中国大陆北热带及亚热带地区樟科、壳斗科物种多样性及其生物地理格局分析

以中国大陆北热带及亚热带地区优势科樟科、壳斗科植物为研究对象,利用专著发表大量的样方数据和物种分布数据,分析樟科、壳斗科与群落构建的关系、它们各大属的地理分布格局,探讨影响其分布的可能历史原因。结果表明:中国大陆北热带及亚热带地区森林乔木层优势科为樟科、壳斗科、山茶科、杜鹃花科。樟科、壳斗科物种丰富度均与其所在群落的物种丰富度呈现一定的正相关,樟科对群落构建的贡献较大。樟科、壳斗科植物种的空间多样性分布中心均出现在我国亚热带中部偏南地区。樟科的厚壳桂属、琼楠属以及壳斗科的锥属物种多样性分布中心主要在南亚热带及北热带区域,以广西、云南省份的南部为主。樟科的樟属、新木姜子属、润楠属、木姜子属及壳斗科的柯属、青冈属主要分布在我国大陆北热带及亚热带中部偏南的地区,其多样性分布中心与樟科、壳斗科科水平的物种多样性分布中心极为相似。樟科的山胡椒属、楠属、黄肉楠属,壳斗科的栎属主要分布在研究区域中部以西的地区。研究结果佐证物种的生态学特性以及生物地理学历史综合作用导致目前樟科和壳斗科植物的生物多样性分布格局。     

Three critical factors affecting automated image species recognition performance for camera traps

Ecological camera traps are increasingly used by wildlife biologists to unobtrusively monitor an ecosystems animal population. However, manual inspection of the images produced is expensive, laborious, and time‐consuming. The success of deep learning systems using camera trap images has been previously explored in preliminary stages. These studies, however, are lacking in their practicality. They are primarily focused on extremely large datasets, often millions of images, and there is little to no focus on performance when tasked with species identification in new locations not seen during training. Our goal was to test the capabilities of deep learning systems trained on camera trap images using modestly sized training data, compare performance when considering unseen background locations, and quantify the gradient of lower bound performance to provide a guideline of data requirements in correspondence to performance expectations. We use a dataset provided by Parks Canada containing 47,279 images collected from 36 unique geographic locations across multiple environments. Images represent 55 animal species and human activity with high‐class imbalance. We trained, tested, and compared the capabilities of six deep learning computer vision networks using transfer learning and image augmentation: DenseNet201, Inception‐ResNet‐V3, InceptionV3, NASNetMobile, MobileNetV2, and Xception. We compare overall performance on “trained” locations where DenseNet201 performed best with 95.6% top‐1 accuracy showing promise for deep learning methods for smaller scale research efforts. Using trained locations, classifications with <500 images had low and highly variable recall of 0.750 ± 0.329, while classifications with over 1,000 images had a high and stable recall of 0.971 ± 0.0137. Models tasked with classifying species from untrained locations were less accurate, with DenseNet201 performing best with 68.7% top‐1 accuracy. Finally, we provide an open repository where ecologists can insert their image data to train and test custom species detection models for their desired ecological domain.     

Performance analysis of real-time plant species recognition using bilateral network combined with machine learning classifier

A real-time plant species recognition under an unconstrained environment is a challenging and time-consuming process. The recognition model should cope up with the computer vision challenges such as scale variations, illumination changes, camera viewpoint or object orientation changes, cluttered backgrounds and structure of leaf (simple or compound). In this paper, a bilateral convolutional neural network (CNN) with machine learning classifiers are investigated in relation to the real-time implementation of plant species recognition. The CNN models considered are MobileNet, Xception and DenseNet-121. In the bilateral CNNs (Homogeneous/Heterogeneous type), the models are connected using the cascade early fusion strategy. The Bilateral CNN is used in the process of feature extraction. Then, the extracted features are classified using different machine learning classifiers such as Linear Discriminant Analysis (LDA), multinomial Logistic Regression (MLR), Naïve Bayes (NB), k-Nearest Neighbor (k−NN), Classification and Regression Tree (CART), Random Forest Classifier (RF), Bagging Classifier (BC), Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). From the experimental investigation, it is observed that the multinomial Logistic Regression classifier performed better compared to other classifiers, irrespective of the bilateral CNN models (Homogeneous - MoMoNet, XXNet, DeDeNet; Heterogeneous - MoXNet, XDeNet, MoDeNet). It is also observed that the MoDeNet + MLR model attained the state-of-the-art results (Flavia: 98.71%, Folio: 96.38%, Swedish Leaf: 99.41%, custom created Leaf-12: 99.39%), irrespective of the dataset. The number of misprediction/class is highly reduced by utilizing the MoDeNet + MLR model for real-time plant species recognition.     

LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease

Plant diseases play a significant role in agricultural production, in which early detection of plant diseases is deemed an essential task. Current computational intelligence and computer vision methods have been promising to improve disease diagnosis. Convolutional Neural Networks (CNN) models are capable of detecting plant diseases in an agricultural field and plantation leaf images. MobileNetV2 refers to an appropriate CNN model for mobile devices with subordinate parameters and model file sizes. However, the effectiveness of MobileNetV2 requires improvement to capture more critical features. Xception refers to the extension of InceptionV3 with fewer and excellent parameters in extracting features. This research suggests an ensemble of MobileNetV2 and Xception by concatenating the extracted features to improve plant disease detection performance. This study indicated that MobileNetV2, Xception, and ensemble model achieved 97.32%, 98.30%, and 99.10% accuracy when considering the entire Plant Village dataset. Particularly, MobileNetV2 and Xception models' accuracy improved by 1.8% and 0.8%, respectively. In addition, our model captures 99.52% of all metric scores in the user-defined dataset. Our model indicated better performance than the seven state-of-the-art CNN models, both individually and in ensemble design. It can be integrated with mobile devices, providing fewer parameters and model file size than an ensemble of MobileNetV2 with InceptionResnetV2, VGG19, and VGG16.     

云南元谋盆地上新世甘棠组植物和孢粉组合及其古气候意义

云南元谋盆地湾堡甘棠组植物群的叶化石和孢粉化石合计107种类型,分属86属,47科。植物叶化石包括18科,24属,35种。除一种裸子植物外,其它均为被子植物。被子植物中,榆科、桦木科、豆科无论属种或者化石数量都是最多;杨柳科、槭科、蔷薇科次之;壳斗科、樟科、杨梅科、鼠李科、忍冬科、胡颓子科、杜鹃科、香蒲料、禾本科均有代表。甘棠组的孢粉植物群也相当丰富,合计97个类型,分属72属,44科。以松科、榆科、禾本科及蕨类植物的水龙骨科最为丰富,胡桃科、壳斗科、金缕梅科及蕨类植物的凤尾蕨属也很常见。被子植物花粉占孢粉总数的50%--60%,以禾本科和榆属花粉含量最高,多在10%以上。裸子植物绝大部分为松科花粉,占孢粉总数的20%-30%。孢子以水龙骨科和凤尾蕨属为主,二者各占孢粉总数的5%-10%。发现于元谋盆地湾堡甘棠组的植物叶化石以及孢子花粉组合在成分上都是混合的类群。组合中既有相当多的湿润亚热带常绿阔叶林成分,也有耐干旱的胡颓子、杨梅、旱蕨等灌木、小乔木或草本分子,同时还有含量很高的、在半干旱环境下也能生存的禾本科、榆科花粉。据此推测甘棠组的植物群和孢粉组合反映了上新世时元谋地区的植被已经分化,盆地的周围山地生长有松科、壳斗科、樟科、胡桃科、金缕梅科为主的常绿和落叶阔叶树木或林块,可能有少许杜鹃科小乔木混杂其中,属于地带性植被。而在盆地内则是以禾本科、蔷薇科等为主,杂以大戟科、豆科、忍冬科、杨梅科等灌木或草本植物以及榆科、桦木科等树木组成的稀树灌丛草原型植被。盆地内的植被所反映的气候和周边地区相比,显得明显干旱。因此推测元谋盆地在2-3百万年前的中晚上新世已经发育成为金沙江流域的干热河谷盆地之一。     

An effective and fast solution for classification of wood species: A deep transfer learning approach

