A small-scale intelligent farming system using low-cost Internet of Agro Things (IoAT) sensors and interactive cloud-based big data analytics to monitor and evaluate crops’ performance in real-time.
The low-cost agricultural Internet of Things (IoT) sensors will be installed in different agricultural zones to collect farm-level datasets. The dashboard will collect big data and stream the results using a big data analytics platform that the Project will develop. The beneficiaries of this deliverable will be small farmers and researchers in the country who will utilize the collected dataset in their research to develop agricultural approaches for enhancing productivity.
A big data model to predict farm-level yield using low-cost agricultural Internet of Agro Things (IoT) sensor data by enhancing district-level resolution yield data to farm-level resolution yield data using Generative Adversarial Networks (GANs).
The project will use Generative Adversarial Networks (GANs) to augment low-resolution district-level data with high-resolution farm-level data. The developed model will have the capacity to predict farm-level yield two months before harvest.
A reliable and reusable ML-driven crop yield prediction model using historical meteorological data, satellite data, and proximal sensor data to enhance crop yield predictions in Tanzania.