Machine learning (ML)-based weather models have recently undergone rapid improvements. These models are typically trained on gridded reanalysis data from numerical data assimilation systems. However, reanalysis data comes with limitations, such as assumptions about physical laws and low spatiotemporal resolution. The gap between reanalysis and reality has sparked growing interest in training ML models directly on observations such as weather stations. Modelling scattered and sparse environmental observations requires scalable and flexible ML architectures, one of which is the convolutional conditional neural process (ConvCNP). ConvCNPs can learn to condition on both gridded and off-the-grid context data to make uncertainty-aware predictions at target locations. However, the sparsity of real observations presents a challenge for data-hungry deep learning models like the ConvCNP. One potential solution is 'Sim2Real': pre-training on reanalysis and fine-tuning on observational data. We analyse Sim2Real with a ConvCNP trained to interpolate surface air temperature over Germany, using varying numbers of weather stations for fine-tuning. On held-out weather stations, Sim2Real training substantially outperforms the same model architecture trained only with reanalysis data or only with station data, showing that reanalysis data can serve as a stepping stone for learning from real observations. Sim2Real could thus enable more accurate models for weather prediction and climate monitoring.
CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1
Cooperative Institute for Research in the Atmosphere, Colorado State University(科罗拉多州立大学大气研究合作研究所);Electrical and Computer Engineering, Colorado State University(科罗拉多州立大学电气与计算机工程学院);Computer Science, Colorado State University(科罗拉多州立大学计算机科学系);Cooperative Institute for Research in Environmental Sciences, University of Colorado Boulder(科罗拉多大学博尔德分校环境科学合作研究所)
Neural networks are increasingly used in environmental science applications. Furthermore, neural network models are trained by minimizing a loss function , and it is crucial to choose the loss function very carefully for environmental science applications, as it determines what exactly is being optimized. Standard loss functions do not cover all the needs of the environmental sciences, which makes it important for scientists to be able to develop their own custom loss functions so that they can implement many of the classic performance measures already developed in environmental science, inclu…
Implicit neural representations as a coordinate-based framework for continuous environmental field reconstruction from sparse ecological observations
Institute of Fundamental Technological Research, Polish Academy of Sciences(波兰科学院基础技术研究院);Department of Plant Physiology, Institute of Biology, Warsaw University of Life Science(华沙生命科学大学生物学系植物生理学系);Institute of Technology and Life Sciences Falenty(Falenty技术与生命科学研究所)
Foundation Models for Environmental Science: A Survey of Emerging Frontiers
University of Pittsburgh(匹兹堡大学);University of Maryland(马里兰大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)
Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression-Guided Neural Network
University of Southern California(南加州大学);Leonard Davis School of Gerontology, University of Southern California(南加州大学伦纳德·戴维斯老年医学院);University of Minnesota(明尼苏达大学)
Neural Ordinary Differential Equations for Data-Driven Reduced Order Modeling of Environmental Hydrodynamics
U.S. Army Engineer Research and Development Center(美国陆军工程研究与发展中心)
用于流体流动模拟的模型降阶在许多科学和工程领域中仍然具有极大的兴趣。在这里,我们探索了神经常微分方程的使用,这是一种最近引入的连续深度可微网络家族(Chen et al 2018),作为在降阶模型中传播潜在空间动力学的一种方式。我们比较他们的行为与两个经典的非侵入性方法的基础上适当的正交分解和径向基函数插值以及动态模式分解。我们考虑的测试问题包括不可压缩的圆柱绕流,以及在河流和河口系统的浅水流体动力学的实际应用。我们的研究结果表明,神经常微分方程提供了一个优雅的框架,潜在的空间动力学的稳定和准确的演变与外推预测的一个有前途的潜力。然而,为了促进它们在大规模系统中的广泛采用,需要做出重大努力来加快它们的培训时间。这将使超参数空间的更全面的探索,以建立广义的神经ODE近似在广泛的系统动力学。
Sistema Sensor para el Monitoreo Ambiental Basado en Redes Neuronales
Instituto Politécnico Nacional(国立理工学院);Tecnológico de Estudios Superiores de Ecatepec(埃卡特佩克高等技术学院);Universidad Autónoma del Estado de Morelos(莫雷洛斯州立自治大学)
CC-GRMAS: A Multi-Agent Graph Neural System for Spatiotemporal Landslide Risk Assessment in High Mountain Asia
Department of Computer Engineering(计算机工程系);Dwarkadas Jivanlal Sanghvi College of Engineering(德瓦尔卡斯·吉文拉尔·桑格维学院);College of Computing(计算机学院);Georgia Institute of Technology(佐治亚理工学院);Geo-Hydro Meteorological Risks Management Division(地质-水文气象灾害管理部);National Institute of Disaster Management(国家灾害管理研究所)
Forecasting Coccidioidomycosis (Valley Fever) in Arizona: A Graph Neural Network Approach
School of Computing and Augmented Intelligence, Arizona State University(计算与增强智能学院,亚利桑那州立大学);School of Life Sciences, Arizona State University(生命科学学院,亚利桑那州立大学);School of Mathematical and Statistical Sciences, Arizona State University(数学与统计科学学院,亚利桑那州立大学)
Scale Mixtures of Neural Network Gaussian Processes
Kim Jaechul Graduate School of AI, KAIST(韩国科学技术院金在哲人工智能研究生院);School of Computing, KAIST(韩国科学技术院计算机学院);Institute for Basic Science (IBS)(基础科学研究院);AITRICS