The problem CULTYVATE solves

Problem Statement

Crop destruction and disease transmission by insects have a remarkable impact on the human economy and health. Nearly 20% of the annual crop production is destroyed by insects and pests every year. Even after the development of insecticides and pesticides, the problem of crop damage still exists due to the unavailability of early detection of the diseases caught by the plant. As a result of which the entire crop harvest is spoiled that further leads to crop destruction. Poor farmers expect that their harvest makes enough money to pay back their loans and make enough money to cater to the day-to-day needs of their families, but this situation of natural crises further worsens their economical condition and renders them even more helpless.

Features Of CULTYVATE

Plant Disease Detection

We will be building a model using ML and DL that will provide us with the early detection of diseases. The user needs to upload an image of the leaf of the plant and our model will predict the name of the disease and respective pesticide that should be given to the crop.

Fertiliser Recommendation

The user needs to enter the values of n,p,k in the soil and the model will provide suggestions to the farmer about which fertiliser should be used so as to ensure a haelthy harvest.

Crop Recommendation

Our model will also be providing suggestions to the farmers about which crop is the best to grow in a particular area by taking into consideration various parameters like water content, mineral composition, salinity present in the soil etc. The user is expected to enter the rainfall (in mm), the state and the respective city.

User-Friendly Interface

By the medium of our project, THE CULTYVATE, we provide the farmers a user-friendly interface that is easy to operate.

*Available in Vernacular Languages *

We also have our services available in the vernacular languages as well thereby solving the problem of language acting as a barrier.

Challenges we ran into

• Faced Difficulties in Deploying
• Faced difficulties in hosting the flask web application due to the huge amount of slug size
• Faced Internal Error in making Napbars
• Faced Issues at in finding alternative packages so as to reduce the slug size
• Frustated at Time of Deployment , several Path errors and several code errors
• Faced Diffilculty in finding a appropriate Data-set with large number of images
• As a newbie to Machine learning domain it is very difficult to work with huge number of funtions and libraries.
• As we had initially used a a sequential model and then a VGG19 architure so most of the common inbuilt functions are not working , we have encounterd with number of errors , So finding new functions and there respective libraries is quite a troublesome.