Machine Learning for Smart Agriculture

In recent years, the field of agriculture is experiencing a significant transformation due to technological advancements. One such technology that holds great promise for revolutionizing the agricultural landscape is machine learning. By leveraging the power of machine learning and deep learning models, we aim to develop a cutting-edge system for monitoring the health of plants efficiently and autonomously.

The primary objective of our project is to build an efficient and autonomous plant monitoring system that operates at the edge directly within the agricultural field. By utilizing low-power consumption techniques, we aim to develop an edge system that can continuously monitor the health of plants, detecting any anomalies or signs of distress at an early stage. This real-time monitoring capability can help farmers promptly identify and address plant health issues, leading to improved crop yields and reduced losses.

The core component of our system is the analysis of stem impedance data, which provides valuable insights into the physiological status of plants. By studying the electrical conductivity within the stem, we can gather information about water uptake, nutrient absorption, and overall plant health. Combined with data from environmental sensors, such as temperature, humidity, and light intensity, our machine-learning models can learn patterns and correlations, enabling accurate and timely plant health assessments.

Our project aims to address several critical challenges in developing this system. These challenges include data preprocessing, feature extraction, model training, and real-time deployment on edge devices with limited computational resources. By overcoming these obstacles, we strive to create a practical and scalable solution that farmers and agricultural professionals can easily adopt.

Keywords: Machine Learning, Edge Computing, Precision Agriculture, Smart Decision Making, Plants Health Monitoring

References:

• • Barezzi, M., Cum, F., Garlando, U., Martina, M,. and Demarchi, D., “On the impact of the stem electrical impedance in neural network algorithms for plant monitoring applications,”2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), Perugia, Italy, 2022, pp. 131-135, doi: 1109/MetroAgriFor55389.2022.9965011.
  • Cum, F., Calvo, S., Demarchi, D., and Garlando, U., “Machine Learning Models Comparison for Water Stress Detection based on Stem Electrical Impedance Measurements”. ACCEPTED