Fast R-CNN深度学习和无人机遥感相结合在松材线虫病监测中的初步应用研究

松材线虫病因其破坏性强、传播速度快和防治难度大等特点,严重威胁着我国的松林资源.及时发现、定位和清理病死松树是控制松材线虫病蔓延的有效手段.本研究利用小型无人机获得松材线虫病疫点的可见光和多光谱的航摄影像.根据松树针叶颜色变化,将松材线虫Bursaphelenchus xylophilus侵染的松树分为病树和枯死树两种...     

Microscopic image recognition of diatoms based on deep learning

Diatoms are a crucial component in the study of aquatic ecosystems and ancient environmental records. However, traditional methods for identifying diatoms, such as morphological taxonomy and molecular detection, are costly, are time consuming, and have limitations. To address these issues, we developed an extensive collection of diatom images, consisting of 7983 images from 160 genera and 1042 species, which we expanded to 49,843 through preprocessing, segmentation, and data augmentation. Our study compared the performance of different algorithms, including backbones, batch sizes, dynamic data augmentation, and static data augmentation on experimental results. We determined that the ResNet152 network outperformed other networks, producing the most accurate results with top-1 and top-5 accuracies of 85.97% and 95.26%, respectively, in identifying 1042 diatom species. Additionally, we propose a method that combines model prediction and cosine similarity to enhance the model's performance in low-probability predictions, achieving an 86.07% accuracy rate in diatom identification. Our research contributes significantly to the recognition and classification of diatom images and has potential applications in water quality assessment, ecological monitoring, and detecting changes in aquatic biodiversity.     

Detection and classification of chilli leaf disease using a squeeze-and-excitation-based CNN model

Chilli leaf disease has a destructive effect on the chilli crop yield. Chilli leaf disease can result in a significant decrease in both the quantity and quality of the chilli crop. Early detection, perfect identification and accurately diagnosing the disease will aid in increasing the profit of the cultivator. However, after a comprehensive survey investigation, we discovered that no studies have been previously conducted to compare the classification performance of machine learning and deep learning for the chilli leaf disease classification problem. In this study, five main leaf diseases i.e. down curl of a leaf, Geminivirus, Cercospora leaf spot, yellow leaf disease, and up curl disease were identified, and images were captured using a digital camera and are labelled. These diseases were classified using 12 different pretrained deep learning networks (AlexNet, DarkNet53, DenseNet201, EfficientNetb0, InceptionV3, MobileNetV2, NasNetLarge, ResNet101, ShuffleNet, SqueezeNet, VGG19, and XceptionNet) using chilli leaf data with and without augmentation using deep learning transfer. Performance metrics such as accuracy, recall, precision, F1-score, specificity, and misclassification were calculated for each network. VGG19 had the best accuracy (83.54%) without augmentation, and DarkNet53 had the best result (98.82%) with augmentation among all pretrained deep learning networks in our self-built chilli leaf dataset. The result was enhanced by designing a squeeze-and-excitation-based convolutional neural network (SECNN) model. The model was tested on a chilli leaf dataset with different input sizes and mini-batch sizes. The proposed model produced the best accuracy of 98.63% and 99.12% without and with augmentation, respectively. The SECNN model was also tested on different datasets from the PlantVillage data, including apple, cherry, corn, grape, peach, pepper, potato, strawberry, and tomato leaves, separately and with the chilli dataset. The proposed model achieved an accuracy of 99.28% in classifying 43 different classes of plant leaf datasets.     

