Most of the farmers lack the necessary knowledge about proper farming and lack proper guidance in many countries. We are dealing with this problem by teaching about farming and climate-friendly farming through electronic devices. Furthermore, soil and land deteriorate due to continuous farming and climate change. We are solving this issue by doing environment & soil testing for suitable crops to maximize the amount of crop production. This challenge displays the lack of proper monitoring and care in most of the cases of farming. We will tackle this problem by doing information feedback every day, month or yearly basis, and other summaries of data. Moreover, this will prepare the necessary data for the next farming season by analyzing previous activities.
Our approach to developing this project:
While tinkering with TheTensorFlow library, we came across a video on YouTube showing us how researchers at PlantVillage of Penn State University and the International Institute of Tropical Agriculture (IITA) are using ML and TensorFlow to help farmers detect diseases in Cassava plants. From that, we were impressed and thought we could make it even better by implementing IoT and adding other features making it possible for anyone to grow their own food from anywhere. We designed the solution and after extensive RnD, we finally had a worthy result. Not only we could use our product in growing vegetables but also use it in any sort of agricultural activity like - vertical farming, aquaponics (already tested and it works), hydroponics (also tested and works), etc.
I had a little difficulty getting a dataset of leaves of diseased plants. I initially had to write a web scraper with Rahat Shovo to scrape ecosia.org until I found this dataset on crowdAI from the PlantVillage Disease Classification Challenge. I finally found this data on Github from spMohanty and settled on it.