Intelligent Hybrid model to Enhance Time Series Models for Predicting Network Traffic

The Intelligent Road Network dataset provided by the Transport Department includes traffic directions, turning restrictions at road junctions, stopping restrictions, on-street parking spaces and other road traffic data for supporting the development of intelligent transport system, fleet management system and car navigation etc. by the public.

Esri China (HK) has prepared this File Geodatabase containing a Network Dataset for the Intelligent Road Network to support Esri GIS users to use the dataset in ArcGIS Pro without going through long configuration steps. Please refer to this guideline to use the Road Network Dataset in ArcGIS Pro for routing analysis. This network dataset has been configured and deployed the following restrictions:

Speed LimitTurnIntersectionTraffic FeaturesPedestrian ZoneTraffic Sign of ProhibitionVehicle RestrictionThe coordinate system of this dataset is Hong Kong 1980 Grid.The objectives of uploading the network dataset to ArcGIS Online platform are to facilitate our Hong Kong ArcGIS users to utilize the data in a spatial ready format and save their data conversion effort.For details about the schema and information about the content and relationship of the data, please refer to the data dictionary provided by Transport Department at https://data.gov.hk/en-data/dataset/hk-td-tis_15-road-network-v2.For details about the data, source format and terms of conditions of usage, please refer to the website of DATA.GOV.HK at https://data.gov.hk.Dataset last updated on: 2021 July

This dataset consists of circles (or lists ) from Twitter. Twitter data was crawled from public sources. The dataset includes node features (profiles), circles, and ego networks. Data is also available from Facebook and Google+. ##Dataset statistics |Attribute| Value| |————-|————| |Nodes| 81306| |Edges| 1768149| |Nodes in largest WCC |81306 (1.000)| |Edges in largest WCC| 1768149 (1.000)| |Nodes in largest SCC| 68413 (0.841)| |Edges in largest SCC |1685163 (0.953)| |Average clustering coefficient| 0.5653| |Number of triangles| 13082506| |Fraction of closed triangles| 0.06415| |Diameter (longest shortest path)| 7| |90-percentile effective diameter| 4.5|

This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics.Anatomical and functional MRI images of the brain have been used to understand the functional connectivity of the human brain and are particularly important in identifying underlying neurodegenerative conditions such as Alzheimer's, Parkinson's, and Autism. Recently, the study of the brain in the form of brain networks using machine learning and graph analytics has become increasingly popular, especially to predict the early onset of these conditions. A brain network, represented as a graph, retains richer structural and positional information that traditional examination methods are unable to capture. However, the lack of brain network data transformed from functional MRI images prevents researchers from data-driven explorations. One of the main difficulties lies in the complicated domain-specific preprocessing steps and the exhaustive computation required to convert data from MRI images into brain networks. We bridge this gap by collecting a large amount of available MRI images from existing studies, working with domain experts to make sensible design choices, and preprocessing the MRI images to produce a collection of brain network datasets. The datasets originate from 6 different sources, cover 4 neurodegenerative conditions, and consist of a total of 2,688 subjects.Due to the data protocol, we are unable to release the ADNI dataset here. The data will be released via the ADNI external data submissions within their data system.We test our graph datasets on 5 machine learning models commonly used in neuroscience and on a recent graph-based analysis model to validate the data quality and to provide domain baselines. To lower the barrier to entry and promote the research in this interdisciplinary field, we release our complete preprocessing details, codes, and brain network data: https://github.com/brainnetuoa/data_driven_network_neuroscience.To stay informed about the new updates of the datasets, kindly provide us with your email address:https://forms.gle/KGAajR6LEysXWKvKAUpdated on 10/09/2024:Please note that we have identified 14 subjects in the PPMI (Parkinson's Progression Markers Initiative) dataset, prodromal group, where the time-series images include only 10 time slots. The invalid subjects are:sub-prodromal103857sub-prodromal120622sub-prodromal146573sub-prodromal40737sub-prodromal52874sub-prodromal55560sub-prodromal56680sub-prodromal58027sub-prodromal58680sub-prodromal59390sub-prodromal59483sub-prodromal59503sub-prodromal71658sub-prodromal75422We have removed the invalid images, and updated the dataset by including both the parcellated images (ppmi_v2.zip) and the preprocessed images (Ppmi_Preprocessed_v2.z*).

