The global rise in wildfire frequency and intensity over the past decade underscores the need for improved fire monitoring techniques. To advance deep learning research on wildfire detection and its associated human health impacts, we introduce SmokeViz, a large-scale machine learning dataset of smoke plumes in satellite imagery. The dataset is derived from expert annotations created by smoke analysts at the National Oceanic and Atmospheric Administration, which provide coarse temporal and spatial approximations of smoke presence. To enhance annotation precision, we propose pseudo-label dimension reduction (PLDR), a generalizable method that applies pseudo-labeling to refine datasets with mismatching temporal and/or spatial resolutions. Unlike typical pseudo-labeling applications that aim to increase the number of labeled samples, PLDR maintains the original labels but increases the dataset quality by solving for intermediary pseudo-labels (IPLs) that align each annotation to the most representative input data. For SmokeViz, a parent model produces IPLs to identify the single satellite image within each annotations time window that best corresponds with the smoke plume. This refinement process produces a succinct and relevant deep learning dataset consisting of over 160,000 manual annotations. The SmokeViz dataset is expected to be a valuable resource to develop further wildfire-related machine learning models and is publicly available at \url{https://noaa-gsl-experimental-pds.s3.amazonaws.com/index.html#SmokeViz/}.

MPI is the most widely used interface for high-performance computing (HPC) workloads. Its success lies in its embrace of libraries and ability to evolve while maintaining backward compatibility for older codes, enabling them to run on new architectures for many years. In this paper, we propose a new level of MPI compatibility: a standard Application Binary Interface (ABI). We review the history of MPI implementation ABIs, identify the constraints from the MPI standard and ISO C, and summarize recent efforts to develop a standard ABI for MPI. We provide the current proposal from the MPI Forum’s ABI working group, which has been prototyped both within MPICH and as an independent abstraction layer called Mukautuva. We also list several use cases that would benefit from the definition of an ABI while outlining the remaining constraints.

A program or library is considered safe when it’s guaranteed that programmer error cannot cause undefined behavior. MPI, both the standard and its implementations, is not designed to be type or memory safe. The standard requires that types must match across point-to-point communications and that collective call arguments must be the same across all ranks; it is up to the user in most cases to avoid these errors, and if not caught, then program behavior is undefined. Existing research attempts to help application developers find these errors using profiling and debugging tools, but these do not focus on solving the problems of safety. These tools are usually designed to catch errors during development but safety errors can depend on the environment, hardware, and input values, thus they are likely to show up even during production runs. To properly bind and use MPI, many modern memory safe languages, such as Rust, have to carefully validate and check for these errors, making it hard to achieve the performance of languages like Fortran and C. Our work examines how to improve MPI safety, both type and memory safety, at the implementation level and within programming languages; in this way it is possible to ensure valid communication and safety whether in development or in production. Our work presents safe point-to-point messaging prototypes within an MPI implementation and as a UCX-based library written in the Rust programming language. These prototypes are both designed to catch point-to-point communication errors at runtime, specifically datatype mismatches. We analyze results from these prototypes to show that catching these types of errors can be done efficiently, both at the level of the language and the implementation.

PetscSF, the communication component of the Portable, Extensible Toolkit for Scientific Computation (PETSc), is designed to provide PETSc's communication infrastructure suitable for exascale computers that utilize GPUs and other accelerators. PetscSF provides a simple application programming interface (API) for managing common communication patterns in scientific computations by using a star-forest graph representation. PetscSF supports several implementations based on MPI and NVSHMEM, whose selection is based on the characteristics of the application or the target architecture. An efficient and portable model for network and intra-node communication is essential for implementing large-scale applications. The Message Passing Interface, which has been the de facto standard for distributed memory systems, has developed into a large complex API that does not yet provide high performance on the emerging heterogeneous CPU-GPU-based exascale systems. In this article, we discuss the design of PetscSF, how it can overcome some difficulties of working directly with MPI on GPUs, and we demonstrate its performance, scalability, and novel features.

