Explore the vast range of titles available.

Projections from the substantia nigra and striatum traverse through the pallidum on the way to their targets. To date, in vivo characterization of these pathways remains elusive. Here we used high angular resolution diffusion imaging (N=138) to study the characteristics and structural subcompartments of the human pallidum. Our central result shows that the diffusion orientation distribution functions within the pallidum are asymmetrically oriented in a dorsal to dorsolateral direction, consistent with the orientation of underlying fiber systems. We also observed systematic differences in the diffusion signal between the two pallidal segments. Compared to the outer pallidal segment, the internal segment has more peaks in the diffusion orientation distribution and stronger anisotropy in the primary fiber direction, consistent with known cellular differences between the underlying nuclei. These differences in orientation, complexity, and degree of anisotropy are sufficiently robust to automatically segment the pallidal nuclei using diffusion properties. We characterize these patterns in one data set using diffusion spectrum imaging and replicate in a separate sample of subjects imaged using multi-shell imaging, highlighting the reliability of these diffusion patterns within pallidal nuclei. Thus the gray matter diffusion signal can be useful as an in vivo measure of the collective efferent pathways running through the human pallidum. •Fiber pathways passing through the human globus pallidus are difficult to visualize.•Diffusion signal in pallidal voxels is consistent with direction of efferents pathways•Diffusion MRI provides an unbiased method of parcellating the globus pallidus.•Probabilistic parcellations of pallidum are consistent across multiple datasets.

Sequence learning plays a central role in motor skill acquisition. One of the algorithms that is essential to the consolidation process is binding, where multiple movements are driven by a single motor command. Here we show that this binding process originates from learning the transitional probabilities between sequential movements. To determine how binding impacted the neural population patterns which control the movements, we generated unbiased encoding networks of the movement representations at multiple levels of the motor hierarchy. The representational geometries associated with individual movements and movement sets were readily dissociable. In addition, the set network comprised a subset of the individual movement network. However, extensive training by human participants on a sequence learning task did not result in any shift of the representational geometries. This suggests that the representations associated with expert performance are rapidly constructed and highly stable.

We introduce a new dataset and algorithm for fast and efficient coastal distance calculations from Anywhere on Earth (AoE). Existing global coastal datasets are only available at coarse resolution (e.g. 1-4 km) which limits their utility. Publicly available satellite imagery combined with computer vision enable much higher precision. We provide a global coastline dataset at 10 meter resolution, a 100+ fold improvement in precision over existing data. To handle the computational challenge of querying at such an increased scale, we introduce a new library: Layered Iterative Geospatial Hierarchical Terrain-Oriented Unified Search Engine (Lighthouse). Lighthouse is both exceptionally fast and resource-efficient, requiring only 1 CPU and 2 GB of RAM to achieve millisecond online inference, making it well suited for real-time applications in resource-constrained environments.

Unsustainable exploitation of the oceans exacerbated by global warming is threatening coastal communities worldwide. Accurate and timely monitoring of maritime activity is an essential step to effective governance and to inform future policy. In support of this complex global-scale effort, we built Atlantes, a deep learning based system that provides the first-ever real-time view of vessel behavior at global scale. Atlantes leverages a series of bespoke transformers to distill a high volume, continuous stream of GPS messages emitted by hundreds of thousands of vessels into easily quantifiable behaviors. The combination of low latency and high performance enables operationally relevant decision-making and successful interventions on the high seas where illegal and exploitative activity is too common. Atlantes is already in use by hundreds of organizations worldwide. Here we provide an overview of the model and infrastructure that enables this system to function efficiently and cost-effectively at global-scale and in real-time.

Illegal, unreported, and unregulated (IUU) fishing poses a global threat to ocean habitats. Publicly available satellite data offered by NASA and the European Space Agency (ESA) provide an opportunity to actively monitor this activity. Effectively leveraging satellite data for maritime conservation requires highly reliable machine learning models operating globally with minimal latency. This paper introduces three specialized computer vision models designed for synthetic aperture radar (Sentinel-1), optical imagery (Sentinel-2), and nighttime lights (Suomi-NPP/NOAA-20). It also presents best practices for developing and delivering real-time computer vision services for conservation. These models have been deployed in Skylight, a real time maritime monitoring platform, which is provided at no cost to users worldwide.

Illegal, unreported, and unregulated (IUU) fishing poses a global threat to ocean habitats. Publicly available satellite data offered by NASA, the European Space Agency (ESA), and the U.S. Geological Survey (USGS), provide an opportunity to actively monitor this activity. Effectively leveraging satellite data for maritime conservation requires highly reliable machine learning models operating globally with minimal latency. This paper introduces four specialized computer vision models designed for a variety of sensors including Sentinel-1 (synthetic aperture radar), Sentinel-2 (optical imagery), Landsat 8-9 (optical imagery), and Suomi-NPP/NOAA-20/NOAA-21 (nighttime lights). It also presents best practices for developing and deploying global-scale real-time satellite based computer vision. All of the models are open sourced under permissive licenses. These models have all been deployed in Skylight, a real-time maritime monitoring platform, which is provided at no cost to users worldwide.

Wildfires are increasing in intensity and severity at an alarming rate. Recent advances in AI and publicly available satellite data enable monitoring critical wildfire risk factors globally, at high resolution and low latency. Live Fuel Moisture Content (LFMC) is a critical wildfire risk factor and is valuable for both wildfire research and operational response. However, ground-based LFMC samples are both labor intensive and costly to acquire, resulting in sparse and infrequent updates. In this work, we explore the use of a pretrained, highly-multimodal earth-observation model for generating large-scale spatially complete (wall-to-wall) LFMC maps. Our approach achieves significant improvements over previous methods using randomly initialized models (20 reduction in RMSE). We provide an automated pipeline that enables rapid generation of these LFMC maps across the United States, and demonstrate its effectiveness in two regions recently impacted by wildfire (Eaton and Palisades).

We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training (\\(1.7 \\) reduction in GPU hours required to train our Base models) and inference (\\(2.9\\) reductions in MACs on Sentinel-2 tasks), while maintaining the models' overall performance. All training code is available at github.com/allenai/olmoearth_pretrain.

We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and more - across space and time. These inputs are useful for diverse remote sensing tasks, such as crop mapping and flood detection. However, learning shared representations of remote sensing data is challenging, given the diversity of relevant data modalities, and because objects of interest vary massively in scale, from small boats (1-2 pixels and fast) to glaciers (thousands of pixels and slow). We present a novel self-supervised learning algorithm that extracts multi-scale features across a flexible set of input modalities through masked modeling. Our dual global and local contrastive losses differ in their targets (deep representations vs. shallow input projections) and masking strategies (structured vs. not). Our Galileo is a single generalist model that outperforms SoTA specialist models for satellite images and pixel time series across eleven benchmarks and multiple tasks.

Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings OlmoEarth achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The OlmoEarth Platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. OlmoEarth source code, training data, and pre-trained weights are available at \\(https://github.com/allenai/olmoearth_pretrainhttps://github.com/allenai/olmoearth_pretrain\\).