Detection of citrus black spot disease and ripeness level in orange fruit using learning-to-augment incorporated deep networks

Fruit infected by pests or diseases and fruit harvests with different levels of ripeness cause a lack of marketability, decrease in economic value, and increase in crop waste. In this study, we propose a robust and generalized deep convolutional neural network (CNN) model via fine-tuning the pre-trained models for detecting black spot disease and ripeness levels in orange fruit. A dataset containing 1896 confirmed orange images in the farm in four classes (unripe, half-ripe, ripe, and infected with black spot disease) was used. In order to prevent overfitting and increase the robustness and generalizability of the model, instead of using fundamental data augmentation techniques, a novel learning-to-augment strategy that creates new data using noisy and restored images was employed. Controllers using the Bayesian optimization algorithm were utilized to select the optimal noise parameters of Gaussian, speckle, Poisson, and salt-and-pepper noise to generate new noisy images. A convolutional autoencoder model was developed to produce newly restored images affected by optimized noise density. The dataset augmented by the best policies of the learning-to-augment strategy was used to fine-tune several pre-trained models (GoogleNet, ResNet18, ResNet50, ShuffleNet, MobileNetv2, and DenseNet201). The results showed that the learning-to-augment strategy for the fine-tuned ResNet50 achieved the best performance with 99.5% accuracy, and 100% F-measure by assigning images infected with black spot disease as the positive class. The proposed automatic disease and fruit quality monitoring technique can be also used for the detection of other diseases in agriculture and forestry.     

Automatic strawberry leaf scorch severity estimation via faster R-CNN and few-shot learning

Using deep learning to estimate strawberry leaf scorch severity often achieves unsatisfactory results when a strawberry leaf image contains complex background information or multi-class diseased leaves and the number of annotated strawberry leaf images is limited. To solve these issues, in this paper, we propose a two-stage method including object detection and few-shot learning to estimate strawberry leaf scorch severity. In the first stage, Faster R-CNN is used to mark the location of strawberry leaf patches, where each single strawberry leaf patch is clipped from original strawberry leaf images to compose a new strawberry leaf patch dataset. In the second stage, the Siamese network trained on the new strawberry leaf patch dataset is used to identify the strawberry leaf patches and then estimate the severity of the original strawberry leaf scorch images according to the multi-instance learning concept. Experimental results from the first stage show that Faster R-CNN achieves better mAP in strawberry leaf patch detection than other object detection networks, at 94.56%. Results from the second stage reveal that the Siamese network achieves an accuracy of 96.67% in the identification of strawberry disease leaf patches, which is higher than the Prototype network. Comprehensive experimental results indicate that compared with other state-of-the-art models, our proposed two-stage method comprising the Faster R-CNN (VGG16) and Siamese networks achieves the highest estimation accuracy of 96.67%. Moreover, our trained two-stage model achieves an estimation accuracy of 88.83% on a new dataset containing 60 strawberry leaf images taken in the field, which indicates its excellent generalization ability.     

Application of thermal and visible imaging to estimate stripe rust disease severity in wheat using supervised image classification methods

Reliable and accurate estimation of plant disease severity at the field scale is a key factor for predicting yield losses, disease management and food security. A field experiment was designed and conducted during 2017–18 and 2018–19 with 24 wheat cultivars to estimate the stripe rust severity by supervised classification of thermal and visible images using parallelepiped, minimum distance, mahalanobis distance, maximum likelihood, support vector machine and neural network methods of image classification. Results demonstrated the potential of thermal and visible imaging techniques to estimate wheat stripe rust severity with good accuracy. For both visible and thermal images used in this study, support vector machine gave the best estimates of the rust severity, while the parallelepiped method was the worst-performing method. Support vector machine and neural network methods showed d-index, Nash-Sutcliffe efficiency and coefficient of determination values above 85%, with accuracies above 98% and kappa coefficient above 0.97 for both thermal and visible images. Comparison of thermal and visible image classification performance revealed that for all the methods except support vector machine, the estimated rust severity, overall accuracy and kappa coefficient of thermal images were better than visible images. The present study clearly showed that both thermal and visible image analysis can be applied as a rapid non-destructive technique to estimate the wheat rust severity under field conditions. The study also provided a comparative insight into thermal and visible image classification methods that have great potential for sustainable plant disease management in modern agriculture.     

