Environment

Predicting extreme weather temperatures

Predict the next day's maximum temperature to better prepare for potential disasters.

Predicting extreme weather temperatures

Environment

NanoEdge AI Studio

Context awareness

Thermal sensor

Welcome to the forefront of extreme weather temperature prediction, where artificial Intelligence (AI) takes center stage, delivering unparalleled accuracy and insights. Extreme weather events, such as heatwaves, cold spells, and storms, have far-reaching consequences on human lives, infrastructure and ecosystems.

By harnessing the potential of AI, we can now unlock the ability to forecast with an unprecedented level of precision and advance notice to prepare, adapt and mitigate risks associated with several weather events or to optimize business operations.

Approach

This use case is based on the "Extreme-Weather Temperature Prediction" dataset from Kaggle.
The goal was to predict the next day's maximum air temperature using 21 values including the current day's min and max temperature, latitude, longitude, elevation, slope, and solar radiation.
We used NanoEdge AI Studio to create an Extrapolation project based on these inputs that could achieve this goal.

Sensor

Temperature sensors and generic sensors.

Data

Extrapolation targets Next day maximum air temperature
Signal length 21 (multi sensors)
Data rate Every day

Results

Extrapolation:
90.18% accuracy, 0.4 Kbytes of RAM, 3.6 Kbytes of Flash memory

Model created with

NanoEdge AI Studio

Model created with

Compatible with

Any STM32 MCU

Compatible with

Resources

Model created with NanoEdge AI Studio

A free AutoML software for adding AI to embedded projects, guiding users step by step to easily find the optimal AI model for their requirements.

Model created with NanoEdge AI Studio

Compatible with Any STM32 MCU

The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.

Compatible with Any STM32 MCU

You also might be interested by

Environment | Agriculture

Plant leaf disease identification

Image classification on high-performance MCU. MobileNet 0.25 model from STM32 model zoo.

Environment | Agriculture

Transfer learning applied to flower recognition 

Image classification on high-performance MCU. MobileNetV2 alpha 0.35 model from STM32 model zoo.

Environment | Agriculture

Transfer learning applied to forest fire detection 

Image classification on high-perf MCU.