a pruning distance of 10 cm and pruning depth of 10 cm).When pruning in BTP,the root ratio of 10-20 cm soil layer increased by 15%.However,the TDW of maize decreased,the largest of which occurred in T8 at 53%.With the exception of a 0.43%increase in T3(JS,UNP,15 cm of pruning distance and 15 cm of pruning depth),the maize yield of all other treatments decreased compared with that of CK,and the largest reduction was in T8 at up to 19.1%.This finding suggests that a small pruning distance and a large pruning depth greatly influence the growth and yield of maize before and during pruning in BTP.The influence of BIP is greater than that of UNP.These results provide evidence for the effects of mechanical root injury on maize growth and yield and serve as a reference for the selection of mechanical topdressing parameters.

Voice-driven fleet management system for agricultural operations

Food consumption is constantly increasing at global scale.In this light,agricultural production also needs to increase in order to satisfy the relevant demand for agricultural products.However,due to by environmental and biological factors(e.g.soil compaction)the weight and size of the machinery cannot be further physically optimized.Thus,only marginal improvements are possible to increase equipment effectiveness.On the contrary,late technological advances in ICT provide the ground for significant improvements in agriproduction efficiency.In this work,the V-Agrifleet tool is presented and demonstrated.VAgrifleet is developed to provide a “hands-free”interface for information exchange and an “Olympic view”to all coordinated users,giving them the ability for decentralized decision-making.The proposed tool can be used by the end-users(e.g.farmers,contractors,farm associations,agri-products storage and processing facilities,etc.)order to optimize task and time management.The visualized documentation of the fleet performance provides valuable information for the evaluation management level giving the opportunity for improvements in the planning of next operations.Its vendorindependent architecture,voice-driven interaction,context awareness functionalities and operation planning support constitute V-Agrifleet application a highly innovative agricultural machinery operational aiding system.