Gene expression profiling in the stem of young maritime pine trees: detection of ammonium stress-responsive genes in the apex

The shoots of young conifer trees represent an interesting model to study the development and growth of conifers from meristematic cells in the shoot apex to differentiated tissues at the shoot base. In this work, microarray analysis was used to monitor contrasting patterns of gene expression between the apex and the base of maritime pine shoots. A group of differentially expressed genes were selected and validated by examining their relative expression levels in different sections along the stem, from the top to the bottom. After validation of the microarray data, additional gene expression analyses were also performed in the shoots of young maritime pine trees exposed to different levels of ammonium nutrition. Our results show that the apex of maritime pine trees is extremely sensitive to conditions of ammonium excess or deficiency, as revealed by the observed changes in the expression of stress-responsive genes. This new knowledge may be used to precocious detection of early symptoms of nitrogen nutritional stresses, thereby increasing survival and growth rates of young trees in managed forests.     

洞庭湖洲滩速生杨树林变化信息提取方法

洞庭湖是我国第二大淡水湖,其湿地资源具有重要的生态功能和经济价值。近20年来,洞庭湖洲滩速生杨树林发展迅速,其中西洞庭湖杨树林的扩张最为明显,极大改变了湖区湿地植被分布格局,隐含极大的生态风险。以Landsat ETM+和HJ-1A/1B CCD影像为数据源,提出了洞庭湖速生杨树林变化信息提取的两种方法,并对这两种方法进行了比较研究。一种是分类的方法,即采用面向对象分层信息提取的方法先提取出树林滩地信息,再将距离大堤一定范围内的树林滩地归为防护林,速生杨树林变化的面积即为两个时相提取结果的差值。另一种是变化检测的方法,它是基于像元进行变化检测,先确定出总的变化区域,再从中筛选速生杨树林的变化信息。结果表明:(1)两种提取方法都是可行的,不同方法提取的速生林变化信息存在一定差异,但空间分布大体一致;(2)基于分类的方法总体精度和Kappa系数均略高于基于变化检测的方法:其中基于分类的方法总体精度达84.00%,Kappa系数为0.67,基于变化检测的方法总体精度达83.00%,Kappa系数为0.65;(3)基于分类的方法图斑较大、图斑数较少,基于变化检测的方法图斑较小且较破碎、图斑数多;(4)基于分类的方法漏分较少、错分较多,基于变化检测的方法漏分较多、错分较少。为洞庭湖洲滩杨树林的动态监测提供了研究方法,也为杨树林扩张原因及其生态效应分析提供研究基础。     

The effect of soundscape composition on bird vocalization classification in a citizen science biodiversity monitoring project

There is a need for monitoring biodiversity at multiple spatial and temporal scales to aid conservation efforts. Autonomous recording units (ARUs) can provide cost-effective, long-term and systematic species monitoring data for sound-producing wildlife, including birds, amphibians, insects and mammals over large areas. Modern deep learning can efficiently automate the detection of species occurrences in these sound data with high accuracy. Further, citizen science can be leveraged to scale up the deployment of ARUs and collect reference vocalizations needed for training and validating deep learning models. In this study we develop a convolutional neural network (CNN) acoustic classification pipeline for detecting 54 bird species in Sonoma County, California USA, with sound and reference vocalization data collected by citizen scientists within the Soundscapes to Landscapes project (www.soundscapes2landscapes.org). We trained three ImageNet-based CNN architectures (MobileNetv2, ResNet50v2, ResNet100v2), which function as a Mixture of Experts (MoE), to evaluate the usefulness of several methods to enhance model accuracy. Specifically, we: 1) quantify accuracy with fully-labeled 1-min soundscapes for an assessment of real-world conditions; 2) assess the effect on precision and recall of additional pre-training with an external sound archive (xeno-canto) prior to fine-tuning with vocalization data from our study domain; and, 3) assess how detections and errors are influenced by the presence of coincident biotic and non-biotic sounds (i.e., soundscape components). In evaluating accuracy with soundscape data (n = 37 species) across CNN probability thresholds and models, we found acoustic pre-training followed by fine-tuning improved average precision by 10.3% relative to no pre-training, although there was a small average 0.8% reduction in recall. In selecting an optimal CNN architecture for each species based on maximum F(β = 0.5), we found our MoE approach had total precision of 84.5% and average species precision of 85.1%. Our data exhibit multiple issues arising from applying citizen science and acoustic monitoring at the county scale, including deployment of ARUs with relatively low fidelity and recordings with background noise and overlapping vocalizations. In particular, human noise was significantly associated with more incorrect species detections (false positives, decreased precision), while physical interference (e.g., recorder hit by a branch) and geophony (e.g., wind) was associated with the classifier missing detections (false negatives, decreased recall). Our process surmounted these obstacles, and our final predictions allowed us to demonstrate how deep learning applied to acoustic data from low-cost ARUs paired with citizen science can provide valuable bird diversity data for monitoring and conservation efforts.     

