2 datasets found
  1. Water Leak Dataset

    • kaggle.com
    Updated Feb 12, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Ziya (2025). Water Leak Dataset [Dataset]. https://www.kaggle.com/datasets/ziya07/water-leak-dataset/discussion
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Feb 12, 2025
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    Ziya
    License

    https://creativecommons.org/publicdomain/zero/1.0/https://creativecommons.org/publicdomain/zero/1.0/

    Description

    📌 Overview This dataset is designed for water loss reduction and leak detection in urban water distribution networks. It includes time-series data from IoT sensors monitoring pressure, flow rate, and leakage events in a water pipeline system.

    📂 Dataset Features Column Name Data Type Description Timestamp datetime Time of measurement (HH:MM:SS) Pressure (bar) float Measured water pressure in the pipeline (in bars) Flow Rate (L/s) float Water flow rate in liters per second Temperature (°C) float Water temperature recorded by sensors Leak Status binary 0 = No Leak, 1 = Leak Detected Burst Status binary 0 = No Burst, 1 = Burst Detected Sensor ID int Unique identifier for each sensor Pipe Section string Section of the pipeline being monitored Anomaly Score float AutoEncoder-based anomaly detection score Optimization Iteration int Number of White Shark Optimization iterations 📊 Data Collection Data is collected every 5 seconds using IoT-enabled pressure loggers and flow meters deployed in an urban water distribution system. Leak/Burst events are labeled using historical maintenance reports and sensor threshold breaches. The Anomaly Score is generated from AutoEncoder models trained on normal operation data.

  2. Shoreline Construction Lines Dataset

    • kaggle.com
    Updated Dec 18, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    The Devastator (2023). Shoreline Construction Lines Dataset [Dataset]. https://www.kaggle.com/datasets/thedevastator/shoreline-construction-lines-dataset
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Dec 18, 2023
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    The Devastator
    Description

    Shoreline Construction Lines Dataset

    Mapping of Shoreline Construction Lines

    By Homeland Infrastructure Foundation [source]

    About this dataset

    Within this dataset, users can find numerous attributes that provide insight into various aspects of shoreline construction lines. The Category_o field categorizes these structures based on certain characteristics or purposes they serve. Additionally, each object in the dataset possesses a unique name or identifier represented by the Object_Nam column.

    Another crucial piece of information captured in this dataset is the status of each shoreline construction line. The Status field indicates whether a particular structure is currently active or inactive. This helps users understand if it still serves its intended purpose or has been decommissioned.

    Furthermore, the dataset includes data pertaining to multiple water levels associated with different shoreline construction lines. This information can be found in the Water_Leve column and provides relevant context for understanding how these artificial coastlines interact with various water bodies.

    To aid cartographic representations and proper utilization of this data source for mapping purposes at different scales, there is also an attribute called Scale_Mini. This value denotes the minimum scale necessary to visualize a specific shoreline construction line accurately.

    Data sources are important for reproducibility and quality assurance purposes in any GIS analysis project; hence identifying who provided and contributed to collecting this data can be critical in assessing its reliability. In this regard, individuals or organizations responsible for providing source data are specified in the column labeled Source_Ind.

    Accompanying descriptive information about each source used to create these shoreline constructions lines can be found in the Source_D_1 field. This supplemental information provides additional context and details about the data's origin or collection methodology.

    The dataset also includes a numerical attribute called SHAPE_Leng, representing the length of each shoreline construction line. This information complements the geographic and spatial attributes associated with these structures.

    How to use the dataset

    • Understanding the Categories:

      • The Category_o column classifies each shoreline construction line into different categories. This can range from seawalls and breakwaters to jetties and groins.
      • Use this information to identify specific types of shoreline constructions based on your analysis needs.
    • Identifying Specific Objects:

      • The Object_Nam column provides unique names or identifiers for each shoreline construction line.
      • These identifiers help differentiate between different segments of construction lines in a region.
    • Determining Status:

      • The Status column indicates whether a shoreline construction line is active or inactive.
      • Active constructions are still in use and may be actively maintained or monitored.
      • Inactive constructions are no longer operational or may have been demolished.
    • Analyzing Water Levels:

      • The Water_Leve column describes the water level at which each shoreline construction line is located.
      • Different levels may impact the suitability or effectiveness of these structures based on tidal changes or flood zones.
    • Exploring Additional Information:

      • The Informatio column contains additional details about each shoreline construction line.
      • This can include various attributes such as materials used, design specifications, ownership details, etc.
    • Determining Minimum Visible Scale:
      -- The Scale_Mini column specifies the minimum scale at which you can observe the coastline's man-made structures clearly.

    • Verifying Data Sources: -- In order to understand data reliability and credibility for further analysis,Source_Ind, Source_D_1, SHAPE_Leng,and Source_Dat columns provide information about the individual or organization that provided the source data and length, and date of the source data used to create the shoreline construction lines.

    Utilize this dataset to perform various analyses related to shorelines, coastal developments, navigational channels, and impacts of man-made structures on marine ecosystems. The combination of categories, object names, status, water levels, additional information, minimum visible scale and reliable source information offers a comprehensive understanding of shoreline constructions across different regions.

    Remember to refer back to the dataset documentation for any specific deta...

  3. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Ziya (2025). Water Leak Dataset [Dataset]. https://www.kaggle.com/datasets/ziya07/water-leak-dataset/discussion
Organization logo

Water Leak Dataset

Developing AI-driven solutions for smart water management!

Explore at:
CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
Dataset updated
Feb 12, 2025
Dataset provided by
Kagglehttp://kaggle.com/
Authors
Ziya
License

https://creativecommons.org/publicdomain/zero/1.0/https://creativecommons.org/publicdomain/zero/1.0/

Description

📌 Overview This dataset is designed for water loss reduction and leak detection in urban water distribution networks. It includes time-series data from IoT sensors monitoring pressure, flow rate, and leakage events in a water pipeline system.

📂 Dataset Features Column Name Data Type Description Timestamp datetime Time of measurement (HH:MM:SS) Pressure (bar) float Measured water pressure in the pipeline (in bars) Flow Rate (L/s) float Water flow rate in liters per second Temperature (°C) float Water temperature recorded by sensors Leak Status binary 0 = No Leak, 1 = Leak Detected Burst Status binary 0 = No Burst, 1 = Burst Detected Sensor ID int Unique identifier for each sensor Pipe Section string Section of the pipeline being monitored Anomaly Score float AutoEncoder-based anomaly detection score Optimization Iteration int Number of White Shark Optimization iterations 📊 Data Collection Data is collected every 5 seconds using IoT-enabled pressure loggers and flow meters deployed in an urban water distribution system. Leak/Burst events are labeled using historical maintenance reports and sensor threshold breaches. The Anomaly Score is generated from AutoEncoder models trained on normal operation data.

Search
Clear search
Close search
Google apps
Main menu