ROBOTIC DETECTION OF HERBICIDES & TOXINS IN GE CROP FIELDS
Project Goal
Development of an array of biochemical sensors for accurate and selective detection of herbicides, glyphosate & atrazine, and Cry toxins.
Realization of a robotic platform for detection and monitoring of soil health and water quality in real-time over targeted regions within a GE crop field.
Scientific Background
Global agriculture faces the dual challenge of feeding a growing population while minimizing environmental harm, with genetically engineered (GE) crops, like those resistant to pests or herbicides, becoming increasingly prevalent.
Despite benefits such as higher yields and lower costs, concerns persist about the environmental impact of GE crops, particularly regarding pesticide usage, with millions of tons sprayed annually.
Pesticide contamination, notably from herbicides like atrazine and glyphosate, poses risks to both human health and ecosystems, with long-term exposure potentially causing acute toxicity and other health hazards.
Transgenic crops, like those containing Bacillus thuringiensis (Bt) genes, raise additional concerns such as harm to non-target species and the development of insect resistance, emphasizing the importance of monitoring toxin spread in soil, water, and organisms.
Key Innovations
Development of specific biochemical sensors to detect toxins like Glyphosate, Atrazine, and Cry1Ab protein in soil and water.
A novel approach that combines robotics, artificial intelligence (AI), and the Internet of Things (IoT) to create a platform for real-time monitoring of soil health and water quality in GE crop fields.
Development of reinforcement learning algorithms to improve the navigation skills and path planning of the robot within the field.
Implementation of convolutional neural networks (CNNs) to analyze data from the biochemical sensors and extract relevant features for accurate detection of toxins.
Utilization of recurrent neural networks (RNNs) to analyze time-series data from the sensors, allowing monitoring of soil health dynamics over time.
The implementation of Edge-AI directly on the robotic platform, enables real-time analysis and decision-making without relying on external computing resources.