基于多时相中巴资源卫星影像的冬小麦分类精度

中巴资源卫星2号星（CBERS-02）具有较高的空间分辨率和较丰富的光谱信息,对植被有较强的探测能力.利用2006—2007年北京地区冬小麦生育期早期的5景CBERS-02卫星影像,计算了各时相和不同时相组合的主要地物类型及冬小麦的光谱可分性距离,进行了监督分类,同时,结合高分辨率航空和卫星遥感影像,构建了训练样本和验证样本,对利用CBERS-02卫星提取的生育早期的冬小麦进行了时相分析和精度评价,并与同期TM影像提取结果进行对比.结果表明：时相是影响冬小麦分类的主要因素,不同光学传感器的遥感影像也会影响分类精度;多时相组合有利于提高冬小麦的提取精度,与单时相冬小麦提取的最高精度相比,最佳时相组合的制图精度提高了20.0%、用户精度提高了7.83%;与TM数据相比, CBERS-02卫星影像的冬小麦分类精度略低.     

基于目标检测的东北虎个体自动识别

东北虎个体的自动识别是种群数量评估和制定有效保护策略的重要基础。以东北虎林园和怪坡虎园38 只虎为研究对象,将目标检测方法首次应用到东北虎个体识别研究中,采用多种深度卷积神经网络模型,以实现虎个体的自动识别。首先通过相机在不同角度对 38 只东北虎进行拍摄取样,建立包含13579张图像的虎样本数据集。由于虎的体侧条纹信息不具有对称性,所以运用单次多盒目标检测（Single Shot MultiBox Detector, SSD）方法,对虎的躯干左侧条纹、右侧条纹以及脸部等不同部位图像,进行自动检测并分割提取,极大节省手工截取时间。在检测分割出的左右侧及脸部不同部位图片基础上,运用上、下、左、右平移变换进行数据增强,使图片数目扩大为原来的5 倍。采用LeNet、AlexNet、ZFNet、VGG16、ResNet34共5 种卷积神经网络模型进行个体自动识别。为了提高识别准确率,运用平均值和最大值不同组合方式来优化池化操作,并在全连接层引入概率分别为0.1、0.2、0.3、0.4的丢弃（Dropout）操作防止过拟合。实验表明,目标检测模型耗时较少,截取分割老虎不同部位条纹能达到0.6 s/张,远快于人工截取速度,并且在测试集上准确率能达到97.4%。不同姿态下的目标部位都能正确识别并分割。ResNet34模型的准确率优于其他网络模型,左右侧条纹以及脸部图像识别准确率分别为93.75%、97.01%和 86.28%,右侧条纹识别准确率优于左侧条纹和脸部图像。研究为野生虎自动相机影像的识别提供技术参考。在未来研究中,对东北虎个体影响数据进行扩充,选取更多影像数据进行训练,使网络具有更强的适应性,从而实现更准确的个体识别。     

A robust deep attention dense convolutional neural network for plant leaf disease identification and classification from smart phone captured real world images