The Navigable Waterway Network Lines dataset is periodically updated by the United States Army Corp of Engineers (USACE) and is part of the U.S. Department of Transportation (USDOT)/Bureau of Transportation Statistics (BTS) National Transportation Atlas Database (NTAD). The National Waterway Network (Lines) is a comprehensive network database of the Nation's navigable waterways. The dataset covers the 48 contiguous states plus the District of Columbia, Hawaii, Alaska, Puerto Rico and water links between. It consists of a line feature class of the National Waterway Network (NWN), which is based on a route feature class for the NWN update regions (“1†through “7†, as well as the open ocean region “0†) and route event table with linear referencing system measures for NWN links. This dataset is a feature class with associated measures (in miles) that are used for finding distances, locating features, and displaying route event layers. It was exported from this route event layer. The nominal scale of the dataset varies with the source material. The majority of the information is at 1:100,000 with larger scales used in harbor/bay/port areas and smaller scales used in open waters. These data could be used for analytical studies of waterway performance, for compiling commodity flow statistics, and for mapping purposes. A data dictionary, or other source of attribute information, is accessible at https://doi.org/10.21949/1529053

The Global Urban Network (GUN) dataset provides pre-computed node and edge attribute features for various cities. Each layer is available in .geojson format and can easily be converted into NetworkX, igraph, PyG, and DGL graph formats.

For node attributes, we adopt a uniform Euclidean approach, as it provides a consistent, straightforward, and extensible basis for integrating heterogeneous data sources across different network locations. Accordingly, we construct 100 metres euclidean buffers for each network node and compute the spatial intersection with spatial targets (e.g., street view imagery points, points of interest, and building footprints). To ensure spatial consistency and accurate distance computation, we project spatial entities into local coordinate reference systems (CRS). Users can employ the Urbanity package to generate Euclidean buffers of arbitrary distance.

For edge attributes, we adopt a two-step approach: 1) compute the distance between each spatial point of interest and its proximate edges in the network, and 2) assign entities to the corresponding edge with lowest distance. To account for remote edges (e.g., peripheral routes that are not located close to any amenities), we specify a distance threshold of 50 metres. For buildings, we compute the distance between building centroids and their respective network edge. Accordingly, we compute spatial indicators based on the set of elements assigned to each network edge.

We also release aggregated subzone statistics for each city. Similarly, users can employ the Urbanity package to generate aggregate statistics for any arbitrary geographic boundary.

Urbanity Python package: https://github.com/winstonyym/urbanity.

Local Road Network for 31 local authorities. Extracted from MapRoad Asset Management System. The Road Management Office and Local Authorities provide this information with the understanding that it is not guaranteed to be accurate, correct or complete. The Road Management Office and Local Authorities accept no liability for any loss or damage suffered by those using this data for any purpose.The road infrastructure is the largest asset managed by local authorities in Ireland. It’s efficient management (both day to day and in the long term) is essential to economic activity as the majority of commuting and haulage occurs using it. The 31 local authorities operate, maintain and improve the network of regional and local roads.

Description: Floods are common natural disasters worldwide and pose substantial risks to life, property, food production, and natural resources. Effective measures for flood mitigation and warning are important. Southeast Texas is still at substantial risk of flooding and Lamar University is assisting the region with asset management of a flood sensor network for flooding events. This network provides real-time water stage information. To make these data more useful for flood monitoring and mapping, Lamar University developed a program to measure elevation and coordinates for the various sensor locations. This paper overviews the measurement of the elevation and coordinates of 74 networked flood sensors and various thresholds at critical points used by flood decision-makers for reference at each site. These sensors, in the first phase of this program, were deployed throughout a 7-county region spanning nearly 6000 square miles in Southeast Texas. The latitude and longitude of the sensors, along with their elevations, were determined using survey-grade Global Navigation Satellite System (GNSS) technology. This is an accurate, rapid, and relatively low-cost surveying method. Various Continually Operating Reference Stations (CORS) were examined during post-processing to achieve the most accurate horizontal and vertical results. After differential corrections were applied, accuracies of 0.4 in. (or better) were achieved. Each site's critical points and thresholds were also established using this method. The thresholds, elevations, and positions of these sensors and their surrounding critical points are transmitted to various dashboards on websites. These data are used to aid with decisions related to road closures or modeling efforts by mitigation decision-makers, emergency managers, and the public, including the Texas Department of Transportation, Houston Transtar, the National Weather Service, and the Sabine River Authority of Texas (SRA). This data may also be used in the development of flood hydrological models in Southeast Texas watersheds and sub-basins. This program currently involves the Flood Coordination Study team which is part of the Center for Resiliency at Lamar University in collaboration with various entities such as the U.S. Department of Homeland Security Science and Technology Directorate, the Southeast Texas Flood Control District, and various other regional agencies, municipalities, and industries.