Classification and recognition of wood species have critical importance in wood trade, industry, and science. Therefore, accurate identification of wood species is a great necessity. Conventional classification and recognition of wood species require knowledge and experience on the anatomy of wood which is time-consuming, cost-ineffective, and destructive. Hence, convolutional neural networks (CNNs) -a deep learning tool- have replaced the conventional methods. In this study, classification of wood species via the WOOD-AUTH dataset and evaluating the performance of various deep learning architectures including ResNet-50, Inception V3, Xception, and VGG19 in classification with transfer learning was investigated in detail. The dataset contains macroscopic images of 12 wood species with three different types of wood sections: cross, radial and tangential. The experimental findings demonstrate that Xception produced a remarkable performance as compared to the other models in this study and the WOOD-AUTH dataset owners, yielding a classification accuracy of 95.88%.     

中国水青冈属 （壳斗科） 叶结构及分类学意义

叶结构对壳斗科(Fagaceae)现存植物和化石的鉴定具有重要意义。通过对水青冈属5种植物叶结构特征进行细致的研究,结果发现水青冈属植物叶脉有羽状弓形脉、羽状半达缘脉两种类型;三级脉有波状对生贯穿、互生贯穿及混合贯穿三种类型;小脉缺失、简单无分支或一次分支;脉间区发育良好,网眼有三边形、四边形和五边形三种类型,排列规则;具齿种类叶齿由齿主脉和齿侧脉构成,齿侧脉环状。研究结果表明水青冈属二级脉与更高级脉序形成的结构稳定且存在种间差异,具重要分类学价值。基于水青冈属叶结构特征观察结果,本次研究编制了水青冈属植物的分种检索表;参照已有研究结果并结合重要外部形态学特征,编制了壳斗科相关类群分属检索表。     

广东南岭大东山浙江润楠群落物种多样性与区系地理成分分析

应用植被调查样地法研究了广东南岭国家级自然保护区大东山片区的浙江润楠群落的物种多样性、区系地理成分,以及优势种种群的年龄结构。结果表明：（1）在1600m2的样地内共有维管束植物73科119属169种,群落的数量优势科为樟科、蔷薇科、山茶科、壳斗科及杜鹃花科等,种类组成的科、属地理成分中热带成分分别占74·51%和70·10%,温带成分分别占23·53%和33·64%;（2）该群落浙江润楠种群以幼、中龄树为主,其优势地位明显且稳定,乔木层的亚优势树种以罗浮栲、马尾松及荷木等为主;（3）群落垂直结构分为乔木层、灌木层和草本层3层,灌木层的物种最丰富,对群落物种多样性分析发现,Simpson指数：灌木层（乔木层=草本层,Shannon指数：灌木层（乔木层（草本层,Margalef指数：灌木层（乔木层（草本层,Pielou指数：乔木层（灌木层（草本层。     

Tree species composition and diversity of tropical mountain cloud forest in the Yunnan, southwestern China

Species composition, physiognomy, and plant diversity of the less known cloud forests in Yunnan were studied based on data collected from 35 sample plots at seven sites. In floristic composition, the cloud forests are mainly comprised of Fagaceae, Ericaceae, Vacciniaceae, Aceraceae, Magnoliaceae, Theaceae, Aquifoliaceae, Illiciaceae, Lauraceae, and Rosaceae. Physiognomically, the forests are dominated by tree and shrub species. Lianas are rare in the forests. The plants with microphyllous or nanophyllous leaves comprise 44.32–63.46% of the total species, and plants with an entire leaf margin account for more than 50% of the tree and shrub species. There are few tree and shrub species with a drip tip leaf apex and papery leaves. Evergreen species make up more than 75% of the total tree and shrub species. In a 2,500 m² sampling area, the number of vascular species ranged between 57 and 110; Simpson’s diversity index ranged from 0.7719 to 0.9544, Shannon–Winner’s diversity index from 1.8251 to 3.2905, and Pielou’s evenness index from 0.5836 to 0.8982 for trees. The cloud forests in Yunnan are physiognomically similar to the tropical cloud forests in America and Southeast Asia. They very much resemble the mountain dwarf mossy forest in Hainan Island, southeastern China, and the Mountain ericaceous forests in the Malay Peninsula. The cloud forests in Yunnan are considered to be developed, as are the tropical upper montane cloud forests in Asia.     