Plant diseases cause significant food loss and hence economic loss around the globe. Therefore, automatic plant disease identification is a primary task to take proper medications for controlling the spread of the diseases. Large variety of plants species and their dissimilar phytopathological symptoms call for the implementation of supervised machine learning techniques for efficient and reliable disease identification and classification. With the development of deep learning strategies, convolutional neural network (CNN) has paved its way for classification of multiple plant diseases by extracting rich features. However, several characteristics of the input images especially captured in real world environment, viz. complex or indistinguishable background, presence of multiple leaves with the diseased leaf, small lesion area, solemnly affect the robustness and accuracy of the CNN modules. Available strategies usually applied standard CNN architectures on the images captured in the laboratory environment and very few have considered practical in-field leaf images for their studies. However, those studies are limited with very limited number of plant species. Therefore, there is need of a robust CNN module which can successfully recognize and classify the dissimilar leaf health conditions of non-identical plants from the in-field RGB images. To achieve the above goal, an attention dense learning (ADL) mechanism is proposed in this article by merging mixed sigmoid attention learning with the basic dense learning process of deep CNN. The basic dense learning process derives new features at higher layer considering all lower layer features and that provides fast and efficient training process. Further, the attention learning process amplifies the learning ability of the dense block by discriminating the meaningful lesion portions of the images from the background areas. Other than adding an extra layer for attention learning, in the proposed ADL block the output features from higher layer dense learning are used as an attention mask to the lower layers. For an effective and fast classification process, five ADL blocks are stacked to build a new CNN architecture named DADCNN-5 for obtaining classification robustness and higher testing accuracy. Initially, the proposed DADCNN-5 module is applied on publicly available extended PlantVillage dataset to classify 38 different health conditions of 14 plant species from 54,305 images. Classification accuracy of 99.93% proves that the proposed CNN module can be used for successful leaf disease identification. Further, the efficacy of the DADCNN-5 model is checked after performing stringent experiments on a new real world plant leaf database, created by the authors. The new leaf database contains 10,851 real-world RGB leaf images of 17 plant species for classifying their 44 distinguished health conditions. Experimental outcomes reveal that the proposed DADCNN-5 outperforms the existing machine learning and standard CNN architectures, and achieved 97.33% accuracy. The obtained sensitivity, specificity and false positive rate values are 96.57%, 99.94% and 0.063% respectively. The module takes approximately 3235 min for training process and achieves 99.86% of training accuracy. Visualization of Class activation mapping (CAM) depicts that DADCNN-5 is able to learn distinguishable features from semantically important regions (i.e. lesion regions) on the leaves. Further, the robustness of the DADCNN-5 is established after experimenting with augmented and noise contaminated images of the practical database.     

Semantic region of interest and species classification in the deep neural network feature domain

In this paper, we focus on animal object detection and species classification in camera-trap images collected in highly cluttered natural scenes. Using a deep neural network (DNN) model training for animal- background image classification, we analyze the input camera-trap images to generate a multi-level visual representation of the input image. We detect semantic regions of interest for animals from this representation using k-mean clustering and graph cut in the DNN feature domain. These animal regions are then classified into animal species using multi-class deep neural network model. According the experimental results, our method achieves 99.75% accuracy for classifying animals and background and 90.89% accuracy for classifying 26 animal species on the Snapshot Serengeti dataset, outperforming existing image classification methods.     

基于多光谱影像的森林树种识别及其空间尺度响应

当前,不同空间分辨率卫星影像对森林类型识别结果中普遍存在的尺度效应,而且纹理参量对不同尺度下树种识别精度的影响仍缺乏广泛认知.本研究以中国东北旺业甸林场为研究区,采用观测时相同步、地理坐标匹配的GF-1 PMS、GF-2 PMS、GF-1 WFV,以及Landsat-8 OLI卫星传感器数据组成空间尺度观测序列(1、2、4、8、16、30 m),并结合支持向量机(SVM)模型,探讨了区域内5种优势树种遥感识别结果的尺度变化规律及其纹理特征参数的影响,同时检验了基于尺度上推转换影像的树种识别结果差异.结果表明: 影像空间分辨率对区域树种识别结果具有显著影响,其中,研究区森林树种识别的最佳影像分辨率为4 m,当分辨率降低至30 m时,树种识别结果最差.在1～8 m影像分辨率范围内,增加纹理信息能够显著提高不同优势树种的识别精度,使总分类精度提升了2.0%～3.6%,但纹理信息对16～30 m影像的识别结果没有显著影响.与真实尺度卫星影像相比,基于升尺度转换影像的树种识别结果及其尺度响应特征存在显著差异,表明在面向多个空间尺度的遥感观测和应用研究中,需要采用真实分辨率影像以确保结果的准确性.     

