Planto

Inspiration

Planto has been developed for the farming sector. In India, farmers are major stakeholders, and almost 70% of the population is involved in the farming sector. Having such a huge emphasis on the country, more attention should be paid to this sector's development and growth.

Target Audience

This app mainly targets the farmers whether large scale or small scale. Farming holds a significant share in the country's GDP, and even some small mistakes can impact the economy. The main purpose of this application is to help the farmers deal with certain issues that can play a major role in destroying the whole crop which makes it difficult for farmers to earn a living. These issues can be handled on the ground level and can save the farmers from losses and can help contribute to an even larger share in the GDP of the nation.

What it does

Plant Disease Prediction: Our app is user-friendly and has been built keeping in mind the difficulties that the farmers face and provides them the solution as well. Planto focuses on the condition (diseases they may carry) of leaves. It scans the leaves and informs the farmer about any discrepancy that may arise in a long run and help them save their plantation from getting destroyed.

Disease Information and Management: Our app also guides them and shows the remedies or methods that should be adopted in order to deal with the situation at hand. It also states the symptoms that help farmers to understand more about the problem and what all can be done to protect their plants. It gives them a heads up about it and highlights the precautionary steps that the farmer can consider to prevent the disease altogether.

How we built it

Planto is delivered as an android application built using Flutter (Dart). The remedies and disease management data are stored in firebase. The deep learning model was built in jupyter notebook using python and extracted as a .tflite file, which was then embedded in the flutter application.

Challenges we ran into

It was our first time implementing an image classification model. Within two hours, we researched and grasped the concepts and technical notions required to implement the same.
The next challenge was to connect that model to our flutter application. Browsing through multiple developer's documents and resources, we pushed through this problem efficiently.

Accomplishments that we're proud of

Embedding Image-Based Deep Learning Model into our flutter application.
Collecting and organizing disease management data in firebase via various sources.
Aesthetic UI/UX built in just 1 hour.

What we learned

Deep Learning
Embedding Machine Learning Models as .tflite files.
Fetching Data from Firebase (Firestore Storage).

What's next for Planto

As an immediate next step, we plan to implement a multilingual chatbot for farmers to interact and discuss their problems with.
To increment the usage of our application and feasibility for farmers, we plan to add shopping functionality that will help them to order all the fertilizers and seeds required.
Developing awareness articles which will discuss the condition of the soil, before the plantation takes place.
The final step in the near future would be to provide farmers and other agricultural practitioners a timeline and best practices for farming.