DecodeX
Home/Problem Statements/SIH26073
All 226 Statements
SIH26073SoftwareDisaster Management
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

AI/ML-Based Intelligent Anomaly Detection for Automatic Weather Stations (AWS)

Ministry / Organization: Ministry of Earth Sciences (MoES)
Department: India Meteorological Department
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
7/10
36h Hackathon Viability
9/10
Step 0 • Zero-Jargon Layman Summary

“Weather stations often send wrong data because of broken sensors or bad connections, leading to inaccurate forecasts. This project asks you to build an AI that can automatically spot these fake or faulty readings in real-time and fix them so weather reports remain reliable.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An intelligent software system that monitors live data streams from weather sensors, flags errors using AI, explains why the error happened, and suggests corrected values.

Step 2

WHO IS IT FOR?

The India Meteorological Department (IMD) and Ministry of Earth Sciences (MoES) are the primary users; beneficiaries include farmers, aviation authorities, and disaster management teams.

Step 3

WHY DOES IT EXIST?

Traditional systems rely on simple 'if-then' rules that fail when weather patterns change naturally. This creates 'false alarms' or misses actual sensor failures, leading to poor decision-making during critical weather events.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

Time-series data streams containing Temperature, Pressure, and Humidity values from AWS sensors.

02 • Processing & AI Core

Multivariate anomaly detection using LSTMs or Transformers, SHAP-based explainability, and spatial correlation analysis with neighboring stations.

03 • Actionable Deliverables

Real-time alerts, sensor health dashboards, root-cause classification (e.g., 'Sensor Drift' vs 'Extreme Weather'), and imputed data values.

Step 5

CONSTRAINTS

  • Must run on low-power edge hardware (ESP32/Raspberry Pi).
  • Must distinguish between a genuine heatwave and a faulty sensor.
  • Must operate with low latency for real-time disaster response.
  • Must handle missing data packets due to poor network connectivity.
Step 6

JURY METRICS

  • F1-Score (balance of precision and recall).
  • Inference latency (milliseconds per data point).
  • Mean Absolute Error (MAE) of imputed values.
  • Explainability score (how accurately the model identifies the 'why').
Step 7

CORE BOTTLENECK

Distinguishing between a 'rare but real' extreme weather event (e.g., a sudden pressure drop in a cyclone) and a sensor malfunction.

Why You Should Choose This PS (Pros)

  • High social impact with clear, measurable outcomes.
  • Strong alignment with national disaster management goals.
  • Allows for a 'Wow' factor through live visualization and Explainable AI.

Challenges & Risks to Watch (Cons)

  • Requires high-quality synthetic data generation if real-world anomaly datasets are sparse.
  • Risk of over-engineering the model beyond edge device capabilities.
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
React.jsRecharts for time-series visualizationTailwind CSS
Backend & APIs
FastAPIPython (Pandas/NumPy)MQTT for sensor data ingestion
AI / ML & Models
Isolation Forest / Local Outlier Factor for baselineLSTM-Autoencoders for sequence modelingSHAP for explainability
Database & Cloud
InfluxDB (Time-series optimized)Redis for real-time caching

Killer Features to Impress the SIH Jury

Spatial Consensus Engine: Compare a station's data with its 3 nearest neighbors to validate anomalies.
Predictive Maintenance: Use degradation trends to alert technicians before a sensor fails completely.
Self-Healing Data: Automatically replace faulty readings with AI-predicted values to keep downstream forecasts running.
View Official SIH 2026 Portal Raw Text
▼
•Title SkyGuard AI: Intelligent Real-Time Anomaly Detection System for Temperature, Pressure, and Humidity Sensors in Automatic Weather Stations
•Background Automatic Weather Stations (AWS) are critical components of modern meteorological observation networks. These stations continuously monitor atmospheric parameters and provide real-time data for weather forecasting, climate monitoring, disaster management, aviation, agriculture, and scientific research.However, AWS observations often contain anomalies caused by sensor malfunction,communication failures, calibration drift, power fluctuations, harsh environmental conditions, and data corruption.Erroneous observations can significantly impact weather forecasting accuracy and decision-making systems. Traditional threshold-based quality control methods are often insufficient for identifying complex or hidden anomalies in meteorological data streams.
•Problem Statement Develop an AI/ML-based intelligent anomaly detection system capable of automatically identifying abnormal, inconsistent, or faulty observations from Automatic Weather Stations in real time using only the following parameters:
•Temperature (°C)
•Atmospheric Pressure (hPa)
•Relative Humidity (%)

The system should distinguish between genuine meteorological events and sensor/data anomalies while minimizing false alarms and enabling scalable deployment across large weather observation networks.

•Objectives
•Detect anomalies in real-time AWS data streams.
•Identify sensor faults, spikes, frozen values, and communication errors.
•Learn normal temporal and seasonal patterns of temperature, pressure, and humidity.
•Perform multivariate consistency analysis among atmospheric parameters.
•Provide confidence scores and explainable AI-based reasoning for detected anomalies.
•Predict possible sensor degradation and maintenance requirements.
•Optionally suggest corrected/imputed values for anomalous observations.
•Expected Inputs Participants may use historical AWS datasets, simulated anomalies, or streaming sensor data containing the following meteorological parameters:

Parameter- Unit Temperature

-°C Atmospheric Pressure
-hPa Relative Humidity
-%
•Expected Outputs
•Real-time anomaly alerts
•Severity and confidence scores
•Root-cause classification
•Visualization dashboard
•Sensor health status
•Corrected data estimation (optional)
•Suggested Technologies
•Explainable AI (SHAP/LIME) (Preferable)
•Edge AI for low-power deployment on ESP32
•Evaluation Criteria (To be evaluated in anomaly injected data)

Criteria

-Weightage Innovation & Novelty
-25% Detection Accuracy
-20% Real-Time Capability
-15% Explainability
-10% Scalability
-10% Practical Deployability
-10% Visualization/UI
-5% Energy Efficiency
-5%
•Example Use Case An AWS suddenly reports a temperature of 55°C with extremely high humidity and abnormal pressure variation while neighboring stations show normal conditions. The AI system should analyze temporal and spatial consistency, identify the reading as a probable sensor anomaly, generate an alert, and suggest corrective action.
•Grand Challenge Can AI build a self-aware and self-healing weather observation network capable of delivering trustworthy atmospheric data under all environmental conditions?
•Output:

Fully executable code with example usage and a document explaining various use cases