Forests cover 30 percent of the Earth’s surface, are an important source for clean air and water, and are crucial for combating climate change with their ability to absorb and store carbon from the atmosphere. Wildfires threaten the world’s largest carbon sink. Fire detection can provide early warning and the location of fires so that loss of trees can be addressed immediately. Predicting fires with AI is even better.
IoT + AI Blueprint:
Assemble the collection of components displayed below to address the use case of reducing forest fires.
Sensor(s)
Smoke: Detect Smoke
Cameras: Computer Vision to Visually Detect Flames + Infrared to Identify Hotspots Before Flames are Visible
Humidity: Detect Fire Favorable, Low Humidity Conditions
Soil Moisture: Detect Fire Favorable Dry Soil Conditions
Wind: High Winds Facilitate Dangerous Fire Conditions + Determine Fire Direction
LoRa: Create Low Bandwidth Coverage Needed to Reach Internet Access
Cellular: If Coverage Available and Cost-Effective for High Bandwidth Scenarios
Satellite: When No Terrestrial Coverage Options are Available for Medium Bandwidth Scenarios
Digital Twin Modeling
Collection of Trees in Protected Forest Areas
Logging Roads
Data Processing + Storage Location(s)
Edge: In Forest
Cloud: Filtered Data Relayed from Edge to Monitor Broader Areas of Forests
Streaming Analytics
Compare Sensor Data Values to Defined Setpoints, KPI Value Ranges and Thresholds
Filter out Duplicate Sensor Data Value Readings
Automation
Green KPI: No Action
Yellow KPI: Warn Notification for Awareness When Sensor Values are Trending Towards Fire Conditions
Red KPI: Alert Notification for Forest Rangers or Fire Fighters to take Action When Fire Conditions are Present
People
Deploy and Maintain Solution
SMEs Define KPIs and Actions
Forest Rangers and Fire Fighters
Security
Uniquely Identify Each Device
TLS 1.3 Encryption for Data in Transit
Encrypt Data at Rest
Validate Device Messages to Ensure they use Expected Data Format
Rotate Security Tokens
Limit IP Address Ranges
AI Anomaly Detection
Zero Trust: Reauthenticate Device Messages Through Every Step of the System
Artificial Intelligence
Computer Vision to Perform Object Detection to Detect Flames and Hotspots
Machine Learning Time Series Forecasting Model to Predict Future Occurrence of Fire Conditions
IoT Platform
Device SDK Captures Sensor Data from Physical Twin and Securely Sends it as a JSON Payload to the IoT Platform Along with a Unique Identifier and Security Token
IoT Platform Captures, Authenticates, and Saves Incoming Device + Sensor Data to a Message Queue
Background Process Takes Queued Data and Hydrates the Digital Twin by Saving it to a Database Table that Mimics the Structure of the Physical Twin
AI Model is Trained and Retrained with Digital Twin Dataset of Current and Historical Data Where Properties of Twin are Mapped to ML Features
Hot Path Data is Sent to Streaming Analytics to Facilitate Real Time Alerting and Automation
Same Hot Path Data is Also Sent to AI Model for Inferencing to Predict Future Occurrences
Rob is a writer, teacher, speaker, world traveller and undersea explorer. He's also a thought leader in the areas of enterprise mobility and the Internet of Things.
