2D Maps from CAMELS IllustrisTNG Simulations (Subset)

Author’s Note

This is my first dataset publication on Kaggle, and I’m very excited to share a small, manageable subset of the CAMELS Multifield (CMD) data to help the ML community practice image classification and astrophysical data analysis! Make sure to upvote, comment, and share if you enjoy or have suggestions for me. This subset is distributed under the MIT License with permission from the original author, Francisco Villaescusa-Navarro, and the CAMELS collaboration.

1. Overview

The CAMELS Multifield Dataset (CMD) is a massive collection of 2D maps and 3D grids derived from cosmological simulations that track the evolution of gas, dark matter, stars, black holes, and (in some suites) magnetic fields. These simulations vary important cosmological and astrophysical parameters, allowing researchers to explore and train machine learning models that could help us understand the universe’s fundamental properties.

Because the original CMD is extremely large, I’m providing a small subset from the IllustrisTNG suite, specifically from the LH (Latin Hypercube) set. This subset focuses on 2D maps at redshift z = 0.00, chosen randomly for demonstration and educational purposes.

2. About CAMELS & CMD

2.1 CAMELS Project

• CAMELS stands for Cosmology and Astrophysics with MachinE Learning Simulations.
• It aims to produce large datasets of cosmological simulations where diverse parameters (e.g., Ω_m, σ_8, supernova feedback, black-hole feedback) are systematically varied.

2.2 CMD (CAMELS Multifield Dataset)

• CMD contains hundreds of thousands of 2D maps and 3D grids from thousands of state-of-the-art hydrodynamic and N-body simulations.
• Data is organized by suite (IllustrisTNG, SIMBA, Astrid, or Nbody) and set (LH, CV, 1P, EX, BE, SB, etc.).
• Each 2D map or 3D grid is associated with a specific set of simulation parameters (the “labels”).

2.3 Suites

1. IllustrisTNG (MHD simulations): Gas, dark matter, stars, black holes, and magnetic fields.
2. SIMBA (Hydrodynamic): Similar to IllustrisTNG, but uses the SIMBA code.
3. Astrid (Hydrodynamic): Another code with its own feedback physics.
4. Nbody (Gravity-only): Follows only dark matter without astrophysical processes.

2.4 Sets

• LH (Latin Hypercube): Each simulation has unique values for all parameters, covering a broad range in parameter space.
• CV, 1P, EX, BE, SB: Other sets that vary parameters differently or keep some fixed.

3. This Subset

1. Suite & Set: IllustrisTNG – LH (Latin Hypercube sampling).
2. Field Example: Dark matter density (Mcdm), though you could encounter other fields if you download more from the official CMD resource.
3. Format: .npy files, each containing multiple 2D slices (maps).
4. Size: A small fraction of the full dataset (~5–10 maps or however many you decide to provide).
5. Coordinates: Each 2D map is a “slice” of the cosmological volume at redshift z = 0.00.
6. Parameter Labels:
   • Ω_m (matter density fraction),
   • σ_8 (root-mean-square amplitude of matter fluctuations),
   • A_SN1, A_SN2 (supernova feedback parameters),
   • A_AGN1, A_AGN2 (black-hole/AGN feedback parameters).

Because these maps are from the IllustrisTNG suite, they have non-zero values for all six parameters. If any user references the corresponding Nbody subset, note that only Ω_m and σ_8 apply there.

4. Why This Matters

The CAMELS data—especially 2D projections—are excellent for: - Machine Learning & Computer Vision: Classification, segmentation, or anomaly detection tasks. - Cosmology Research: Investigating how changes in Ω_m, σ_8, or feedback physics affect large-scale structure formation. - Educational Purposes: Students and newcomers can learn how real cosmological simulation data is structured and experiment with analysis or ML pipelines.

5. License & Attribution

This subset is shared under the MIT License granted by the original author, Francisco Villaescusa-Navarro, and the broader CAMELS collaboration. Please see the “License” section for the full text.

1. I am not the original author; I only provide a subset for educational and ML practice purposes.
2. All credits go to the CAMELS collaboration and the authors of the CMD.
3. If you publish results using this data, please cite the original sources appropriately and mention the CAMELS project.

6. References & Further Reading

-**CAMELS Project Overview**
-**IllustrisTNG Official Site**
-**[CMD Official Documentation](https://camels-multifield-dataset.read...

The raster datasets in this data release are maps of soil surface properties that were used in analyzing different approaches for digital soil mapping. They include maps of soil pH, electrical conductivity, soil organic matter, and soil summed fine and very fine sand contents that were created using both 2D and 3D modeling strategies. For each property a map was created using both 2D and 3D approaches to compare the mapped results.