Steps to reproduce: A Trimble GEOX7 Global Navigation Satellite System (GNSS) handheld device, which employs Trimble H-StarTM technology, and a ZIPLEVEL PRO-2000 High Precision Altimeter was used to determine the coordinates and elevations of the sensors and surrounding critical points. Post-processing of the GNSS data used the Trimble GPS Pathfinder Office software. The closest CORS base stations were used for differential corrections and the NAD 1983 (2011) (epoch 2010.00) horizontal datum was used as the geographic coordinate system. Furthermore, orthometric heights were calculated using GEOID 18 which is referenced to the North American Vertical Datum of 1988 (NAVD 88). ArcGIS Pro 3 was used to create a map of the sensors and critical points, as well as a watershed delineation relative to Southeast Texas landmarks. Data were gathered in Southeast Texas watersheds and sub-watersheds in order to monitor and map the elevation and movement of water in the drainages. Vertical and horizontal positions of the 74 flood sensors installed in the first phase of the project and their surrounding critical points, including the node (solar panels, battery, and transmission device), the bottom of the posts that nodes attached (bottom of the node from now on), top of the bank, the bottom of the ditch, the bottom of the bridge's deck, and the center of the road and edges, have been gathered accordingly. Also, the relative elevations between these points are important and were collected.

Networked Audio Products Market Outlook

The global market size for networked audio products was valued at USD 16.5 billion in 2023 and is projected to reach USD 29.3 billion by 2032, growing at a CAGR of 6.5% during the forecast period. This growth is driven by the rising demand for wireless and networked audio solutions across various applications, including residential, commercial, and automotive sectors.

One of the primary growth factors for the networked audio products market is the increasing adoption of wireless connectivity solutions. Consumers are increasingly seeking seamless and wire-free audio experiences, which has propelled the demand for products like wireless speakers, soundbars, and multi-room audio systems. The convenience and flexibility offered by these wireless audio products have led to their widespread adoption in both residential and commercial settings. Technological advancements in wireless connectivity, such as Bluetooth and Wi-Fi, have further enhanced the performance and reliability of these products, contributing to market growth.

Another significant driver of the market is the growing trend of smart homes, where networked audio products play a crucial role in enhancing the overall home automation experience. The integration of voice assistants like Amazon Alexa and Google Assistant with audio devices has transformed how consumers interact with their home entertainment systems. This trend has fueled the demand for networked audio products that can be easily controlled through voice commands and integrated with other smart home devices. Additionally, the increasing disposable income and changing lifestyle preferences of consumers have further driven the adoption of these premium audio solutions.

The commercial sector is also witnessing substantial growth in the adoption of networked audio products. Businesses and organizations are increasingly investing in advanced audio solutions for enhancing customer experiences in retail stores, restaurants, and offices. Networked audio products enable centralized control and distribution of audio content, making them ideal for commercial applications. Additionally, the automotive industry is incorporating networked audio systems to enhance in-car entertainment, providing a more immersive audio experience for passengers. These factors collectively contribute to the expanding market for networked audio products.

Regionally, North America holds a significant share of the networked audio products market, driven by the high adoption rate of advanced audio technologies and the presence of major industry players in the region. However, the Asia Pacific region is expected to witness the highest growth rate during the forecast period, owing to the increasing penetration of smart home technologies and rising consumer disposable income. The growing urbanization and rapid technological advancements in countries like China and India are also contributing to the market growth in this region.

Product Type Analysis

The networked audio products market is segmented by product type into wireless speakers, soundbars, AV receivers, multi-room audio systems, and others. Wireless speakers have emerged as the most popular category, driven by their portability, ease of use, and ability to deliver high-quality audio without the need for wires. These speakers are ideal for both indoor and outdoor use, making them versatile for various applications. The integration of advanced features such as voice control, water resistance, and long battery life further enhances their appeal to consumers.

Soundbars are another significant segment in the networked audio products market. They are designed to provide an enhanced audio experience for television viewing, offering a compact and stylish alternative to traditional home theater systems. Soundbars are equipped with multiple speakers and advanced audio technologies to deliver immersive sound quality. The ease of installation and compatibility with various TV models have made soundbars a popular choice among consumers looking to upgrade their home entertainment systems without the hassle of complex setups.

