Search

Data-driven weather prediction (DDWP) models are increasingly becoming popular for weather forecasting. However, while operational weather forecasts predict a wide variety of weather variables, DDWPs currently forecast a specific set of key prognostic variables. Non-prognostic ("diagnostic") variables are sometimes modeled separately as dependent variables of the prognostic variables (c.f. FourCastNet), or by including the diagnostic variable as a target in the DDWP. However, the cost of training and deploying bespoke models for each diagnostic variable can increase dramatically with more diagnostic variables, and limit the operational use of such models. Likewise, retraining an entire DDWP each time a new diagnostic variable is added is also cost-prohibitive. We present an two-stage approach that allows new diagnostic variables to be added to an end-to-end DDWP model without the expensive retraining. In the first stage, we train an autoencoder that learns to embed prognostic variables into a latent space. In the second stage, the autoencoder is frozen and "downstream" models are trained to predict diagnostic variables using only the latent representations of prognostic variables as input. Our experiments indicate that models trained using the two-stage approach offer accuracy comparable to training bespoke models, while leading to significant reduction in resource utilization during training and inference. This approach allows for new "downstream" models to be developed as needed, without affecting existing models and thus reducing the friction in operationalizing new models., Comment: Accepted as a spotlight paper at the NeurIPS 2023 workshop on Tackling Climate Change with Machine Learning

Clouds have a significant impact on the Earth's climate system. They play a vital role in modulating Earth's radiation budget and driving regional changes in temperature and precipitation. This makes clouds ideal for climate intervention techniques like Marine Cloud Brightening (MCB) which refers to modification in cloud reflectivity, thereby cooling the surrounding region. However, to avoid unintended effects of MCB, we need a better understanding of the complex cloud to climate response function. Designing and testing such interventions scenarios with conventional Earth System Models is computationally expensive. Therefore, we propose a hybrid AI-assisted visual analysis framework to drive such scientific studies and facilitate interactive what-if investigation of different MCB intervention scenarios to assess their intended and unintended impacts on climate patterns. We work with a team of climate scientists to develop a suite of hybrid AI models emulating cloud-climate response function and design a tightly coupled frontend interactive visual analysis system to perform different MCB intervention experiments.

High-fidelity computational fluid dynamics (CFD) simulations for design space explorations can be exceedingly expensive due to the cost associated with resolving the finer scales. This computational cost/accuracy trade-off is a major challenge for modern CFD simulations. In the present study, we propose a method that uses a trained machine learning model that has learned to predict the discretization error as a function of largescale flow features to inversely estimate the degree of lost information due to mesh coarsening. This information is then added back to the low-resolution solution during runtime, thereby enhancing the quality of the under-resolved coarse mesh simulation. The use of a coarser mesh produces a non-linear benefit in speed while the cost of inferring and correcting for the lost information has a linear cost. We demonstrate the numerical stability of a problem of engineering interest, a 3D turbulent channel flow. In addition to this demonstration, we further show the potential for speedup without sacrificing solution accuracy using this method, thereby making the cost/accuracy trade-off of CFD more favorable., Comment: 7 pages, under review at ASME IMECE 2023 conference

Data-driven weather prediction models (DDWPs) have made rapid strides in recent years, demonstrating an ability to approximate Numerical Weather Prediction (NWP) models to a high degree of accuracy. The fast, accurate, and low-cost DDWP forecasts make their use in operational forecasting an attractive proposition, however, there remains work to be done in rigorously evaluating DDWPs in a true operational setting. Typically trained and evaluated using ERA5 reanalysis data, DDWPs have been tested only in a simulation, which cannot represent the real world with complete accuracy even if it is of a very high quality. The safe use of DDWPs in operational forecasting requires more thorough "real-world" verification, as well as a careful examination of how DDWPs are currently trained and evaluated. It is worth asking, for instance, how well do the reanalysis datasets, used for training, simulate the real world? With an eye towards climate justice and the uneven availability of weather data: is the simulation equally good for all regions of the world, and would DDWPs exacerbate biases present in the training data? Does a good performance in simulation correspond to good performance in operational settings? In addition to approximating the physics of NWP models, how can ML be uniquely deployed to provide more accurate weather forecasts? As a first step towards answering such questions, we present a robust dataset of in-situ observations derived from the NOAA MADIS program to serve as a benchmark to validate DDWPs in an operational setting. By providing a large corpus of quality-controlled, in-situ observations, this dataset provides a meaningful real-world task that all NWPs and DDWPs can be tested against. We hope that this data can be used not only to rigorously and fairly compare operational weather models but also to spur future research in new directions., Comment: 10 pages, 6 figures, under review at NeurIPS main conference