中国水青冈属（壳斗科）叶结构及分类学意义

叶结构对壳斗科（Fagaeeae）现存植物和化石的鉴定具有重要意义。通过对水青冈属5种植物叶结构特征进行细致的研究,结果发现水青冈属植物叶脉有羽状弓形脉、羽状半达缘脉两种类型;三级脉有波状对生贯穿、互生贯穿及混合贯穿三种类型：小脉缺失、简单无分支或一次分支：脉间区发育良好,网眼有三边形、四边形和五边形三种类型,排列规则;具齿种类叶齿由齿主脉和齿侧脉构成,齿侧脉环状。研究结果表明水青冈属二级脉与更高级脉序形成的结构稳定且存在种问差异．具重要分类学价值。基于水青冈属叶结构特征观察结果,本次研究编制了水青冈属植物的分种检索表：参照已有研究结果并结合重要外部形态学特征,编制了壳斗科相关类群分属检索表。     

亚热带常绿阔叶林89种木本植物一级根碳氮浓度变异规律

为了解亚热带地区常绿阔叶林木本植物一级根养分元素变化规律,基于根序法对福建省建瓯市万木林自然保护区天然常绿阔叶林群落的89种树种一级根进行碳、氮浓度测定。结果表明,89种树种一级根的C、N质量浓度分别为433.9和13.7 mg/g,C∶N为36.7,变异系数分别为6.4%、39.2%和39.9%;一级根C浓度在叶片习性和生长型间存在显著差异,而N浓度和C∶N在不同叶片习性和生长型间的差异不显著;6主要科[樟科(Lauraceae)、壳斗科(Fagaceae)、冬青科(Aquifoliaceae)、山矾科(Symplocaceae)、五列木科(Pentaphylacaceae)和杜英科(Elaeocarpaceae)]树种间一级根C、N浓度和C∶N均差异显著;一级根N浓度随物种系统发育由低级向高级呈现增加的趋势。因此,亚热带常绿阔叶林一级根C浓度种间变异低于N浓度;一级根N浓度受系统发育的影响,而C浓度则受叶片习性和生长型影响,表现出一定的趋同效应。     

A new Latuspina Monzen oak gallwasp species from Taiwan (Hymenoptera: Cynipidae: Cynipini)

A new species of oak gallwasp, Latuspina manmiaoyangae sp. nov., is described in Taiwan. The species induces leaf galls on Quercus variabilis (Fagaceae). Data on the diagnosis, distribution, and biology of the new species are given. This is the second known Latuspina species.     

江西武夷山河岸带阔叶林群落的物种组成和多样性分析

以江西武夷山国家级自然保护区河岸带阔叶林群落为研究对象,对其物种组成进行调查,并采用物种丰富度指数、多样性指数和均匀度指数分析物种多样性。结果表明,保护区河岸带物种极丰富,三条水系10个样方中共调查到维管束植物93科174属304种,群落建群种和灌木层优势种均以常绿阔叶树种为主,物种组成具有典型的亚热带植被特色,以壳斗科、樟科、山茶科物种最多。保护区不同海拔河岸带物种丰富度指数、多样性指数的变化规律基本一致。     

贵州省黔南州古树资源特征分析

对黔南州56科122属213种5571株古树资源的数量分布、种类组成及区系成分特征进行分析。结果表明：黔南州古树资源以三级古树为主,占古树总量的79.7%,胸径多在2 m以下,最大胸径4.9 m;城镇、单位庭院、农村宅院及寺庙分布极少,95.7%的资源分布在乡村,且多为散状分布;以壳斗科Fagaceae、樟科Lauraceae、木兰科Magnoliaceae、榆科Ulmaceae、松科Pinaceae等为种类组成优势科,以金缕梅科Hamamelidaceae、榆科、柏科Cupressaceae、樟科、银杏科Ginkgoaceae等为数量组成优势科,优势种有枫香Liquidambar formosona、柏木Cupressus funebris、榉木Zelkova schneideriana、香樟Cinnamomum camphora和银杏Ginkgo biloba等;有较多的孑遗种、中国特有种和保护树种;科、属、种分布区类型及变型多样,科和种的热带性质较为明显,而在属的层面上,温带成分与热带成分比重无明显差异,科的热带性质偏向于泛热带分布,属和种则以泛热带分布和热带亚洲分布为重;科的温带性质偏向于北温带和南温带间断分布变型,属以北温带分布、东亚和北美洲间断分布、东亚分布为重,种则以北温带分布为重。     