AV receivers are essential components in home theater systems, serving as the central hub for connecting various audio and video devices. They offer advanced audio processing capabilities and support multiple audio formats, providing a superior audio experience. The growing trend of home theaters and the increasing demand for high-fidelity audio systems have driven the adoption of AV receivers. Additionally, the integration of wireless connec

The UCSD Network Telescope consists of a globally routed, but lightly utilized /9 and /10 network prefix, that is, 1/256th of the whole IPv4 address space. It contains few legitimate hosts; inbound traffic to non-existent machines - so called Internet Background Radiation (IBR) - is unsolicited and results from a wide range of events, including misconfiguration (e.g. mistyping an IP address), scanning of address space by attackers or malware looking for vulnerable targets, backscatter from randomly spoofed denial-of-service attacks, and the automated spread of malware. CAIDA continously captures this anomalous traffic discarding the legitimate traffic packets destined to the few reachable IP addresses in this prefix. We archive and aggregate these data, and provide this valuable resource to network security researchers. This dataset represents raw traffic traces captured by the Telescope instrumentation and made available in near-real time as one-hour long compressed pcap files. We collect more than 3 TB of uncompressed IBR traffic traces data per day. The most recent 14 days of data are stored locally at CAIDA. Once data slides out of this near-real-time window, the pcap files are off-loaded to a tape storage. This historical Telescope data starting from 2008 are available by additional request.

we present the "CTGAN-Enhanced Dataset for UAV Network Intrusion Detection"

Key information about Thailand Information Technology Networked Readiness

• Thailand Information Technology Networked Readiness was reported at 4.201 Score in Dec 2016
• This records an increase from the previous number of 4.049 Score for Dec 2015
• Thailand Information Technology Networked Readiness data is updated yearly, averaging 4.006 Score from Dec 2012 to 2016, with 5 observations
• The data reached an all-time high of 4.201 Score in 2016 and a record low of 3.784 Score in 2012
• Thailand Information Technology Networked Readiness data remains active status in CEIC and is reported by World Economic Forum
• The data is categorized under World Trend Plus’s Information Technology Networked Readiness Index (NRI) (Discontinued) – Table NRI: Overall Index: Emerging and Developing Asia (EMDA)

Network datasets used as examples for network cards.

This dataset accompanies the paper "STREETS: A Novel Camera Network Dataset for Traffic Flow" at Neural Information Processing Systems (NeurIPS) 2019. Included are: *Over four million still images form publicly accessible cameras in Lake County, IL. The images were collected across 2.5 months in 2018 and 2019. *Directed graphs describing the camera network structure in two communities in Lake County. *Documented non-recurring traffic incidents in Lake County coinciding with the 2018 data. *Traffic counts for each day of images in the dataset. These counts track the volume of traffic in each community. *Other annotations and files useful for computer vision systems. Refer to the accompanying "readme.txt" or "readme.pdf" for further details.

Abstract

This dataset and its metadata statement were supplied to the Bioregional Assessment Programme by a third party and are presented here as originally supplied:

The Geofabric Surface Network product provides a set of related feature classes to be used as the basis for production of consistent hydrological surface stream network analysis. This product contains a topographically consistent representation of the (major) surface water features of Australia (excluding external territories). Primarily, these are natural surface hydrology features but the product also contains some man-made features (notably reservoirs and other hydrographic features).

The Geofabric Surface Network product is based upon the input from ANUDEM Derived Streams V1.1.2 (ANUDEM Streams) which is the vectorised version of the nine second ANUDEM derived raster steams product. The product is related to, but distinct from, the stream network contained in the Geofabric Surface Cartography product. The network product represents the flow direction of streams over the surface of the terrain, based on the GEODATA Nine Second Digital Elevation Model (DEM-9S) Version 3. This product is more generalised than the Geofabric Surface Cartography and represents the main channels of the stream, particularly in areas where streams are heavily anabranched or disconnected.

In addition, the stream connectivity represents a stream flow over the terrain, regardless of the presence of a corresponding Geofabric Surface Cartography stream segment. This means that the Geofabric Surface Cartography product may represent a stream as an interrupted or intermittent feature, whereas this product represents the same stream as a continuous connected feature. That is, the path that a stream would take (according to the terrain model) if sufficient water were available for flow. This product is fully topologically correct which means that all the stream segments flow in the correct direction. It also has full connectivity based on the flow of water across a terrain model.

