Key points are not available for this paper at this time.
Agriculture holds the key to our country's financial wellness. The crop yield is primarily determined by weather, soil fertility, and moisture level, among other factors. The majority of crops in India rely entirely on weather and soil characteristics. As a result, crop output can be increased by investigating soil parameter data using machine learning techniques. This study presents a crop selection approach based on meteorological and soil data to maximize the yield of crops. Prevention and early detection of agricultural diseases is imperative for increasing productivity. Machine learning technologies such as convolutional neural networks and Random Forest classification algorithms are used to detect crop diseases and select permissible crops. Fertilizers are normally recommended based on the nutrients present in the soil. To recommend a suitable fertilizer level, soil nutrient analysis needs to be performed, which is mostly done using laboratory techniques. Manual methods of determining soil nutrients are time-consuming. Many farmers refrain from conducting soil testing in the laboratory and grow the same crop on the land constantly, resulting in the soil losing its fertility. The suggested Internet of Things (IoT)based software platform has the potential to recommend the appropriate quantity of water and fertilizer demanded to improve soil quality and guarantee crop development. Through this technique, the outcome for various parameters of soil for distinguished soil samples is obtained, and an adequate amount of fertilizers will be recommended, limiting the use of surplus fertilizers and therefore maximizing yield. Reliable findings are obtained when innovations occur, which increases cultivation. As a result, precision agriculture improves agricultural practices by keeping up real-time data.
Lakshmi et al. (Wed,) studied this question.