The availability of training data remains a significant obstacle for the implementation of machine learning in scientific applications. In particular, estimating how a system might respond to external forcings or perturbations requires specialized labeled data or targeted simulations, which may be computationally intensive to generate at scale. In this study, we propose a novel solution to this challenge by utilizing a principle from statistical physics known as the Fluctuation-Dissipation Theorem (FDT) to discover knowledge using an AI model that can rapidly produce scenarios for different external forcings. By leveraging FDT, we are able to extract information encoded in a large dataset produced by Earth System Models, which includes 8250 years of internal climate fluctuations, to estimate the climate system's response to forcings. Our model, AiBEDO, is capable of capturing the complex, multi-timescale effects of radiation perturbations on global and regional surface climate, allowing for a substantial acceleration of the exploration of the impacts of spatially-heterogenous climate forcers. To demonstrate the utility of AiBEDO, we use the example of a climate intervention technique called Marine Cloud Brightening, with the ultimate goal of optimizing the spatial pattern of cloud brightening to achieve regional climate targets and prevent known climate tipping points. While we showcase the effectiveness of our approach in the context of climate science, it is generally applicable to other scientific disciplines that are limited by the extensive computational demands of domain simulation models. Source code of AiBEDO framework is made available at https://github.com/kramea/kdd_aibedo. A sample dataset is made available at https://doi.org/10.5281/zenodo.7597027. Additional data available upon request.

Marine cloud brightening (MCB) is a proposed climate intervention technology to partially offset greenhouse gas warming and possibly avoid crossing climate tipping points. The impacts of MCB on regional climate are typically estimated using computationally expensive Earth System Model (ESM) simulations, preventing a thorough assessment of the large possibility space of potential MCB interventions. Here, we describe an AI model, named AiBEDO, that can be used to rapidly projects climate responses to forcings via a novel application of the Fluctuation-Dissipation Theorem (FDT). AiBEDO is a Multilayer Perceptron (MLP) model that uses maps monthly-mean radiation anomalies to surface climate anomalies at a range of time lags. By leveraging a large existing dataset of ESM simulations containing internal climate noise, we use AiBEDO to construct an FDT operator that successfully projects climate responses to MCB forcing, when evaluated against ESM simulations. We propose that AiBEDO-FDT can be used to optimize MCB forcing patterns to reduce tipping point risks while minimizing negative side effects in other parts of the climate., Comment: AAAI Spring Symposium conference full paper

Climate change is one of the most pressing challenges of our time, requiring rapid action across society. As artificial intelligence tools (AI) are rapidly deployed, it is therefore crucial to understand how they will impact climate action. On the one hand, AI can support applications in climate change mitigation (reducing or preventing greenhouse gas emissions), adaptation (preparing for the effects of a changing climate), and climate science. These applications have implications in areas ranging as widely as energy, agriculture, and finance. At the same time, AI is used in many ways that hinder climate action (e.g., by accelerating the use of greenhouse gas-emitting fossil fuels). In addition, AI technologies have a carbon and energy footprint themselves. This symposium brought together participants from across academia, industry, government, and civil society to explore these intersections of AI with climate change, as well as how each of these sectors can contribute to solutions.

In fluid physics, data-driven models to enhance or accelerate solution methods are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of reduced order models of high-dimensional time-dependent fluid systems, machine learning methods grant the benefit of automated learning from data, but the burden of a model lies on its reduced-order representation of both the fluid state and physical dynamics. In this work, we build a physics-constrained, data-driven reduced order model for the Navier-Stokes equations to approximate spatio-temporal turbulent fluid dynamics. The model design choices mimic numerical and physical constraints by, for example, implicitly enforcing the incompressibility constraint and utilizing continuous Neural Ordinary Differential Equations for tracking the evolution of the differential equation. We demonstrate this technique on three-dimensional, moderate Reynolds number turbulent fluid flow. In assessing the statistical quality and characteristics of the machine-learned model through rigorous diagnostic tests, we find that our model is capable of reconstructing the dynamics of the flow over large integral timescales, favoring accuracy at the larger length scales. More significantly, comprehensive diagnostics suggest that physically-interpretable model parameters, corresponding to the representations of the fluid state and dynamics, have attributable and quantifiable impact on the quality of the model predictions and computational complexity., Comment: Submitted to Physical Review Fluids

Past Lagrangian/Eulerian modeling has served as a poor match for the mixing limited physics present in many sprays. Though these Lagrangian/Eulerian methods are popular for their low cost, they are ill-suited for the physics of the dense spray core and suffer from limited predictive power. A new spray model, based on mixing limited physics, has been constructed and implemented in a multi-dimensional CFD code. The spray model assumes local thermal and inertial equilibrium, with air entrainment being limited by the conical nature of the spray. The model experiences full two-way coupling of mass, momentum, species, and energy. An advantage of this approach is the use of relatively few modeling constants. The model is validated with three different sprays representing a range of conditions in diesel and gasoline engines., Comment: Submitted to International Journal of Multiphase Flow

