Search

Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.

Evaluating models and datasets in computer vision remains a challenging task, with most leaderboards relying solely on accuracy. While accuracy is a popular metric for model evaluation, it provides only a coarse assessment by considering a single model's score on all dataset items. This paper explores Item Response Theory (IRT), a framework that infers interpretable latent parameters for an ensemble of models and each dataset item, enabling richer evaluation and analysis beyond the single accuracy number. Leveraging IRT, we assess model calibration, select informative data subsets, and demonstrate the usefulness of its latent parameters for analyzing and comparing models and datasets in computer vision.

Buckling instabilities driven by tissue growth underpin key developmental events such as the folding of the brain. Tissue growth is disordered due to cell-to-cell variability, but the effects of this variability on buckling are unknown. Here, we analyse what is perhaps the simplest setup of this problem: the buckling of an elastic rod with fixed ends driven by spatially varying growth. Combining analytical calculations for simple growth fields and numerical sampling of random growth fields, we show that variability can increase as well as decrease the growth threshold for buckling, even when growth variability does not cause any residual stresses. For random growth, we find that the shift of the buckling threshold correlates with spatial moments of the growth field. Our results imply that biological systems can either trigger or avoid buckling by exploiting the spatial arrangement of growth variability., Comment: 6 pages, 3 figures; Supplemental Material: 7 pages, 1 figure

Global climate models typically operate at a grid resolution of hundreds of kilometers and fail to resolve atmospheric mesoscale processes, e.g., clouds, precipitation, and gravity waves (GWs). Model representation of these processes and their sources is essential to the global circulation and planetary energy budget, but subgrid scale contributions from these processes are often only approximately represented in models using parameterizations. These parameterizations are subject to approximations and idealizations, which limit their capability and accuracy. The most drastic of these approximations is the "single-column approximation" which completely neglects the horizontal evolution of these processes, resulting in key biases in current climate models. With a focus on atmospheric GWs, we present the first-ever global simulation of atmospheric GW fluxes using machine learning (ML) models trained on the WINDSET dataset to emulate global GW emulation in the atmosphere, as an alternative to traditional single-column parameterizations. Using an Attention U-Net-based architecture trained on globally resolved GW momentum fluxes, we illustrate the importance and effectiveness of global nonlocality, when simulating GWs using data-driven schemes., Comment: 9 pages, 7 figures, no tables

Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs trained using domain-focused corpora perform better on specialized tasks. Inspired by this pivotal insight, we developed INDUS, a comprehensive suite of LLMs tailored for the Earth science, biology, physics, heliophysics, planetary sciences and astrophysics domains and trained using curated scientific corpora drawn from diverse data sources. The suite of models include: (1) an encoder model trained using domain-specific vocabulary and corpora to address natural language understanding tasks, (2) a contrastive-learning-based general text embedding model trained using a diverse set of datasets drawn from multiple sources to address information retrieval tasks and (3) smaller versions of these models created using knowledge distillation techniques to address applications which have latency or resource constraints. We also created three new scientific benchmark datasets namely, CLIMATE-CHANGE-NER (entity-recognition), NASA-QA (extractive QA) and NASA-IR (IR) to accelerate research in these multi-disciplinary fields. Finally, we show that our models outperform both general-purpose encoders (RoBERTa) and existing domain-specific encoders (SciBERT) on these new tasks as well as existing benchmark tasks in the domains of interest.

Stability and reliable operation under a spectrum of environmental conditions is still an open challenge for soft and continuum style manipulators. The inability to carry sufficient load and effectively reject external disturbances are two drawbacks which limit the scale of continuum designs, preventing widespread adoption of this technology. To tackle these problems, this work details the design and experimental testing of a modular, tendon driven bead-style continuum manipulator with tunable stiffness. By embedding the ability to independently control the stiffness of distinct sections of the structure, the manipulator can regulate it's posture under greater loads of up to 1kg at the end-effector, with reference to the flexible state. Likewise, an internal routing scheme vastly improves the stability of the proximal segment when operating the distal segment, reducing deviations by at least 70.11%. Operation is validated when gravity is both tangential and perpendicular to the manipulator backbone, a feature uncommon in previous designs. The findings presented in this work are key to the development of larger scale continuum designs, demonstrating that flexibility and tip stability under loading can co-exist without compromise., Comment: To be presented at ICRA 2024, Yokohama, Japan. 6 pages

Increasingly, more software services have been published onto the Internet, making it a big challenge to recommend services in the process of a scientific workflow composition. In this paper, a novel context-aware approach is proposed to recommending next services in a workflow development process, through learning service representation and service selection decision making behaviors from workflow provenance. Inspired by natural language sentence generation, the composition process of a scientific workflow is formalized as a step-wise procedure within the context of the goal of workflow, and the problem of next service recommendation is mapped to next word prediction. Historical service dependencies are first extracted from scientific workflow provenance to build a knowledge graph. Service sequences are then generated based on diverse composition path generation strategies. Afterwards, the generated corpus of composition paths are leveraged to study previous decision making strategies. Such a trained goal-oriented next service prediction model will be used to recommend top K candidate services during workflow composition process. Extensive experiments on a real-word repository have demonstrated the effectiveness of this approach., Comment: 14 pages, 8 figures. arXiv admin note: text overlap with arXiv:2205.11771