This product contains six feature types including: Waterbody, Network Stream, Network Node, Catchment, Network Connectivity (Upstream) and Network Connectivity (Downstream).

Purpose

This product contains a topographic representation of the (major) surface water features of 'geographic Australia' excluding external territories. It is intended to be used as the basis for production of consistent surface stream network analysis.

Geofabric Surface Network is intended to be used in stream flow tracing operations, using its full topological connection. The product can support the spatial selection of associated hydrological features as inputs for spatial analysis/modelling.

This product is intended to supplement the Geofabric Surface Cartography, Geofabric Surface Catchments and Geofabric Hydrology Reporting Catchments data products. This product is also used to support the definition of the Geofabric Surface Catchments and Geofabric Hydrology Reporting Catchments products and provides a spatial framework for analysis and assessment of streams and their catchments.

Dataset History

This dataset and its metadata statement were supplied to the Bioregional Assessment Programme by a third party and are presented here as originally supplied:

Lineage statement: Geofabric Surface Network is part of a suite of Geofabric products produced by the Australian Bureau of Meteorology. The geometry of this product is largely derived from the ANUDEM Derived Streams V1.1.2 (ANUDEM Streams). It consists of water bodies such as swamps, reservoirs, lakes, etc as derived from AusHydro V1, as well as the stream lines and stream line connectors through these water bodies. The ANUDEM Streams are firstly vectorised to be usable in vector line feature format and are then informed and modified by the coincident locations of the AHGFMappedStream feature class. The features are organised into specific feature class subtypes, based upon both the inputs from the AusHydro V1.7.2 and their behaviour within the AHGF Network Stream relationships. All of the AHGFNetworkStream and AHGFWaterbody features participate in the connected stream flow topology.

This product also contains the AHGFCatchment features that are derived from the National Catchment Boundaries V1.1.4. The AGHFCatchment feature class consist of the lowest level stream flow catchments based upon the inputs from ANUDEM Streams. The catchment boundaries are based upon a single AHGFNetworkStream extent over GEODATA National 9 Second DEM grid. These catchments form the basis of aggregated catchment boundaries, either by Contracted Nodes or by Pfafstetter ID Levels.

All of these features participate in the connected stream flow topology.

Changes at v2.1

! Addition of Beta Monitoring Point Table including 479 ghost nodes

 connected to the network.

- New Water Storages in the WaterBody FC.

Changes at v2.1.1

! Replacement of Beta Monitoring Point Table and inclusion of 3,310

(formerly 479) ghost nodes connected to the stream network.



! 16 New BoM Water Storages attributed in the AHGFWaterBody feature class

and 1 completely new water storage feature added.



- SegnoLink attribute update to fix single catchment feature in Tasmania.



- Correction to spelling of Numeralla river in AHGFMappedStream (formerly

Numaralla).



! Metadata updated adding explanation of AHGFNetworkStream AusHydroEr codes

and revision made to description of DrainID field.



- Fixed a series of NoFlow catchments (small internally draining catchments

not related to a stream segment) in Murray-Darling were incorrectly

attributed as externally draining via the ExtrnlBasn field in

AHGFCatchments.



! Usage of the MergedSink attribute changed from v2.1 (see

HR_Catchments_Technical_Overview.pdf for more info).

Processing steps:

1. ANUDEM Streams dataset is received and loaded into the Geofabric development GIS environment.

2. Feature classes from ANUDEM Streams are recomposed into composited Geofabric Feature Dataset Feature Classes in the Geofabric Maintenance Geodatabase.

3. Re-composited feature classes in the Geofabric Maintenance Geodatabase Feature Dataset are assigned unique Hydro-IDs using ESRI ArcHydro for Surface Water (ArcHydro: 1.4.0.180 and ApFramework: 3.1.0.84).

4. Feature classes from the Geofabric Maintenance Geodatabase Feature Dataset are extracted and reassigned to the Geofabric Surface Network Feature Dataset within the Geofabric Surface Network Geodatabase.

A complete set of data mappings, from input source data to Geofabric Products, is included in the Geofabric Product Guide, Appendices.

Dataset Citation

Bureau of Meteorology (2014) Geofabric Surface Network - V2.1.1. Bioregional Assessment Source Dataset. Viewed 13 March 2019, http://data.bioregionalassessments.gov.au/dataset/d84e51f0-c1c1-4cf9-a23c-591f66be0d40.

