JalOS
An AI-driven predictive water resource management platform that uses demand forecasting models and water-supply endurance estimation to shift water resource monitoring from passive observation to proactive planning, targeting residential property management scenarios.
Timeline (last 90 days)
JalOS is an AI-driven predictive water resource management platform developed by Jai Singh Bisht and Tanishka Rawat during the 'Bharat Builds Tour: Environmental Hacks' hackathon organized by WeBuildDevs.
JalOS consists of three main components: a backend service, an admin portal, and a resident mobile client.
The JalOS backend uses Python and FastAPI to provide API interfaces and host water resource management logic, including water tank reading processing, inventory management, water supply endurance calculation, and predictive model integration.
The JalOS management portal is built with React and TypeScript, while the resident-facing side is developed using Flutter.
JalOS employs a Ridge Regression model to estimate future water demand based on structured time-series data.
JalOS's technology stack uses Docker for application packaging, Terraform for infrastructure as code, and GitHub Actions for CI/CD, deployed on Amazon Web Services.
On the AWS side, JalOS uses EC2 for hosting, IAM for access control, Systems Manager Parameter Store for configuration management, S3 for storing deployment artifacts and model files, CloudWatch for log collection, and Systems Manager Run Command for executing deployments.
JalOS's GitHub Actions workflow obtains short-lived AWS temporary credentials via OpenID Connect (OIDC) rather than storing long-term access keys.
The current JalOS prototype uses synthetic water demand data, and the prediction model has only been evaluated on a held-out synthetic test set and has not yet been validated with real residential water meter readings and sensor data.
JalOS's anomaly analysis metrics can support early inspection but cannot independently confirm whether a leak or equipment failure exists.
1 more timeline events
All Facts (11)
JalOS is an AI-driven predictive water resource management platform developed by Jai Singh Bisht and Tanishka Rawat during the 'Bharat Builds Tour: Environmental Hacks' hackathon organized by WeBuildDevs.
50%UnverifiedJalOS consists of three main components: a backend service, an admin portal, and a resident mobile client.
50%UnverifiedThe JalOS backend uses Python and FastAPI to provide API interfaces and host water resource management logic, including water tank reading processing, inventory management, water supply endurance calculation, and predictive model integration.
50%UnverifiedThe JalOS management portal is built with React and TypeScript, while the resident-facing side is developed using Flutter.
50%UnverifiedJalOS employs a Ridge Regression model to estimate future water demand based on structured time-series data.
50%UnverifiedJalOS's technology stack uses Docker for application packaging, Terraform for infrastructure as code, and GitHub Actions for CI/CD, deployed on Amazon Web Services.
50%UnverifiedOn the AWS side, JalOS uses EC2 for hosting, IAM for access control, Systems Manager Parameter Store for configuration management, S3 for storing deployment artifacts and model files, CloudWatch for log collection, and Systems Manager Run Command for executing deployments.
50%UnverifiedJalOS's GitHub Actions workflow obtains short-lived AWS temporary credentials via OpenID Connect (OIDC) rather than storing long-term access keys.
50%UnverifiedThe current JalOS prototype uses synthetic water demand data, and the prediction model has only been evaluated on a held-out synthetic test set and has not yet been validated with real residential water meter readings and sensor data.
50%UnverifiedJalOS's anomaly analysis metrics can support early inspection but cannot independently confirm whether a leak or equipment failure exists.
50%UnverifiedJalOS's water volume endurance estimation feature estimates how long the available water supply can last before reaching a critical reserve or being completely exhausted, based on expected consumption.
50%