Growth and defence in young pine and spruce and the expression of resistance to a stem-feeding weevil

Defence in young trees has been much less studied than defence in older ones. In conifers, resin within ducts in bark is an important quantitative defence, but its expression in young trees may be influenced by developmental or physical constraints on the absolute size of the resin ducts as well as by differential allocation of resources to growth and resin synthesis. To examine these relationships, we used nitrogen fertilisation of 1- and 2-year-old pine and spruce to produce trees of different sizes and measured the effect on the number and size of resin ducts and the amount of resin they contained. All of these variables tended to increase with stem diameter, indicating a positive relationship between resin-based defence and growth of 1- and 2-year-old trees. In pine, however, the mass of resin flowing from severed ducts was much lower relative to duct area in 1- than in 2-year-old trees, suggesting that the older trees allocated a higher proportion of the carbon budget to resin synthesis. Resin-based defence in 1-year-old pines appears to be both positively related to growth and resource limited. In spruce, resin production was generally lower, and age-related differences were not observed, suggesting that resin-based defence is less important in this species. Bio-assays of 2-year-old trees with the pine weevil, Hylobius abietis, emphasised the importance of resin as a defence against this bark feeding insect. Nitrogen fertilisation had a limited influence on resistance expression. One-year-old trees remained susceptible because of their small size, low resin production and limited response to fertilisation. The strong growth response of 2-year-old trees to fertilisation increased resin-based defence, but most spruce trees remained susceptible, while most pines were resistant at all levels of fertilisation.     

Spatial pattern of seedlings 1 year after fire in a Mediterranean pine forest

Summary The spatial distribution of seedlings of the dominant perennial plant species (Pinus halepensis, Cistus salviifolius, Rhus coriaria) and may annual species was studied after a wild fire in an eastern Mediterranean pine forest. The spatial distribution of all seedlings is affected by the location of the old burned pine trees. Seedling density of Pinus and Cistus is higher at a distance from the burned pine canopy and lower near the burned pine trunk. It is also higher beneath small burned pine trees than under big ones. Rhus seedling density is higher under big burned pine trees and also near the burned trunks. Seedlings of Pinus, Cistus and Rhus growing under the burned canopy of big pine trees tend to be taller than seedlings under small ones or outside the burned canopy. Most annual species germinate and establish themselves outside the burned canopies, and only a few annual species are found beneath them. It is suggested that variation in the heat of the fire, in the amount of ash between burned pine trees of different sizes, and in the distance from the burned canopy are responsible for the observed pattern of seedling distribution. The possible ecological significance of the spatial pattern of seedlings distribution and their differential growth rate are discussed.     

Animal Scanner: Software for classifying humans,animals, and empty frames in camera trap images

Camera traps are a popular tool to sample animal populations because they are noninvasive, detect a variety of species, and can record many thousands of animal detections per deployment. Cameras are typically set to take bursts of multiple photographs for each detection and are deployed in arrays of dozens or hundreds of sites, often resulting in millions of photographs per study. The task of converting photographs to animal detection records from such large image collections is daunting, and made worse by situations that generate copious empty pictures from false triggers (e.g., camera malfunction or moving vegetation) or pictures of humans. We developed computer vision algorithms to detect and classify moving objects to aid the first step of camera trap image filtering—separating the animal detections from the empty frames and pictures of humans. Our new work couples foreground object segmentation through background subtraction with deep learning classification to provide a fast and accurate scheme for human–animal detection. We provide these programs as both Matlab GUI and command prompt developed with C++. The software reads folders of camera trap images and outputs images annotated with bounding boxes around moving objects and a text file summary of results. This software maintains high accuracy while reducing the execution time by 14 times. It takes about 6 seconds to process a sequence of ten frames (on a 2.6 GHZ CPU computer). For those cameras with excessive empty frames due to camera malfunction or blowing vegetation automatically removes 54% of the false‐triggers sequences without influencing the human/animal sequences. We achieve 99.58% on image‐level empty versus object classification of Serengeti dataset. We offer the first computer vision tool for processing camera trap images providing substantial time savings for processing large image datasets, thus improving our ability to monitor wildlife across large scales with camera traps.     