The realization that interfacial features play little role in diesel spray vaporization and advection has changed the modus operandi for spray modeling. Lagrangian particle tracking has typically been focused on droplet behavior, with sub-models for breakup, collision, and interfacially limited vaporization. In contrast, the mixing-oriented spray models are constructed so that gas entrainment is the limiting factor in the evolution of momentum and energy. In this work, a new spray model, ELMO (Eulerian-Lagrangian Mixing-Oriented), is implemented in a three-dimensional CFD code with two-way coupling with the gas phase. The model is verified and validated with three canonical sprays including spray A, H, and G from the ECN database., Comment: Presented at the ILASS-Americas 31st Annual Conference on Liquid Atomization and Spray Systems, May 2021. arXiv admin note: text overlap with arXiv:2107.03508

Multi-scale, multi-fidelity numerical simulations form the pillar of scientific applications related to numerically modeling fluids. However, simulating the fluid behavior characterized by the non-linear Navier Stokes equations are often times computational expensive. Physics informed machine learning methods is a viable alternative and as such has seen great interest in the community [refer to Kutz (2017); Brunton et al. (2020); Duraisamy et al. (2019) for a detailed review on this topic]. For full physics emulators, the cost of network inference is often trivial. However, in the current paradigm of data-driven fluid mechanics models are built as surrogates for complex sub-processes. These models are then used in conjunction to the Navier Stokes solvers, which makes ML model inference an important factor in the terms of algorithmic latency. With the ever growing size of networks, and often times overparameterization, exploring effective network compression techniques becomes not only relevant but critical for engineering systems design. In this study, we explore the applicability of pruning and quantization (FP32 to int8) methods for one such application relevant to modeling fluid turbulence. Post-compression, we demonstrate the improvement in the accuracy of network predictions and build intuition in the process by comparing the compressed to the original network state.

Fluid turbulence is characterized by strong coupling across a broad range of scales. Furthermore, besides the usual local cascades, such coupling may extend to interactions that are non-local in scale-space. As such the computational demands associated with explicitly resolving the full set of scales and their interactions, as in the Direct Numerical Simulation (DNS) of the Navier-Stokes equations, in most problems of practical interest are so high that reduced modeling of scales and interactions is required before further progress can be made. While popular reduced models are typically based on phenomenological modeling of relevant turbulent processes, recent advances in machine learning techniques have energized efforts to further improve the accuracy of such reduced models. In contrast to such efforts that seek to improve an existing turbulence model, we propose a machine learning(ML) methodology that captures, de novo, underlying turbulence phenomenology without a pre-specified model form. To illustrate the approach, we consider transient modeling of the dissipation of turbulent kinetic energy, a fundamental turbulent process that is central to a wide range of turbulence models using a Neural ODE approach. After presenting details of the methodology, we show that this approach outperforms state-of-the-art approaches.

It is well-accepted that the ability to go from one place to another, or mobility, contributes significantly to one's wellbeing. The need for mobility is universal, but the demand for mobility shows a great variation on a country basis. This particular study looks at what are some of the most important factors on a global level that can help in predicting the passengerkilometers-travelled or passenger-miles-travelled (PKT/PMT) on a country by country basis. This particular work tries to quantify the impact of some of the key variables like Gross Domestic Product (GDP), population growth, employment rate, number of households, age demographics within the population and macroeconomic variables on the total vehicle-based travel within each country. A panel-based regression model is developed to identify the effect of some of the key macroeconomic variables on the countries' PKT growth.

We propose a new deep learning based framework to identify pedestrians, and caution distracted drivers, in an effort to prevent the loss of life and property. This framework uses two Convolutional Neural Networks (CNN), one which detects pedestrians and the second which predicts the onset of drowsiness in a driver, is implemented on a Raspberry Pi 3 Model B+, shows great promise. The algorithm for implementing such a low-cost, low-compute model is presented and the results discussed., Comment: arXiv admin note: text overlap with arXiv:1412.0069 by other authors

The paper has been withdrawn effective November 18, 2015. Hydraulic Pump sumps are designed to provide a swirl free flow to the pump. The degree of swirl is measured in physical model tests using a swirl meter and a quantity known as swirl angle is generally measured. The present paper presents a novel method to compute the bulk swirl angle using the local velocity field obtained from computational fluid dynamics data. The basis for the present method is the conservation of angular momentum conservation. By carrying out both numerical and experimental studies the novel swirl angle calculation method is validated. Further the effect of vortex suppression devices in reducing the swirl angle is also demonstrated., Comment: The paper has been withdrawn by the author (Peetak Mitra) since it was felt the paper was sketchy in its concepts