FARM AI

Farm AI

To develop a platform that uses machine learning to provide foresight into proper and timely farming through predictive analysis. Through our application, farmers will have valuable information regarding the average demand for different crops in a particular time period, the expected average supply of crops, a predictive analysis on the price variations of those crops in a given time period, what crops are potentially most profitable for farmers to grow in a given time period and more.

There are many countries in the world whose economy is predominantly based around agriculture. Out of them, agriculture plays an important role in the economies of a large number of developing countries in Asia, Africa and South America. Worldwide the agricultural sector amounts to a significant percentage of the country’s economy. But in most parts of the world, farmers grow crops based on their current knowledge and past experiences.

For example, most farmers grow a selected limited number of crops. This is because they have the necessary knowledge required to grow those crops and the experience gained in previous years. If we consider that, in a particular period, the price of a particular crop (for this example, consider carrots), skyrocketed suddenly due to certain reasons. At the immediately next season, most farmers will opt to grow carrots because there was a high demand and high price for it earlier. By growing carrots for the immediate season, farmers expect to obtain high profits as they have the experience of the price of carrots going up due to lack of supply to satisfy the demand. But in reality, many farmers might think in the same manner and grow carrots, ultimately resulting in an excessive supply of carrots that now exceeds the demands of the market. When there is a high supply of a certain product, the resultant effect would be a drop in the prices of that product. Therefore, now the prices of carrots have a high possibility to go down and thereby create losses for a large number of farmers who grew carrots during that time. Also due to the excessive supply of carrots, it might result in overproduction and lead to crop wastage. This happens because the supply of carrots hugely exceeds the demands of the market and therefore create a relatively larger supply-demand market gap.

The solution we developed to address this problem is to create a platform that uses machine learning to provide predictive analytics for crops. Through this application, users will be able to gain valuable information with regards to the expected supply of different crops in a particular time period, the expected demand for those crops, a predictive analysis of the average price variations for those crops in the market and what crops are potentially most profitable to be grown for a particular period and so on. Also, users will be able to gain insight on what crops are best to be grown in a particular time in relevance to weather conditions, geographical information etc thereby reducing overproduction, wastage of crops and financial losses to the farmers.

At present, around 40% of crops produced are wasted throughout the world. This is an alarming percentage, specially when we take into consideration the ever-increasing demand for food throughout the world. As the global population keeps increasing, the wastage of crops must be controlled. Even in Sri Lanka, the situation is more or less the same, with around 30-40% of crops being wasted due to low yield levels and a mismatch between production and the demand of the market.

We conducted a survey involving 138 farmers and 12 agricultural officers from different areas in Sri Lanka. A major concern of the farmers was that the prices they receive for their crops were low due to an overproduction of those crops; often at certain times, either a particular crop gets overproduced or whenever a crop is not produced enough, a sudden huge deficiency of it occurs in the market and prices skyrocket. If we consider the overproduction issue, here the supply exceeds the actual demand of the market and consequently, the prices the farmers receive are low and most of those crops are thrown away and never consumed. On the other hand, when a particular crop is not produced enough, the market prices skyrocket and a massive deficiency of it occurs, again destabilizing the market.

Most farmers are caught in between this disparity and mostly end up not receiving reasonable prices for their crops and crop wastage. Due to these issues, today, farming is not considered a profitable venture and therefore lesser and lesser people are willing to become involved in it. This was one of the major concerns for regional agricultural officers and related government officials as a large percentage of the children of present farmers opt-out of pursuing farming because the profitability of it is decreasing. This decrease in the number of people pursuing agriculture is again a warning sign for a major issue because even though the number of people pursuing farming becomes low, the demand for food is increasing ever so fast.

Farming is crucially important to the population of the entire world and what we saw was most of the prevalent problems in farming was due to a lack of proper and timely foresight into the demands, supply of the market and accordingly what crops to grow & obtain profits. Therefore, if the much needed proper and timely foresight is provided, more people would be encouraged to invest in farming and the present farming communities would be able to obtain good profits for what they grow, thereby uplifting their lives as well.

Scope

The project will consist of a smartphone application which will provide farmers with important foresight into the potential variations of the market and valuable information regarding how to accordingly pursue farming & obtain the maximum profits.

Through the application, farmers will be able to access critical information including what the average expected market demand is for a particular crop in a given period, what the average expected market supply would be for that particular crop in a given period, what the expected price variations would be in relevance to that crop and foresight into what would potentially be most profitable for a particular farmer to grow in a particular period.

Apart from these core features, the application will also include extra features such as a messageboard to notify the farming community of diseases that could potentially destroy their crops, suggestion of methods of mitigating the effects of those diseases, a chat platform that facilitates knowledge sharing amongst the farming community and so on. Also in future, this application could potentially act as a platform for buying and selling crops as well.

Feasibility

Economic Feasibility

There are 570 Million farms around the world.And from our app giving foresight the lives of farmers would get better. Therefore we expect to see high rates of adoption for the app. An example, if we can get just 1% of farms worldwide that would encompass 5.7 million farms.

We aim to initially provide the core forecasting capability of the app free of charge. For the add on features which includes the disease alert feature auctioning feature and for the access to the message boards we aim to get a monthly subscription fee of $20.

Give the revenue and a scale we’ll be able to easily handle the employment costs, maintenance costs and server costs.

Technical Feasibility

ML Studio by Microsoft will be used for the core component of this application. ML Studio has neural network components and we will be using recurrent neural networks to develop the application. Microsoft ML Studio and its technologies are subscriber based and already existing technologies. The front end will be developed using Cordova and Ionic framework. These are open source cross-platform supported technologies.

Operational Feasibility

Farmers are the main stakeholders in this platform. In the current world, more and more smartphones are being used globally. According to www.statistica.com, the number of smartphone users by the year 2019 will be around 2.5 billion worldwide, which is approximately around 36% of the global population and this number is increasing ever so fast every year, with smartphones penetrating a large number of developing countries throughout the world. Therefore, this particular application has a huge potential in the market because there are no competitors which offer predictive analytics and a variety of other features as this application does.