Floristic diversity and co-occurrences in a subtropical broad-leaved forest and two contrasting regrowth stands in central-west Yunnan Province,China

Many of the natural forested ecosystems that still remain in mainland China are being cleared with potentially detrimental effects on woody plant species diversity on both local and regional scales. The most extensive stand of subtropical broad-leaved forest remaining in China is located in Yunnan Province. In an effort to document the influence of human-induced disturbance on Yunnan's woody flora, floristic inventories were conducted in a stand of primary forest and in regrowth stands located in its interior and along its outer margin in the Xujiaba Nature Sanctuary in the Ailao Mountain Range. Of particular interest was the location of the disturbance relative to the primary forest source area. A total of 134 woody plant species representing 74 genera and 43 families were recorded. The floristics of the two regrowth stands were significantly different from each other, with < 10% of their respective floras comprised of co-occurring species. The interior regrowth stand had a higher number of co-occurring species with the primary forest; however, > 40% were still non-co-occurring.The principal families represented in the primary forest and the interior regrowth stand were Aquifoliaceae, Berberidaceae, Fagaceae, Lauraceae, Rosaceae, Smilacaceae, Symplocaceae, Theaceae, and Vacciniaceae. The three dominant species with relative importance values ranging from > 5% to 18% in both the primary forest and the interior regrowth stand were Castanopsis wattii, Lithocarpus jingdongensis, and Symplocos sumuntia. The edge regrowth stands had the lowest species diversity and were dominated by the native pine Pinus yunnanensis, with a relative importance of 24%. The principal families represented in the edge regrowth stand were Betulaceae, Ericaceae, Fagaceae, Myricaceae, Pinaceae, and Theaceae. Only the Fagaceae and Theaceae were well-represented in all three stands. The results of the study document the low species diversity in post-cutting regrowth on the margins of the primary forest as compared with post-cutting regrowth in the forest interior.     

不同干扰强度下江西武夷山河岸带阔叶林群落的结构与数量特征

为揭示中亚热带典型河岸带阔叶林群落的结构特征、数量特征和干扰强度的耦合关系,根据干扰强度的不同,在江西武夷山保护区内选取3条主要水系进行阔叶林群落调查,共统计到河岸带维管束植物93科174属304种,分别占保护区维管束植物总数的41.5%、18.0%、11.9%。物种组成以壳斗科（6属22种）、山茶科（7属22种）、樟科（6属16种）、蔷薇科（8属16种）为主。不同干扰强度下的河岸带植被群落相似性Jaccard系数均在0.2-0.3之间,各群落优势种完全不同,且存在特有分布的物种,但群落乔木层优势种优势度（重要值）差异不显著（P〉0.05）。不同干扰强度下,物种数量、群落Jaccard系数、丰富度指数、多样性指数、均匀度指数总体上为：轻微干扰〉中等干扰〉无干扰;而乔木的平均高度和平均胸径却为：无干扰〉中等干扰〉轻微干扰。研究结果表明,江西武夷山河岸带阔叶林以常绿阔叶树种为主,但不同干扰梯度下群落的结构和数量特征差异性较大。     

CO-WOA: Novel Optimization Approach for Deep Learning Classification of Fish Image

The most significant groupings of cold-blooded creatures are the fish family. It is crucial to recognize and categorize the most significant species of fish since various species of seafood diseases and decay exhibit different symptoms. Systems based on enhanced deep learning can replace the area's currently cumbersome and sluggish traditional approaches. Although it seems straightforward, classifying fish images is a complex procedure. In addition, the scientific study of population distribution and geographic patterns is important for advancing the field's present advancements. The goal of the proposed work is to identify the best performing strategy using cutting-edge computer vision, the Chaotic Oppositional Based Whale Optimization Algorithm (CO-WOA), and data mining techniques. Performance comparisons with leading models, such as Convolutional Neural Networks (CNN) and VGG-19, are made to confirm the applicability of the suggested method. The suggested feature extraction approach with Proposed Deep Learning Model was used in the research, yielding accuracy rates of 100 %. The performance was also compared to cutting-edge image processing models with an accuracy of 98.48 %, 98.58 %, 99.04 %, 98.44 %, 99.18 % and 99.63 % such as Convolutional Neural Networks, ResNet150V2, DenseNet, Visual Geometry Group-19, Inception V3, Xception. Using an empirical method leveraging artificial neural networks, the Proposed Deep Learning model was shown to be the best model.     