A dataset for 2d path-planning. There are 172192 train instances, 51103 test instances and 15311 validation instances. Each sample contains: - map: a [100, 100] tensor representing an occupancy grid map. 0s are traversable cells, 1s are obstacles. - start: a [2,] tensor representing the coordinates of the starting point on the map - goal: a [2,] tensor representing the coordinates of the desired target point on the map - path: a [n, 2] tensor representing the ground truth optimal trajectory to follow from the start to the goal. The path is computed using the popular D* Lite algorithm, modified so to force a margin of 1 cell from any obstacle. Notice that there are samples in which the goal appears to be placed on an obstacle. In those cases, the trajectory ends with the last feasible (i.e. a cell which is not an obstacle, a 0 in the matrix map) position closest to the goal.

I'm sorry, but I messed up with python namespaces while saving the dataset samples. Check the related notebook for a quick and dirty fix. If you want to make your own dataset, follow the instructions on the github repo.

For an example of a possible application, have a look at my article on Medium.

2D Web Map depicting the "Smart Centres" at 700 Centre St, Thornhill, ON L4J 0A7. 43.811572597832004, -79.45177129969935, 207 MSL. Civil Engineering "Crack & Fracture" assessment of the Public Parking Areas and Aerial (Drone Photogrammetry) "Reality Capture" mission conducted by ACCESSiFLY between Friday, June 24, through Wednesday, June 29, 2022 during Transport Canada & NAVCanada approved "RPAS Flight".

The Navigation Electronic Map market is booming, projected to reach $3021 million by 2025 with a 25.4% CAGR. This report analyzes market drivers, trends, restraints, and key players, offering insights into 2D/3D maps across personal, commercial, and military applications. Explore regional market shares and future growth projections.

The U.S. Geological Survey (USGS) National Uncrewed Systems Office (NUSO) supported the USGS National Cooperative Geologic Mapping Program’s Geoheritage Sites of the Nation Project in July of 2024 with the collection of UAS-based high-resolution imagery of the Marsh-Felch Quarry site at the Bureau of Land Management (BLM) Garden Park Fossil Area. One of the most complete dinosaur skeletons ever unearthed was found here. These discoveries around present-day Garden Park Fossil Area sparked the “Bone Wars” of the late 1800s and inspired the selection of Colorado's state fossil, the Stegosaurus. Three-dimensional (3D) scan flights were conducted at the fossil site using a Skydio X10 UAS, in which the aircraft autonomously determined where to capture photos to achieve coverage across a volume of interest. The natural color UAS images were processed in photogrammetry software to generate a 3D model of this fossil site for inclusion in the Geoheritage web application. A two-dimensional (2D) mapping scan with the Skydio X10 UAS flown at 300 feet above ground level was also conducted to capture the topography of the surrounding area. This portion of the data release presents raw natural color images collected during the 2D mapping flights over the fossil site. Over the course of one 21-minute flight, a Skydio X10 UAS with an integrated VT300-Z Narrow sensor mapped a 36,483 square meter area and captured 456 natural color red, green, blue (RGB) photos to achieve 75% overlap and 75% sidelap. The images are provided here in a zip file to facilitate bulk download. Structure-from-motion (SfM) Digital Surface Model (DSM) and Orthomosaic data products were generated by processing these 2D Mapping images in photogrammetry software. These data products are provided here in .tif format zipped with supporting files. These DSM and orthomosaic data products were generated for visualization of the environment surrounding the quarry site.

Discover the booming commercial aerial surveying market! This in-depth analysis reveals key trends, market size, growth projections (2025-2033), leading companies, and regional insights. Learn about the impact of drone technology and future opportunities in construction, environmental monitoring, and agriculture.

Using ArcGIS, anyone can quickly make and share a map-but creating an effective map requires knowing a few design fundamentals. Enroll in this plan to learn techniques to appropriately symbolize and label map features, apply settings that enhance user interaction with your maps, and create impactful data visualizations that resonate with your intended audience.Goals Choose appropriate map symbols to represent your data. Create attractive labels to provide information about map features. Visualize data in 2D and 3D.

This is a platform that provides high-quality maps of Vworld for web and desktop in a mobile environment. It accepts various national spatial information of Vworld, and allows creation and editing of places, lines, polygons, and circles, and various map expression methods. It supports iOS and Android, and the Android Framework is based on Osmdroid and Java 1.7, so API 25 or lower is recommended.