The accuracy of simulation-based forecasting in chaotic systems is heavily dependent on high-quality estimates of the system state at the beginning of the forecast. Data assimilation methods are used to infer these initial conditions by systematically combining noisy, incomplete observations and numerical models of system dynamics to produce highly effective estimation schemes. We introduce a self-supervised framework, which we call \textit{amortized assimilation}, for learning to assimilate in dynamical systems. Amortized assimilation combines deep learning-based denoising with differentiable simulation, using independent neural networks to assimilate specific observation types while connecting the gradient flow between these sub-tasks with differentiable simulation and shared recurrent memory. This hybrid architecture admits a self-supervised training objective which is minimized by an unbiased estimator of the true system state even in the presence of only noisy training data. Numerical experiments across several chaotic benchmark systems highlight the improved effectiveness of our approach compared to widely-used data assimilation methods.

Active Learning (AL) is a methodology from Machine Learning and Design of Experiments (DOE) in which the quantities of interest are measured sequentially and the corresponding surrogate models are constructed incrementally. AL provides compelling optimizations over static DOE in applications with engineering processes where the cost of individual experiments is significant. It also helps perform series of computer experiments in parameter sweeps and performance analysis studies. One of the non-trivial tasks in the design of AL systems is the selection of algorithms for cost-efficient exploration of the input spaces of interest: AL needs to balance ""exploitation"" of experiments with modest costs and careful ""exploration"" of expensive configurations. Finding this balance in an automatic and general manner is challenging yet desirable in practice. In this paper, we investigate the application of AL algorithms to Adaptive Mesh Refinement (AMR) performed on a supercomputer. We use AL in conjunction with Gaussian Process Regression for the incremental modeling of cost and memory usage of a series of AMR simulations of a shock-bubble interaction phenomenon. In the studied 5-dimensional input parameter space - with physical, numerical, and machine parameters - we allow AL to guide experimentation across hundreds of configurations. We develop and evaluate a novel multi-objective AL experiment selection algorithm which prioritizes cost-efficient exploration of available configurations and at the same time avoids simulations that violate memory constraints.

Active Learning (AL) is a methodology from machine learning in which the learner interacts with the data source. In this paper, we investigate application of AL techniques to a new domain: regression problems in performance analysis. For computational systems with many factors, each of which can take on many levels, fixed experiment designs can require many experiments, and can explore the problem space inefficiently. We address these problems with a dynamic, adaptive experiment design, using AL in conjunction with Gaussian Process Regression (GPR). The performance analysis process is "seeded" with a small number of initial experiments, then GPR provides estimates of regression confidence across the full input space. AL is used to suggest follow-up experiments to run, in general, it will suggest experiments in areas where the GRP model indicates low confidence, and through repeated experiments, the process eventually achieves high confidence throughout the input space. We apply this approach to the problem of estimating performance and energy usage of HPGMG-FE, and create good-quality predictive models for the quantities of interest, with low error and reduced cost, using only a modest number of experiments. Our analysis shows that the error reduction achieved from replacing the basic AL algorithm with a cost-aware algorithm can be significant, reaching up to 38% for the same computational cost of experiments.

Simulations of long-term lithospheric deformation involve post-failure analysis of high-contrast brittle materials driven by buoyancy and processes at the free surface. Geodynamic phenomena such as subduction and continental rifting take place over millions year time scales, thus require efficient solution methods. We present pTatin3D, a geodynamics modeling package utilising the material-point-method for tracking material composition, combined with a multigrid finite-element method to solve heterogeneous, incompressible visco-plastic Stokes problems. Here we analyze the performance and algorithmic tradeoffs of pTatin3D's multigrid preconditioner. Our matrix-free geometric multigrid preconditioner trades flops for memory bandwidth to produce a time-to-solution > 2× faster than the best available methods utilising stored matrices (plagued by memory bandwidth limitations), exploits local element structure to achieve weak scaling at 30% of FPU peak on Cray XC-30, has improved dynamic range due to smaller memory footprint, and has more consistent timing and better intra-node scalability due to reduced memory-bus and cache pressure.

The Portable, Extensible Toolkit for Scientific computing (PETSc), which focuses on the scalable solution of problems based on partial differential equations, now incorporates new components that allow full compos ability of solvers for multiphysics and multilevel methods. Through strong encapsulation, we achieve arbitrary, dynamic composition of hierarchical methods for coupled problems and allow customization of all components in composite solvers. For example, we support block decompositions with nested multigrid as well as multigrid on the fully coupled system with block-decomposed smoothers. This paper provides an overview of PETSc's new multiphysics capabilities, which have been used in parallel applications including lithosphere dynamics, subduction and mantle convection, ice sheet dynamics, subsurface reactive flow, fusion, mesoscale materials modeling, and power networks.