Introduction

Agriculture is the backbone of our economy, as the requirement of foodstuff due to rise in population is constantly increasing. There is a huge requirement of advancements in the agriculture sector such as to make precise calculations regarding yield production, using best and latest farming equipment, in order to meet the increasing needs of crop. Because of these advancements modern farming is also referred as digital farming, precise farming, intelligent farming, intensive farming, continual farming, organic farming and agribusiness. Balasankari and Salokhe (1999) studied how farmers utilize tractors in the field.

First, precision agriculture is a farming supervision theory that comprises detecting, computing and reacting to inconsistencies within the same field and other field yields. The main objective of precision agriculture study is to provide a judgment support system for managing the entire field farming with the aim to optimize profits on inputs along with the preservation of resources. Predicting weather and effect of different fertilizers with the help of remote sensing and sensors for crop health are the initial steps of precise farming. Suprem et al. (2013) reviewed the new technologies emerging in the agriculture sector to enhance the productivity.

Second, the agribusiness is the professional term related to agricultural yields. It is a hybrid of business in agriculture that consists of breeding, yield production, agrichemicals, farm appliances and seed supply and also the strategy of marketing and distribution. The representatives and organizations that effect food and fibre chain are the part of this agribusiness structure. Wang et al. (2006) introduced wireless sensors in agriculture and food industry.

Another significant aspect of modern agriculture is handling the problems in terms of yield, atmosphere impact, food safety and sustainability in the prevailing circumstances. As the global requirement of crop is increasing rapidly, crop production must be increased along with its timely availability and high nutritional quality. This can be achieved by protecting the natural ecosystem using sustainable farming practices. Farming management concept is based on observing, measuring and responding to inter-​ and intra-​field variability in crops.

In addition to these aspects of the current agriculture industry the field of agriculture faces various problems, for example, inappropriate treatment of farms, different ailments prevailing in animals, pest infection, irregular irrigation, etc. All these problems lead to a severe damage to the yield and also prove to be hazardous to the ecosystem due to incorporation of too many chemicals in it. It is not possible to give a generalized solution for all the problems. In order to address these problems, the composite intermittent agricultural ecology should be dealt with through instantaneous observation and investigation regarding all aspects and occurrences. A remedy to this condition is possible using artificial intelligence in general and machine learning in particular. Machine learning can facilitate the agriculturalists with information to increase the crop production and diminish the initial cost as well as to balance the loss occurring during the natural calamities. Gomes and Leta (2012) reviewed a new technique of computer application in agriculture and food sector to increase the product quality. Also, Davies (2009) reviewed machine vision and its application in food and agriculture sector.