1. This map is intended as a current snapshot of information that can be disclosed publicly regarding tax credit seismic surveys.2. Representation on this map does not guarantee public release and is subject to statutory requirements in effect at the time of acquisition and application for tax credit.3. Release is subject to public notice and permission of private oil and gas mineral estate owner where applicable. Some surveys require clipping to mineral ownership boundaries; actual map extents of released datasets may differ from those shown here. 4. Year label "Released" surveys denote actual release year. Year label "Eligible" and "Issued" denote the year in which the data is eligible for release and distribution under AS 43.55.025(f)(2)(c), most tax credit seismic projects are held confidential for 10 years from completion of initial seismic processing. 5. Map does not include surveys whose initial seismic processing was completed less than 10 years ago but prior to legislative adoption of the disclosure clause of AS 43.55.025(f)(5). Seismic surveys acquired with credits under AS 43.55.023 are not subject to disclosure under AS 43.55.025(f)(5), and cannot be represented here until their confidentiality period has expired.6. Additional qualifying surveys will be added to this map as new tax credit certificates are issued or as changes in confidentiality status allows.

The automotive digital mapping market is estimated to be worth USD XXX million in 2025 and is projected to grow at a CAGR of XX% from 2025 to 2033. The market is driven by the increasing adoption of advanced driver-assistance systems (ADAS) and autonomous vehicles, which require high-precision digital maps. In addition, the growing demand for location-based services, such as navigation and ride-sharing, is also contributing to the market growth. The market is segmented by application into navigation, fleet management, and location-based services. The navigation segment is the largest segment and is expected to continue to grow at a steady pace. The fleet management segment is also expected to grow at a healthy pace, driven by the increasing adoption of fleet management solutions by businesses. The location-based services segment is expected to grow at the fastest pace, driven by the increasing demand for location-based services, such as ride-sharing and food delivery. The market is also segmented by type into 2D maps, 3D maps, and dynamic maps. The 2D maps segment is the largest segment and is expected to continue to dominate the market. However, the 3D maps segment is expected to grow at a faster pace, driven by the increasing adoption of 3D maps in ADAS and autonomous vehicles. The dynamic maps segment is also expected to grow at a healthy pace, driven by the increasing demand for real-time traffic information.

A 2D background map created based on a continuous digital map, projecting the map to EPSG:3857. Provides graphic map/image map/midnight map/gray map/hybrid map map information. WMTS is an OGC international standard that can be used in libraries and tools that comply with the standard, such as openlayers, qgis, arcgis, cesium, and leaflet. For more details, see the attached file. If the sample does not run, receive an authentication key, change it, and then run it.

Number of tesserae in 2D distance map-based final pipeline segmentations.

The global Projection Mapping Software market is poised for significant expansion, projected to reach an estimated market size of approximately $2.5 billion in 2025 and grow at a robust Compound Annual Growth Rate (CAGR) of around 18% through 2033. This dynamic growth is fueled by several key drivers, including the increasing demand for immersive visual experiences in live events and performances, the burgeoning application in architectural displays for urban beautification and branding, and the evolving use in retail and advertising to create captivating customer engagement. The software's ability to transform static surfaces into dynamic visual canvases is proving indispensable across a wide array of industries. Furthermore, advancements in real-time rendering capabilities, AI-powered content generation, and seamless integration with augmented and virtual reality technologies are pushing the boundaries of what's possible with projection mapping, further stimulating market adoption. The market is segmented into 2D and 3D Projection Mapping Software, with 3D software expected to gain substantial traction due to its enhanced realism and complexity. The market's trajectory, however, is not without its challenges. High initial setup costs for specialized projectors and sophisticated hardware, coupled with the need for skilled professionals to design and execute complex mapping projects, represent significant restraints. Despite these hurdles, the increasing accessibility of user-friendly software solutions and the growing pool of trained technicians are gradually mitigating these limitations. Geographically, North America and Europe currently dominate the market, driven by early adoption and a strong presence of innovative technology companies. However, the Asia Pacific region, particularly China and India, is expected to witness the fastest growth, propelled by rapid digitalization, increasing investments in entertainment infrastructure, and a growing adoption in commercial and educational sectors. Key players like HeavyM, MadMapper, Resolume Arena, and others are actively innovating and expanding their offerings to cater to this expanding global demand. This report provides an in-depth analysis of the global projection mapping software market, forecasting significant growth from $500 million in the Base Year (2025) to an estimated $1.8 billion by the end of the Forecast Period (2033). The Study Period spans from 2019-2033, encompassing the Historical Period (2019-2024) and offering a forward-looking perspective. This market is characterized by rapid technological advancements and a burgeoning demand for immersive visual experiences across diverse sectors.