主成分分析法在壳斗科植物化石鉴定中的应用*

壳斗科化石是北半球新生代地层的优势分子,然而由于其属种众多,叶片属种间特异性不明显,该科叶片化石的鉴定是古植物学研究的难点之一。面对化石标本不完整的性状特征信息,如何剔除冗余特征,重点考虑具有鉴定意义的标本特征,就显得非常必要。本研究通过调研多种降维算法,考虑到植物特征编码及赋值的数值特性,选用主成分分析法,以壳斗科青冈亚属植物叶片为例,对可能在化石叶片上观察到的22个性状特征(变量)进行降维处理,挑选出对于壳斗科化石叶片分类鉴定起主要作用的10个性状特征,并将其应用于化石鉴定进行验证。结果表明,仅考虑经过主成分分析法压缩挑选的10个主要性状特征,仍然能够实现壳斗科化石植物的准确鉴定。主成分分析法应用于壳斗科性状特征的降维处理效果良好,剔除冗余特征对标本鉴定结果没有影响。     

江西荒山灌木草丛的群落学特征及开发利用

在以往中亚热带植被研究中所提到的有关概念,如草坡、荒坡、山地草原、荒山草甸、荒山草丛、灌丛高草群落、草山草坡、灌丛与荒山草地、次生灌草丛、亚热带次生稀树草丛、草灌丛、亚热带草丛、丘陵荒山荒地、丘陵荒坡和亚热带稀树灌木草原等等,均可认为是亚热带荒山灌木草丛的同义语。但,为与Steppe、Meadow(Prata)、Savannah及撩荒地等加以区别,我们采用了“荒山灌木草丛”的术语,而冠以“荒山”二字是为体现其动态特点和人为利用特点。 亚热带荒山灌木草丛在植被类型学上属于“灌丛和灌草丛”植被型组,但却分属于不同的植被型和植被亚型。可见“荒山灌木草丛,并非植被类型学的概念,而是亚热带地区地     

广州市萝岗区风水林植物组成及群落结构分析

通过野外实地调查,对广州市萝岗区风水林的植物组成及群落结构进行了分析.结果表明:萝岗区单个风水林面积为40 ～600 hm2,共有维管植物112科255属387种;其中,蕨类植物15科21属35种,裸子植物1科1属2种,被子植物96科233属350种;草本和乔木种类较多,分别有122和111种;灌木和藤本种类较少,分别有84和70种;其中,包含国家级珍稀保护植物5种和一些需要关注的种类,以及林下凤尾蕨(Pteris grevilleana Wall.ex Agardh)和虎克鳞盖蕨[Microlepia hookeriana (Wall.) Presl]2种广州市新记录种.优势科较明显,包含茜草科(Rubiaceae)、菊科(Compositae)、大戟科(Euphorbiaceae)、禾本科(Poaceae)、蝶形花科(Papilionaceae)、樟科( Lauraceae)等;虽然寡属科和寡种科所占比例较大,但包含种数较少;寡种属所占比例较大,占总属数的90.59％.植被类型属于南亚热带季风常绿阔叶林,以南亚热带常绿树种为主,可分为乔木层、灌木层和草本层,层间有丰富的藤本植物;作为群落的主体结构,木本植物较草本植物有优势.群落优势建群种主要为樟科、大戟科、壳斗科(Fagaceae)、山茶科(Theaceae)、胡桃科(Juglandaceae)和苏木科(Caesalpiniaceae)等科的种类,依据优势种不同可划分为13个群系.根据调查结果,对广州市萝岗区风水林的保护和资源利用提出了建议.