Lead Mentor: Dr. Mehdi Sookhak

Project Background: The emerging IoT brings new opportunities to empower next-generation agriculture. IoT can significantly extend the agricultural workforce with minimum cost and human involvement while maintaining excellent performance.

Project Description: We will implement a small-scale embedded IoT network consisting of multiple low-power embedded IoT devices. Each embedded IoT device will be equipped with multiple environmental sensors (temperature, humidity, etc.), a microcontroller unit, and a transceiver to enable sensing, processing, and communication. Due to long-term cost, sustainability, and environmental concerns, we will power the devices with energy harvesters that scavenge ambient energy from solar, wind, and heat.

Student Research Activities:

1) Build up an energy harvesting powered IoT embedded system with off-the-shelf electronic components.

2) Design smart sensing algorithms for the equipped sensors.

3) Design and deploy data preprocessing algorithms for sensor data on the microcontroller.

4) Enable wireless delivery of preprocessed data to the IoT edge server for further analysis.

Lead Mentor: Dr. Bhandari

Background: Advances in analyzing UAS remote sensing images have contributed to improving our understanding of crop growth and development and yield predictions by the ability to collect high spatial-temporal data on plant morphological traits. However, ground-truth data collection, a key component in UAS applications, is tedious, laborious, and expensive. Automated systems equipped with IoT technology have shown the potential to gather high quality real-time data related to field conditions continuously. We envision that the integration of UAS with a ground-based IoT system will enhance our capability on understanding crop growth and developing management practices.

Project Description: We will investigate challenges and their solutions in the combination of IoT and UAS for predicting crop yield. The IoT sensors will collect site-specific field conditions (for example soil moisture, canopy temperature, air temperature, and relative humidity). The UAS will gather data on canopy height, canopy cover, and vegetation indices. We will feed data from both platforms into mechanistic crop growth models to assess site-specific crop management practices and predict crop yield. This will help students learn the data integration approach from multiple devices, and we can demonstrate how advanced tools and techniques can be used to better understand crop growth and manage them efficiently and effectively.

Student Research Activities:

1) Develop a workflow combining IoT and UAS data for predicting crop yield.

2) Process continuous and real-time field condition data from IoT sensors.

3) Link the IoT and UAS data to crop growth models for crop growth and yield simulations.

Lead Mentor: Dr. Huang

Background: A real-time geo-visualization and analytics platform incorporates data collection, modeling, and visualization. This platform is critical for applying the IoT in agriculture but has not received much attention.

Project Description: We will use ArcGIS Enterprise to build a platform on the ArcGIS GeoEvent Server to process the continuous real-time data collected from IoT sensors from Project #1. Further, we will design and build a spatial database to store and manage both sensors and UAS data and develop geospatial analytical tools to analyze and visualize the results from Project #2. In addition, we will leverage ArcGIS Dashboards to create geospatial dashboards to monitor and track farm field conditions as well as crop growth by integrating sensors and UAS from project #2.

Student Research Activities:

1) Connect IoT systems to the GeoEvent Server for ingesting sensor data.

2) Create GeoEvent Services to analyze the sensor data in real-time.

3) Implement a geospatial database to store and manage sensor and UAS data.

4) Build an analytics dashboard that visualizes, monitors, and tracks farm field conditions and crop growth.

Lead Mentor: Dr. Mcginty

Background: A key goal of the land grant university system is to provide educational outreach to stakeholders. Texas A&M AgriLife Extension Service is tasked with bringing science-based information and solutions to landowners and managers across the state through its network of 250 county offices.

Project Description: During the spring and summer, county extension agents (CEA’s) provide educational programs and conduct result demonstrations in various row crops in south Texas. Topics of these programs and demonstrations are crop variety selection, pest management, and general crop management.

Student Research Activities: Students will spend time with local CEA’s as they conduct onfarm result demonstrations in cotton, corn, and grain sorghum and learn how these demonstrations help to improve the sustainability and profitability of local producers. Students will also participate in educational programs where they will have the opportunity to present data from Projects 1-3 to local producers.