Significant progress in the development of highly adaptable and reusable Artificial Intelligence (AI) models is expected to have a significant impact on Earth science and remote sensing. Foundation models are pre-trained on large unlabeled datasets through self-supervision, and then fine-tuned for various downstream tasks with small labeled datasets. This paper introduces a first-of-a-kind framework for the efficient pre-training and fine-tuning of foundational models on extensive geospatial data. We have utilized this framework to create Prithvi, a transformer-based geospatial foundational model pre-trained on more than 1TB of multispectral satellite imagery from the Harmonized Landsat-Sentinel 2 (HLS) dataset. Our study demonstrates the efficacy of our framework in successfully fine-tuning Prithvi to a range of Earth observation tasks that have not been tackled by previous work on foundation models involving multi-temporal cloud gap imputation, flood mapping, wildfire scar segmentation, and multi-temporal crop segmentation. Our experiments show that the pre-trained model accelerates the fine-tuning process compared to leveraging randomly initialized weights. In addition, pre-trained Prithvi compares well against the state-of-the-art, e.g., outperforming a conditional GAN model in multi-temporal cloud imputation by up to 5pp (or 5.7%) in the structural similarity index. Finally, due to the limited availability of labeled data in the field of Earth observation, we gradually reduce the quantity of available labeled data for refining the model to evaluate data efficiency and demonstrate that data can be decreased significantly without affecting the model's accuracy. The pre-trained 100 million parameter model and corresponding fine-tuning workflows have been released publicly as open source contributions to the global Earth sciences community through Hugging Face.

Machine learning and deep learning methods have been widely explored in understanding the chaotic behavior of the atmosphere and furthering weather forecasting. There has been increasing interest from technology companies, government institutions, and meteorological agencies in building digital twins of the Earth. Recent approaches using transformers, physics-informed machine learning, and graph neural networks have demonstrated state-of-the-art performance on relatively narrow spatiotemporal scales and specific tasks. With the recent success of generative artificial intelligence (AI) using pre-trained transformers for language modeling and vision with prompt engineering and fine-tuning, we are now moving towards generalizable AI. In particular, we are witnessing the rise of AI foundation models that can perform competitively on multiple domain-specific downstream tasks. Despite this progress, we are still in the nascent stages of a generalizable AI model for global Earth system models, regional climate models, and mesoscale weather models. Here, we review current state-of-the-art AI approaches, primarily from transformer and operator learning literature in the context of meteorology. We provide our perspective on criteria for success towards a family of foundation models for nowcasting and forecasting weather and climate predictions. We also discuss how such models can perform competitively on downstream tasks such as downscaling (super-resolution), identifying conditions conducive to the occurrence of wildfires, and predicting consequential meteorological phenomena across various spatiotemporal scales such as hurricanes and atmospheric rivers. In particular, we examine current AI methodologies and contend they have matured enough to design and implement a weather foundation model., Comment: 44 pages, 1 figure, updated Fig. 1

As service-oriented architecture becoming one of the most prevalent techniques to rapidly deliver functionalities to customers, increasingly more reusable software components have been published online in forms of web services. To create a mashup, it gets not only time-consuming but also error-prone for developers to find suitable services from such a sea of services. Service discovery and recommendation has thus attracted significant momentum in both academia and industry. This paper proposes a novel incremental recommend-as-you-go approach to recommending next potential service based on the context of a mashup under construction, considering services that have been selected to the current step as well as its mashup goal. The core technique is an algorithm of learning the embedding of services, which learns their past goal-driven context-aware decision making behaviors in addition to their semantic descriptions and co-occurrence history. A goal exclusionary negative sampling mechanism tailored for mashup development is also developed to improve training performance. Extensive experiments on a real-world dataset demonstrate the effectiveness of our approach.

As increasingly more software services have been published onto the Internet, it remains a significant challenge to recommend suitable services to facilitate scientific workflow composition. This paper proposes a novel NLP-inspired approach to recommending services throughout a workflow development process, based on incrementally learning latent service representation from workflow provenance. A workflow composition process is formalized as a step-wise, context-aware service generation procedure, which is mapped to next-word prediction in a natural language sentence. Historical service dependencies are extracted from workflow provenance to build and enrich a knowledge graph. Each path in the knowledge graph reflects a scenario in a data analytics experiment, which is analogous to a sentence in a conversation. All paths are thus formalized as composable service sequences and are mined, using various patterns, from the established knowledge graph to construct a corpus. Service embeddings are then learned by applying deep learning model from the NLP field. Extensive experiments on the real-world dataset demonstrate the effectiveness and efficiency of the approach., Comment: 10 pages, 15 figures, 1 table

Icephobic surfaces inspired by superhydrophobic surfaces offer a passive solution to the problem of icing. However, modeling icephobicity is challenging because some material features that aid superhydrophobicity can adversely affect the icephobic performance. This study presents a new approach based on artificial neural networks to model icephobicity. Artificial neural network models were developed to predict the icephobic performance of concrete. The models were trained on experimental data to predict the surface ice adhesion strength and the coefficient of restitution (COR) of water droplet bouncing off the surface under freezing conditions. The material and coating compositions, and environmental condition were used as the models' input variables. A multilayer perceptron was trained to predict COR with a root mean squared error of 0.08, and a 90% confidence interval of [0.042, 0.151]. The model had a coefficient of determination of 0.92 after deployment. Since ice adhesion strength varied over a wide range of values for the samples, a mixture density network was model was developed to learn the underlying relationship in the multimodal data. Coefficient of determination for the model was 0.96. The relative importance of the input variables in icephobic performance were calculated using permutation importance. The developed models will be beneficial to optimize icephobicity of concrete.

Tribocorrosion maps serve the purpose of identifying operating conditions for acceptable rate of degradation. This paper proposes a machine learning based approach to generate tribocorrosion maps, which can be used to predict tribosystem performance. First, unsupervised machine learning is used to identify and label clusters from tribocorrosion experimental data. The identified clusters are then used to train a support vector classification model. The trained SVM is used to generate tribocorrosion maps. The generated maps are compared with the standard maps from literature.