Improving sugarcane production in saline soils with Machine Learning and the Internet of Things

Abstract

The Indian sugar industry is the second largest in the world. Sugar is an essential domestic grocery item required in India producing over 25 million tonnes per annum. Sugarcane is the root of sugar products that grow in over 5 million hectares all over India. However, nearly 1.5 million hectares of overall farms are saline soil lands (high salt content). This leads to lower yields in sugarcane agriculture than what would be expected. Therefore, tackling the salinity problem is crucial to achieve strong food security as well as tackle the sustainability of farming practices in India that have reach beyond just sugarcane. This research proposes efficient, sustainable, smart farming techniques for sugarcane cultivation in salt-affected lands with the help of the Internet of Things (IoT) and Machine Learning (ML). The proposed model has been implemented in a real-world two hectare sugar cane field cultivated from saline soils using Raspberry PI IoT nodes to control the drip irrigation (water supply). The Naïve Bayes model has been used to train and predict the leaching requirement suggested by Food and Agriculture Organization of the United Nations (FAO) and United Nations Educational, Scientific and Cultural Organization (UNESCO) for efficient leaching water requirements. The performance of the proposed model has been evaluated in terms of sugar cane growth, cost of cultivation, as well as water requirements leading to an improved outlook for future use. Moreover, our results have been compared with regular sugar cane cultivation to show their effectiveness.