Crop Yield Prediction through Proximal Sensing and Machine Learning Algorithms

Abstract

Proximal sensing techniques can potentially survey soil and crop variables responsible for variations in crop yield. The full potential of these precision agriculture technologies may be exploited in combination with innovative methods of data processing such as machine learning (ML) algorithms for the extraction of useful information responsible for controlling crop yield. Four ML algorithms, namely linear regression (LR), elastic net (EN), k-nearest neighbor (k-NN), and support vector regression (SVR), were used to predict potato (Solanum tuberosum) tuber yield from data of soil and crop properties collected through proximal sensing. Six fields in Atlantic Canada including three fields in Prince Edward Island (PE) and three fields in New Brunswick (NB) were sampled, over two (2017 and 2018) growing seasons, for soil electrical conductivity, soil moisture content, soil slope, normalized-difference vegetative index (NDVI), and soil chemistry. Data were collected from 39–40 30 × 30 m2 locations in each field, four times throughout the growing season, and yield samples were collected manually at the end of the growing season. Four datasets, namely PE-2017, PE-2018, NB-2017, and NB-2018, were then formed by combing data points from three fields to represent the province data for the respective years. Modeling techniques were employed to generate yield predictions assessed with different statistical parameters. The SVR models outperformed all other models for NB-2017, NB-2018, PE-2017, and PE-2018 dataset with RMSE of 5.97, 4.62, 6.60, and 6.17 t/ha, respectively. The performance of k-NN remained poor in three out of four datasets, namely NB-2017, NB-2018, and PE-2017 with RMSE of 6.93, 5.23, and 6.91 t/ha, respectively. The study also showed that large datasets are required to generate useful results using either model. This information is needed for creating site-specific management zones for potatoes, which form a significant component for food security initiatives across the globe.

A novel NIR-image segmentation method for the precise estimation of above-ground biomass in rice crops

“…Lastly, Fig 12c–12f present the comparative results of both approaches for the estimation of the AGBD according to the physiological response of two rice genotypes under lowland and upland production systems. Elastic-Net regressions [ 43 ] were used to determine these relationships. This method overcomes several limitations of standard multi-variable regressions by combining the penalties of both lasso and ridge regression methods, with the aim of minimizing the following loss function: where r is the mixing parameter between ridge r = 0 and lasso r = 1.…”

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

“…The LR model represents a relationship between independent and one or more dependent variables [54]. In a machine learning framework, learning can be done by using data and minimizing the loss or error (RMSE or MSE) that are experienced by using regression algorithms.…”

“…The learning data is split into sets of adaptive splines with unique slopes [70]. The K-NN is used for classification and regression that provides more weightage to close neighbors in making the prediction so that they relate more to the average than distant ones [54]. Various distance formulas such as Euclidean, Manhattan, and Minkowski can be applied to compute the distance between two neighbors.…”

“…Abbas et al [54] employed LR, SVR and k-NN algorithms for potato yield prediction using datasets containing NDVI and soil properties. The SVR models performed better in predicting the potato yield over the other three models.…”

A Machine Learning Approach to Predict the Average Localization Error With Applications to Wireless Sensor Networks

“…Moreover, it is also flexible in dealing with geometry, transmission, data generalisation and additional functionality of kernel [41]. This additional functionality enhances the model capacity for predictions by considering the quality of features [42].…”