PLAID (Physics-Learning AI Datamodel) is a Python library and data format for representing, storing, and sharing physics simulation datasets for machine learning.Unlike domain-specific formats, PLAID accommodates time-dependent, multi-resolution simulations and heterogeneous meshes.The library provides a high-level API to easily load, inspect, and save data.Beyond basic I/O, PLAID adopts a backend-oriented storage design supporting several backends (cgns, hf_datasets, and zarr), and integrates with the Hugging Face Hub to push and pull datasets.It also ships command-line tools to check, serve, and interactively visualize datasets.In short, PLAID couples a flexible on-disk standard with a software toolkit to manipulate physics data, addressing the needs of ML researchers in fluid dynamics, structural mechanics, and related fields in a generic fashion.Full documentation, examples and tutorials are available at plaid-lib.readthedocs.io.
Combining complementary imaging modalities is critical to build reliable 3D coronary models: intravascular imaging gives sub-millimetre resolution but limited whole-vessel context, while CCTA supplies 3D geometry but suffers from limited spatial resolution and artefacts (e.g., blooming). Prior work demonstrated intravascular/CCTA fusion, yet no open, flexible toolkit is tailored for multi-state analysis (rest/stress, pre-/post-stenting) while offering deterministic behaviour, high performance, and easy pipeline integration. multimodars addresses this gap with deterministic alignment algorithms, a compact NumPy-centred data model, and an optimised Rust backend suitable for scalable, reproducible experiments. The package accepts CSV/NumPy inputs including data formats produced by the AIVUS-CAA software
Understanding the architecture of the human heart requires analysis of its microstructural organization across scales. With the advent of high-resolution imaging techniques such as synchrotron-based tomography, it has become possible to visualize entire hearts at micron-scale resolution. However, translating these large, complex volumetric datasets into interpretable, quantitative descriptors of cardiac organization remains a major challenge. Here we present cardiotensor, an open-source Python package designed to quantify 3D cardiomyocyte orientation in whole- or partial-heart imaging datasets. It provides efficient, scalable implementations of structure tensor analysis, enabling extraction of directional metrics such as helical angle (HA), intrusion angle (IA), and fractional anisotropy (FA). The package supports datasets reaching teravoxel-scale and is optimized for high-performance computing environments, including parallel and chunk-based processing pipelines. In addition, cardiotensor includes tractography functionality to reconstruct continuous cardiomyocyte trajectories. This enables multi-scale myoaggregate visualization down to the myocyte level, depending on resolution. These capabilities enable detailed structural mapping of cardiac tissue, supporting the assessment of anatomical continuity and regional organization.
Remote sensing has entered a new era with the rapid development of artificial intelligence approaches. However, the implementation of deep learning has largely remained restricted to specialists and has been impractical because it often requires (i) large reference datasets for model training and validation; (ii) substantial computing resources; and (iii) strong coding skills. Here, we introduce IAMAP, a user-friendly QGIS plugin that addresses these three challenges in an easy yet flexible way. IAMAP builds on recent advancements in self-supervised learning strategies, which now provide robust feature extractors, often referred to as foundation models. These generalist models can often be reliably used in few-shot or zero-shot scenarios (i.e., with little to no fine-tuning). IAMAP's interface allows users to streamline several key steps in remote sensing image analysis: (i) extracting image features using a wide range of deep learning architectures; (ii) reducing dimensionality with built-in algorithms; (iii) performing clustering on features or their reduced representations; (iv) generating feature similarity maps; and (v) calibrating and validating supervised machine learning models for prediction. By enabling non-AI specialists to leverage the high-quality features provided by recent deep learning approaches without requiring GPU capacity or extensive reference datasets, IAMAP contributes to the democratization of computationally efficient and energy-conscious deep learning methods.
FSML is a Modern Fortran statistics and machine learning library suitable for contemporary research problems and teaching. It includes procedures for basic statistics, hypothesis tests, linear and non-linear methods, and statistical distribution functions.
Aviation turbulence is atmospheric turbulence occurring at length scales large enough (ap proximately 100m to 1km) to affect an aircraft (Sharman, 2016). According to the National Transport Safety Board (NTSB), turbulence experienced whilst onboard an aircraft was the leading cause of accidents from 2009 to 2018 (NTSB, 2021). Clear air turbulence (CAT) is a form of aviation turbulence which cannot be detected by the onboard weather radar. Thus, pilots are unable to preemptively avoid such regions. In order to mitigate this safety risk, CAT diagnostics are used to forecast turbulent regions such that pilots are able to tactically avoid them. rojak is a parallelised Python library and command-line tool for using meteorological data to forecast CAT and evaluating the effectiveness of CAT diagnostics against turbulence observations. Currently, it supports, 1. Computing turbulence diagnostics on meteorological data from the European Centre for Medium-Range Weather Forecasts’s (ECMWF) ERA5 reanalysis on pressure levels (Hersbach, 2023). Moreover, it is easily extendable through a software update to support other types of meteorological data. 2. Retrieving and processing turbulence observations from Aircraft Meteorological Data Relay (AMDAR) data archived at the National Oceanic and Atmospheric Administration (NOAA)(NCEP Meteorological Assimilation Data Ingest System (MADIS), 2024) and AMDAR data collected via the Met Office MetDB system (Met Office, 2008) 3. Computing 27 different turbulence diagnostics, such as the three-dimensional fronto genesis equation (Bluestein, 1993), turbulence index 1 and 2 (Ellrod & Knapp, 1992), negative vorticity advection (Sharman et al., 2006), and Brown’s Richardson tendency equation (Brown, 1973). 4. Converting turbulence diagnostic values into the eddy dissipation rate (EDR) — the International Civil Aviation Organization’s (ICAO) official metric for reporting turbulence (Meteorological Service for International Air Navigation, 2010) These features not only allow users to perform operational forecasting of CAT but also to interrogate the intensification in frequency and severity of CAT due to climate change (Kim et al., 2023; Storer et al., 2017; Williams, 2017), such as by analysing the climatological distribution of the probability of encountering turbulence at different severities (e.g. light turbulence or moderate-or-greater turbulence) for each turbulence diagnostic. These applications involve high-volume datasets, ranging from tens to hundreds of gigabytes, necessitating the use of parallelisation to preserve computational tractability and efficiency, while substantially reducing execution time. As such, rojak leverages Dask to process larger-than-memory data and to run in a distributed manner (Dask Development Team, 2016). The name of the package, rojak, is inspired by its wide range turbulence diagnostics and its applications. While rojak refers to a type of salad, it is also a colloquial term in Malaysia and Singapore for an eclectic mix, reflecting the diverse functionality of the package.
