Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature space via a deep neural network. Applied to bird observational data from the citizen science project \textit{eBird}, we demonstrate how the DMSE model discovers inter-species relationships to outperform single-species distribution models (random forests and SVMs) as well as competing multi-label models. Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. An important domain contribution of the DMSE model is the ability to discover and describe species interactions while simultaneously learning the shared habitat preferences among species. As an additional contribution, we provide a graphical embedding of hundreds of bird species in the Northeast US.
SAGE: A sampling-aware global evaluation benchmark for species distribution modeling
University of Zurich（苏黎世大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Swiss Federal Institute for Forest, Snow and Landscape Research, WSL（瑞士联邦森林、雪与景观研究所）；ETH Zürich（苏黎世联邦理工学院）
Institute of Analytics and Data Science, Kennesaw State University（肯尼索州立大学分析与数据科学研究所）；Department of Information Technology, Kennesaw State University（肯尼索州立大学信息技术系）
TEPI: Taxonomy-aware Embedding and Pseudo-Imaging for Scarcely-labeled Zero-shot Genome Classification
Auburn University（奥本大学）；Oklahoma State University（俄克拉荷马州立大学）；Oklahoma Animal Disease Diagnostics Laboratory, College of Veterinary Medicine, Oklahoma State University（俄克拉荷马州立大学兽医学院俄克拉荷马动物疾病诊断实验室）
Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution
Virginia Tech（弗吉尼亚理工大学）；Oak Ridge National Laboratory（橡树岭国家实验室）；University of California, Irvine（加利福尼亚大学欧文分校）；Tulane University（杜兰大学）；Battelle（巴特尔公司）；Duke University（杜克大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；The Ohio State University（俄亥俄州立大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation
Department of Computer Science, Cornell University, USA（康奈尔大学计算机科学系，美国）；School of Computer Science and Informatics, Cardiff University, UK（卡迪夫大学计算机科学与信息学院，英国）；Gulf of Maine Research Institute, USA（缅因湾研究所，美国）；Department of Ecology, Evolution, and Natural Resources, Rutgers University, USA（罗格斯大学生态、进化与自然资源系，美国）
Multi-scale species richness estimation with deep learning
Dynamic Macroecology, Land Change Science, Swiss Federal Research Institute WSL（瑞士联邦研究 institute WSL 动态宏观生态学与土地变化科学）；Department of Evolutionary Biology and Environmental Studies, University of Zurich（苏黎世大学进化生物学与环境研究系）；Department of Spatial Sciences, Faculty of Environmental Sciences, Czech University of Life Sciences Prague（捷克生命科学与技术大学环境科学系空间科学系）；Resource Analysis, Forest Resources and Management, Swiss Federal Research Institute WSL（瑞士联邦研究 institute WSL 资源分析、森林资源与管理）；Ecosystems and Landscape Evolution, Department of Environmental Systems Science, ETH Zürich（苏黎世联邦理工学院环境系统科学系生态系统与景观演变）；Ecosystems and Landscape Evolution, Land Change Science, Swiss Federal Research Institute WSL（瑞士联邦研究 institute WSL 生态系统与景观演变、土地变化科学）；Department of Botany and Zoology, Faculty of Science, Masaryk University（马萨里克大学科学学院植物学与动物学系）；Institute of Biology, Geobotany and Botanical Garden, Martin Luther University Halle-Wittenberg（马尔堡大学生物学、地质植物学与植物园系）；German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig（德国整合生物多样性研究中心 (iDiv) 赫尔伯斯特-耶拿-莱比锡）；Department of Plant Biology and Ecology, Faculty of Science and Technology, University of the Basque Country UPV/EHU（巴斯克国家大学 (UPV/EHU) 科学与技术学院植物生物学与生态学系）
A Deep Generative Artificial Intelligence system to decipher species coexistence patterns
Instituto de Física Corpuscular (IFIC, Universidad de Valencia-CSIC)（瓦伦西亚大学-西班牙国家研究委员会粒子物理研究所）；Universidad de Valencia（瓦伦西亚大学）；CSIC（西班牙国家研究委员会）；Centro de Investigaciones Sobre Desertificación (CIDE, CSIC-Universidad de Valencia-Generalitat Valenciana)（荒漠化研究中心 (CIDE, 西班牙国家研究委员会-瓦伦西亚大学-瓦伦西亚自治区政府)）；University of Sussex（苏塞克斯大学）
InfiniteWalk: Deep Network Embeddings as Laplacian Embeddings with a Nonlinearity
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
用于学习词嵌入的skip-gram模型（Mikolov et al. 2013）已经广泛流行，DeepWalk（Perozzi et al. 2014）以及其他方法已经将该模型扩展到从网络中学习节点表示。Qiu et al.（2018）最近的工作为DeepWalk目标提供了一个封闭形式的表达式，避免了对小数据集进行采样的需要，并提高了准确性。在这些方法中，“窗口大小”T是一个关键的超参数，在该窗口大小内，单词或节点被认为是共现的。我们研究的目标在极限T走向无穷大，这使我们能够简化Qiu等人的表达。我们证明，这个限制目标对应于分解一个简单的变换的伪逆图拉普拉斯，链接DeepWalk广泛的频谱图嵌入的工作。此外，我们表明，通过对这个伪逆应用一个简单的非线性逐项变换，我们恢复了有限T目标和嵌入的良好近似，这些目标和嵌入与DeepWalk和多标签分类中的其他skip-gram方法具有竞争力。令人惊讶的是，我们发现，即使是简单的二进制阈值的拉普拉斯伪逆往往是有竞争力的，这表明最近的方法的核心进步是一个非线性的经典谱嵌入方法的顶部。
A deep learning-based model reduction (DeePMR) method for simplifying chemical kinetics
Shanghai Jiao Tong University（上海交通大学）；Shanghai Center for Brain Science and Brain-Inspired Technology（上海脑科学与类脑研究中心）；Princeton University（普林斯顿大学）；Peking University（北京大学）；AI for Science Institute（北京科学智能研究院）
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
The Ohio State University（俄亥俄州立大学）；Smithsonian Institution（史密森学会）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Irvine（加州大学伊市分校）；Princeton University（普林斯顿大学）；Duke University（杜克大学）
Identification of Tree Species in Japanese Forests based on Aerial Photography and Deep Learning
Research Centre on Interactive Media, Smart Systems and Emerging Technologies (RISE)（互动媒体、智能系统与新兴技术研究中心）；University of Twente（特温特大学）；Leibniz University Hannover（莱布尼茨汉诺威大学）
AudioProtoPNet: An interpretable deep learning model for bird sound classification
Fraunhofer Institute for Energy Economics and Energy System Technology (IEE)（弗劳恩霍夫能源经济与能源系统技术研究所）；Intelligent Embedded Systems (IES), University of Kassel（卡塞尔大学智能嵌入式系统研究所）
Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science（广东省数据科学交叉研究与应用重点实验室）；Beijing Normal University-Hong Kong Baptist University United International College（北京师范大学-香港浸会大学联合国际学院）
