M5Stack's M5Stamp-Pico Powers This Smart, Wireless Color-Based Plant Health Monitor
Built for "a few tens of dollars," this smart sensor in its 3D-printed housing could help deliver better data on plant health and growth.
Researchers from the Graduate School of Life Sciences and Department of Electronic Engineering at Tohoku University have developed a low-cost wireless plant sensor, costing "a few tens of dollars" and featuring an M5Stack M5Stamp-Pico at its heart, which they say could deliver better agricultural monitoring than current approaches.
"The traditional [monitoring] methods may work well for some purposes, but they are difficult to operate and quite expensive," claims first and co-corresponding author Kaori Kohzuma of the problem the team set out to solve. "In order to continuously monitor small changes, we needed a new solution. This affordable sensor is a promising tool for accurately monitoring plant health and stress through leaf color and light reflection data. Its low cost makes it possible to place multiple sensors across various locations, creating a network for simultaneous monitoring in many spots."
"Smart agriculture is a huge time-saver," adds co-corresponding author Ko-ichiro Miyamoto. "Farmers don't have time to manually check every single plant. This sensor is able to provide fine-tuned readings for what's going on in real time. Then, they can react accordingly to areas where plants are experiencing high levels of stress."
The team's two-part sensor is built from largely off-the-shelf parts: the sensor head, which attaches to the underside of leaves in order to avoid blocking sunlight, is based on the DFRobot Gravity OSRAM AS7341 11-channel visible light sensor, connected to an M5Stack M5Stamp-Pico Espressif ESP32-PICO-D4 microcontroller board, programmed using the Arduino IDE, through a custom carrier board. Everything is housed in 3D-printed cases, sealed against the weather with simple silicone sealant, and powered by CR2 lithium batteries β good for more than a month of monitoring, the researchers found.
Despite its low cost β "a few tens of dollars" per unit, the researchers say β the sensor system performed well when compared to a far higher-cost commercial spectrometer. In field tests the sensors were used to track the leaves of a birch tree, tracking its chlorophyll levels and response to sunlight intensity over time.
The team's work has been published in the journal Sensing and Bio-Sensing Research under open-access terms.