The North American Rail Network (NARN) Rail Nodes dataset was created in 2016 and was updated on April 09, 2025 from the Federal Railroad Administration (FRA) and is part of the U.S. Department of Transportation (USDOT)/Bureau of Transportation Statistics (BTS) National Transportation Atlas Database (NTAD). The NARN Rail Nodes dataset is a database of North America's railway system at 1:24,000 or better within the United States. The data set covers all 50 States, the District of Columbia, Mexico, and Canada. The dataset holds topology of the network and provides geographic location information. A data dictionary, or other source of attribute information, is accessible at https://doi.org/10.21949/1529070

Key information about Indonesia Information Technology Networked Readiness

• Indonesia Information Technology Networked Readiness was reported at 4.009 Score in Dec 2016
• This records an increase from the previous number of 3.911 Score for Dec 2015
• Indonesia Information Technology Networked Readiness data is updated yearly, averaging 3.911 Score from Dec 2012 to 2016, with 5 observations
• The data reached an all-time high of 4.041 Score in 2014 and a record low of 3.745 Score in 2012
• Indonesia Information Technology Networked Readiness data remains active status in CEIC and is reported by World Economic Forum
• The data is categorized under World Trend Plus’s Information Technology Networked Readiness Index (NRI) (Discontinued) – Table NRI: Overall Index: Emerging and Developing Asia (EMDA)

The National Highway Planning Network (NHPN) dataset was compiled on May 01, 2014 from the Federal Highway Administration (FHWA) and is part of the U.S. Department of Transportation (USDOT)/Bureau of Transportation Statistics (BTS) National Transportation Atlas Database (NTAD). This dataset is a comprehensive network database of the nation's major highway system. It consists of the nation's highways comprised of Rural Arterials, Urban Principal Arterials and all National Highway System routes. The data set covers the 48 contiguous States plus the District of Columbia, Alaska, Hawaii, and Puerto Rico. The nominal scale of the data set is 1:100,000 with a maximal positional error of 80 meters.

Data Source:National Highway Freight Network, Federal Highway Administration, Office of Management and Operations. Please contact Birat Pandey for any questions related to NHFN or visit the NHFN website at Freight Network.The NHFN includes the following subsystems of roadways: Primary Highway Freight System (PHFS): This is a network of highways identified as the most critical highway portions of the U.S. freight transportation system determined by measurable and objective national data. The network consists of 41,518 centerlines miles, including 37,436 centerline miles of Interstate and 4,082 centerline miles of non-Interstate roads. Other Interstate portions not on the PHFS: These highways consist of the remaining portion of Interstate roads not included in the PHFS. These routes provide important continuity and access to freight transportation facilities. These portions amount to an estimated 9,709 centerline miles of Interstate, nationwide, and will fluctuate with additions and deletions to the Interstate Highway System. Critical Rural Freight Corridors (CRFCs): These are public roads not in an urbanized area which provide access and connection to the PHFS and the Interstate with other important ports, public transportation facilities, or other intermodal freight facilities. Nationwide, there are 5,044 centerline miles designated as CRFCs. Critical Urban Freight Corridors (CUFCs): These are public roads in urbanized areas which provide access and connection to the PHFS and the Interstate with other ports, public transportation facilities, or other intermodal transportation facilities. Nationwide, there are 2,387 centerline miles designated as CUFCs.

The NHFN consists of the PHFS, other Interstate portions not on the PHFS, the CRFCs, and the CUFCs for an estimated total of 58,654 centerline miles.

Predicting the spread of populations across fragmented habitats is vital if we are to manage their persistence in the long term. We applied network theory with a model and an experiment to show that spread rate is jointly defined by the configuration of habitat networks (i.e., the arrangement and length of connections between habitat fragments) and the movement behavior of individuals. We found that population spread rate in the model was well predicted by algebraic connectivity of the habitat network. A multi-generation experiment with the microarthropod Folsomia candida validated this model prediction. Realized habitat connectivity and spread rate were determined by the interaction between dispersal behavior and habitat configuration, such that the network configurations that facilitated the fastest spread changed depending on the shape of the species’ dispersal kernel. Predicting the spread rate of populations in fragmented landscapes requires combining knowledge of species-specific dispersal kernels and the spatial configuration of habitat networks. This information can be used to design landscapes to manage the spread and persistence of species in fragmented habitats.