A computational model for soil fertility prediction in ubiquitous agriculture

• Published in: Computers and electronics in agriculture Vol. 175; p. 105602
• Main Authors: Helfer, Gilson Augusto, Victória Barbosa, Jorge Luis, Santos, Ronaldo dos, da Costa, Adilson Ben
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.08.2020; Elsevier BV
• Subjects: Agriculture; Algorithms; Context awareness; Environmental impact; Machine learning; Organic matter; Precision agriculture; Prediction models; Productivity; Soil fertility; Soils; Ubiquitous computing; Productivity; Precision agriculture; 99-00; 00-01; Soil fertility; Context awareness; Ubiquitous computing
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2020.105602

•Soil fertility and productivity predicted through context history and machine learning.•450 samples analyzed for soil fertility prediction.•Organic matter and clay based on NIR spectral data.•Wheat productivity based on climatic events between 2001 and 2015. The application of sophisticated sensors to measure soil composition and plant needs are a tendence in precision agriculture. In any case, prediction models are built using machine learning algorithms. The goal is to make farming more efficient and productive with minimal impact on the environment. The present article proposes an architectural model that evaluates the soil’s fertility and productivity through context history with Partial Least Squares Regression. Also productivity prediction of a wheat planted area was performed using climatic events between the years of 2001 and 2015 resulting a mean square error of calibration (RMSEC) of 0.20 T/ha, mean square errors of cross-validation of 0.54 T/ha with a Pearson coefficient (R2) of 0.9189. For the prediction of organic matter and clay, the best results obtained were a R2 of 0.9345, RMSECV of 0.54% and R2 of 0.9239, RMSECV of 5.28%, respectively.