Project Details

Project Name: Data mining for better farming.

Project Code: ILSW001DM

Summary: Smart farming system is an autonomous & sophisticated mechanism, which will aid in the growth of agriculture yield by applying hi-tech agriculture techniques without human intervention. The paper represents an overview of a recent smart farming software solutions. The proposed system works on the data mining techniques & data obtained from satellite information, Internet, from soil testing report fed in the existing databases. It elegantly makes use of the clustering algorithms for taking decisions based on the awareness of weather changes, by keeping track of crop growing stages, with proper water utilization, along with the decision of fertilizer to be used according to crop stage, as well as the pesticide to be used to protect crops from diseases and insect attack. This system is capable of increasing the productivity of fields by managing farm operations smartly.

Agriculture is the biggest water consumer, while the irrigation accounts for approximately 70% of global water consumption. The domestic and industrial sectors account for 10% and 20%, respectively, although these percentages vary considerably across countries. As population is increasing day by day, the demand of food is on gain too. There are certain more factors that affect more crop yield, such as environmental factors like erratic weather conditions leading to crop loss, farmer’s ignorance in embracing newer technologies that can be used for enhancement of gross profit from agriculture. In spite of all such problems, agriculture is a cardinal source of employment and plays a key role in socio-economic development of India. So, in order to improve the condition, we can make use of technology in smarter way. In order to make this possible we need more productivity from farming. The domestic and industrial sectors account for 10% and 20%. Without improved efficiencies, agricultural water consumption is expected to increase globally by around 20% in few years. In the proposed system, Data mining is used for all data mapping & processing. Data Mining is about finding rules in data. The technology of data mining is narrowly connected to data storage and is intertwined with database management system. Data mining involves the process of finding large quantity of previously unknown data, and then their use in important business decision making. Key phrase here is ‘unknown datum’ which means that the datum is buried in large quantity of operational data, which if analyzed, provides relevant information to agriculture decision makers. The overall goal of the data mining process is to extract information from a data set to extract previously unknown, interesting patterns such as groups of data records (cluster analysis), unusual records (anomaly detection) and transform it into an understandable structure for further use. The. data mining is the process of finding correlations or patterns among dozens of fields in large relational databases. Here, K-nearest neighbor technique is used for smart farming decision making.

The main motive behind the smart farming system is to provide better solution to farmer for high yield. In this system all 3 main modules i.e. Irrigation, Fertilizer and pesticide modules are integrated. Smart farming system is a web application with huge amount of dataset available in backend. The data mining is used in the process of finding correlations or patterns among the dozens of fields in relational databases. Clustering algorithm is used. Clustering is the process which partitions given data set into homogeneous group based on similarities and dissimilarity. Initially farmer have to send soil for testing and feed the soil testing report details (which include nitrogen, potassium, phosphorus, calcium, magnesium, etc.) in application. These details are necessary for prediction of water required, fertilizer and pesticides. Also for the first time have to save the exact location of farm so that the longitude and latitude of farm is identified which is useful to get the exact temperature of farm location. Temperature of farm location is identified from satellite and online whether forecasting sources. We need to insert initial crop information such as crop name, crop stage, soil condition, etc.