Effect of pine foliage damage on the incidence of larval diapause in the pine caterpillar Dendrolimus punctatus (Lepidoptera: Lasiocampidae)

The pine caterpillar Dendrolimus punctatus (Walker) with a larval facultative diapause is one of the most destructive insect pests of the pine tree Pinus massoniana in China. The larvae feeding on pine trees with different damage levels were studied to determine the induction of diapause under both laboratory and field conditions. Developmental duration of larvae before the third instar was the longest when fed with 75%–90% damaged needles, followed by 25%–40% damaged needles and intact pine needles, whereas mortalities did not differ among different treatments under the conditions of 25° and critical photoperiod 13.5:10.5 L:D. At 25°, no diapause was induced under 15:9 L:D, whereas 100% diapause occurred under 12:12 L:D regardless of the levels of needle damage. Incidences of larvae entering diapause when they were fed with intact, 25%–40% and 75%–90% damaged pine needles were 51.7%, 70.8% and 81% under 13.5:10.5 L:D, respectively. Similar results were obtained in the field experiment. Incidence of diapause was significantly different among the pine needle damage levels of pine trees when the photoperiod was close to the critical day length, indicating that the effect of host plants on diapause induction was dependent on the range of photoperiod. The content of amino acid and sugar decreased and tannin increased in pine needles after feeding by the pine caterpillars, suggesting that changed levels of nutrients in damaged needles or a particular substance emitted by damaged pine trees was perhaps involved in the diapause induction of the pine caterpillar.     

Trapping for Sirex Woodwasp in Brazilian Pine Plantations: Lure,Trap Type and Height of Deployment

The Sirex woodwasp, Sirex noctilio (Hymenoptera: Siricidae) is considered a secondary pest of pine in its native range but has caused considerable economic losses in pine plantation forests in the southern hemisphere. In Brazil, trap trees are the primary tool used for early detection purposes but these are costly, labor-intensive to install and require stressing trees by herbicide application. Flight intercept traps baited with synthetic blends of host volatiles are an attractive alternative but have performed poorly in some settings. This study was carried out to look for alternatives to trap trees for use in Brazilian pine plantations for early detection of S. noctilio. Four field experiments were conducted in two consecutive flight seasons (2015–16 and 2016–17), in planted loblolly pine (Pinus taeda) stands, to compare captures among flight intercept traps baited with different lures, deployed at different heights and among different intercept trap designs. Two experiments compared different host volatile lures and a significant treatment effect was observed in one. No effect of trap design or height was observed.     

基于不同决策树的面向对象林区遥感影像分类比较

面向地理对象影像分析技术(GEOBIA)是影像分辨率越来越高的背景下的产物.如何提高高分辨率影像分类精度和分类效率是影像处理的重要议题之一.本研究对QuickBird影像多尺度分割后的对象进行分类,分析了C5.0、C4.5、CART决策树算法在林区面向对象分类中的效率,并与kNN算法的分类精度进行比较.利用eCognition软件对遥感影像进行多尺度分割,分析得到最佳尺度为90和40.在90尺度下分离出植被和非植被后,在40尺度下提取不同类别植被的光谱、纹理、形状等共21个特征,并利用C5.0、C4.5、CART决策树算法分别对其进行知识挖掘,自动建立分类规则.最后利用建立的分类规则分别对植被区域进行分类,并比较分析其精度.结果表明: 基于决策树的分类精度均高于传统的kNN法.其中,C5.0方法的精度最高,其总体分类精度为90.0%,Kappa系数0.87.决策树算法能有效提高林区树种分类精度,且C5.0决策树的Boosting算法对该分类效果具有最明显的提升.