Litcius/Paper detail

Crop Yield Analysis Using Machine Learning Algorithms

Fatin Farhan Haque, Ahmed Abdelgawad, Venkata P. Yanambaka, Kumar Yelamarthi

202039 citationsDOI

Abstract

Agriculture is not only a huge aspect of the growing economy, but it’s essential for us to survive. Predicting crop yield is not an easy task, as it depends on many parameters such as water, ultra-violet (UV), pesticides, fertilizer, and the area of the land covered for that region. In this paper, two different Machine Learning (ML) algorithms are proposed to analyze the crops’ yield. These two algorithms, Support Vector Regression (SVR) and Linear Regression (LR), are quite suitable for validating the variable parameters in the predicting the continuous variable estimation with 140 data points that were acquired. The parameters mentioned above are key factors affecting the yield of crops. The error rate was measured with the help of Mean Square Error (MSE) and Coefficient of Determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ), where MSE gave out approximately 0.005 and R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> gave around 0.85. The same dataset has been used for quick comparison between the algorithms’ performances.

Topics & Concepts

Yield (engineering)AlgorithmMachine learningSupport vector machineMean squared errorArtificial intelligenceRegressionVariable (mathematics)Crop yieldLinear regressionRegression analysisComputer scienceMathematicsStatisticsAgronomyBiologyMathematical analysisMetallurgyMaterials scienceSmart Agriculture and AIGreenhouse Technology and Climate ControlLeaf Properties and Growth Measurement