Internet of Things and Machine-Learning-Based Leaching Requirements Estimation for Saline Soils

Abstract

Soil salinity is a soil degradation phenomenon with a severe impact on crop production. Internet of Things (IoT)-assisted solution is proposed in this article to determine soil salinity level and environment conditions to recommend irrigation water, with a purpose to leach down the salts from the root zone of crops in saline soils. IoT and machine learning (ML)-based leaching water requirements estimation for saline soils is made using the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in situ</i> monitoring of the salinity level and crop field temperature. The Food and Agricultural Organization (FAO)-proposed method of leaching requirement is implemented for efficient leaching water estimation. These estimations are used to train and test the Naive Bayes classifier for ML to predict the leaching requirements (LR) in future while using only temperature and soil salinity level. The performance of ML is judged in terms of accuracy, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${f}$ </tex-math></inline-formula> -measures, precision, and recall. The proposed solution is implemented on a cotton crop in a salt-affected area, to test the agronomic impact of the proposed solution.