IOT / MACHINE LEARNING · September – November 2025
PICSListen before watering.
Predictive irrigation control connecting the physical world to data. Validated at FEMECI Sinaloa 2025.
PythonMachine LearningIoT
VERIFIABLE EVIDENCE · OCTOBER 2026
- FEMECI Sinaloa 2025
- Basic Sciences category ↗
- Prototype
- Sensors, regression model and actuators
The problem
Fixed irrigation schedules do not respond to changes in crop moisture and weather.
My contribution
Development of a system integrating sensors, data processing and intelligent control for agricultural environments.
How it works
- Sensors
- Environmental data
- Predictive model
- Irrigation control
Validated academic project
A system that integrates sensors, regression models, IoT telemetry and actuator control to estimate soil moisture needs.
Validated at FEMECI Sinaloa 2025, Basic Sciences category. The demo uses a fixed moisture threshold; it does not run the project's predictive model.
Design decisions
- Connect data from the physical environment with control decisions.
- Separate the model's estimate from actuator activation.
Facing a similar problem?
We can talk through how you work today, define the scope and find a starting point.
Tell me your idea ↗