The global video mapping software market is poised for significant expansion, projected to reach an estimated $2,500 million by 2025, with a robust Compound Annual Growth Rate (CAGR) of 18.5% over the forecast period of 2025-2033. This impressive growth is primarily fueled by the escalating demand for immersive and interactive visual experiences across various sectors. The Entertainment and Live Events segment is a dominant force, driven by the increasing popularity of large-scale concerts, festivals, theatrical productions, and brand activations that leverage video mapping to create captivating spectacles. Advancements in projection technology, coupled with the decreasing cost of hardware, further democratize access to sophisticated video mapping solutions, propelling adoption. The Advertising and Marketing sector is also a key driver, with businesses increasingly utilizing video mapping for impactful product launches, interactive retail displays, and dynamic outdoor advertising campaigns to capture consumer attention and enhance brand engagement. Emerging trends like the integration of AI and machine learning for intelligent content generation and real-time adaptation are set to revolutionize the video mapping landscape. The growing adoption of cloud-based solutions is facilitating greater accessibility, scalability, and collaborative workflows, breaking down geographical barriers and enabling smaller businesses to implement advanced visual strategies. While the market experiences strong tailwinds, potential restraints include the high initial investment costs for complex installations, the need for skilled professionals for operation and content creation, and ongoing concerns regarding content piracy and intellectual property rights. Geographically, North America and Europe are expected to lead the market, driven by early adoption and a mature entertainment and advertising industry. However, the Asia Pacific region, with its rapidly growing economies and increasing disposable income, presents substantial untapped potential for future growth. Key players like Adobe, Resolume, and TouchDesigner are at the forefront of innovation, continuously developing cutting-edge software to meet the evolving demands of this dynamic market. This report offers an in-depth analysis of the global video mapping software market, a rapidly evolving sector crucial for immersive visual experiences. Spanning the historical period of 2019-2024, the base year of 2025, and a forecast period extending to 2033, this research provides actionable insights for stakeholders. The market is projected to witness significant growth, driven by technological advancements and an increasing demand for dynamic visual content across various applications.

2D Map For T1 distribution vs T2 distribution curve from Halliburton Logging. Measured in unitless.

Part of the DEEPEN (DE-risking Exploration of geothermal Plays in magmatic ENvironments) project involved developing and testing a methodology for a 3D play fairway analysis (PFA) for multiple play types (conventional hydrothermal, superhot EGS, and supercritical). This was tested using new and existing geoscientific exploration datasets at Newberry Volcano. This GDR submission includes images, data, and models related to the 3D favorability and uncertainty models and the 2D favorability and uncertainty maps. The DEEPEN PFA Methodology, detailed in the journal article below, is based on the method proposed by Poux & O'brien (2020), which uses the Leapfrog Geothermal software with the Edge extension to conduct PFA in 3D. This method uses all available data to build a 3D geodata model which can be broken down into smaller blocks and analyzed with advanced geostatistical methods. Each data set is imported into a 3D model in Leapfrog and divided into smaller blocks. Conditional queries can then be used to assign each block an index value which conditionally ranks each block's favorability, from 0-5 with 5 being most favorable, for each model (e.g., lithologic, seismic, magnetic, structural). The values between 0-5 assigned to each block are referred to as index values. The final step of the process is to combine all the index models to create a favorability index. This involves multiplying each index model by a given weight and then summing the resulting values. The DEEPEN PFA Methodology follows this approach, but split up by the specific geologic components of each play type. These components are defined as follows for each magmatic play type: 1. Conventional hydrothermal plays in magmatic environments: Heat, fluid, and permeability 2. Superhot EGS plays: Heat, thermal insulation, and producibility (the ability to create and sustain fractures suitable for and EGS reservoir) 3. Supercritical plays: Heat, supercritical fluid, pressure seal, and producibility (the proper permeability and pressure conditions to allow production of supercritical fluid) More information on these components and their development can be found in Kolker et al., (2022). For the purposes of subsurface imaging, it is easier to detect a permeable fluid-filled reservoir than it is to detect separate fluid and permeability components. Therefore, in this analysis, we combine fluid and permeability for conventional hydrothermal plays, and supercritical fluid and producibility for supercritical plays. We also project the 3D favorability volumes onto 2D surfaces for simplified joint interpretation, and we incorporate an uncertainty component. Uncertainty was modeled using the best approach for the dataset in question, for the datasets where we had enough information to do so. Identifying which subsurface parameters are the least resolved can help qualify current PFA results and focus future efforts in data collection. Where possible, the resulting uncertainty models/indices were weighted using the same weights applied to the respective datasets, and summed, following the PFA methodology above, but for uncertainty.

The global Digital HD Map market is booming, projected to reach $1558.9 million by 2025 with a 24.4% CAGR. Driven by autonomous vehicles and AR/VR, this market analysis explores key trends, challenges, and major players like Google and TomTom. Discover the future of location intelligence.