An important issue for agricultural planning purposes is the accurate yield estimation for the numerous crops involved in the planning. Machine learning (ML) is an essential approach for achieving practical and effective solutions for this problem. Many comparisons of ML methods for yield prediction have been made, seeking for the most accurate technique. Generally, the number of evaluated crops and techniques is too low and does not provide enough information for agricultural planning purposes. This paper compares the predictive accuracy of ML and linear regression techniques for crop yield prediction in ten crop datasets. Multiple linear regression, M5-Prime regression trees, perceptron multilayer neural networks, support vector regression and k-nearest neighbor methods were ranked. Four accuracy metrics were used to validate the models: the root mean square error (RMS), root relative square error (RRSE), normalized mean absolute error (MAE), and correlation factor (R). Real data of an irrigation zone of Mexico were used for building the models. Models were tested with samples of two consecutive years. The results show that M5-Prime and k-nearest neighbor techniques obtain the lowest average RMSE errors (5.14 and 4.91), the lowest RRSE errors (79.46% and 79.78%), the lowest average MAE errors (18.12% and 19.42%), and the highest average correlation factors (0.41 and 0.42). Since M5-Prime achieves the largest number of crop yield models with the lowest errors, it is a very suitable tool for massive crop yield prediction in agricultural planning.

Efficient cropping requires yield estimation for each involved crop, where data-driven models are commonly applied. In recent years, some data-driven modeling technique comparisons have been made, looking for the best model to yield prediction. However, attributes are usually selected based on expertise assessment or in dimensionality reduction algorithms. A fairer comparison should include the best subset of features for each regression technique; an evaluation including several crops is preferred. This paper evaluates the most common data-driven modeling techniques applied to yield prediction, using a complete method to define the best attribute subset for each model. Multiple linear regression, stepwise linear regression, M5′ regression trees, and artificial neural networks (ANN) were ranked. The models were built using real data of eight crops sowed in an irrigation module of Mexico. To validate the models, three accuracy metrics were used: the root relative square error (RRSE), relative mean absolute error (RMAE), and correlation factor (R). The results show that ANNs are more consistent in the best attribute subset composition between the learning and the training stages, obtaining the lowest average RRSE (86.04%), lowest average RMAE (8.75%), and the highest average correlation factor (0.63).

Entropy is a key concept in the characterization of uncertainty for any given signal, and its extensions such as Spectral Entropy and Permutation Entropy. They have been used to measure the complexity of time series. However, these measures are subject to the discretization employed to study the states of the system, and identifying the relationship between complexity measures and the expected performance of the four selected forecasting methods that participate in the M4 Competition. This relationship allows the decision, in advance, of which algorithm is adequate. Therefore, in this paper, we found the relationships between entropy-based complexity framework and the forecasting error of four selected methods (Smyl, Theta, ARIMA, and ETS). Moreover, we present a framework extension based on the Emergence, Self-Organization, and Complexity paradigm. The experimentation with both synthetic and M4 Competition time series show that the feature space induced by complexities, visually constrains the forecasting method performance to specific regions; where the logarithm of its metric error is poorer, the Complexity based on the emergence and self-organization is maximal.

A hybrid variant of the Fuzzy C-Means and K-Means algorithms is proposed to solve large datasets such as those presented in Big Data. The Fuzzy C-Means algorithm is sensitive to the initial values of the membership matrix. Therefore, a special configuration of the matrix can accelerate the convergence of the algorithm. In this sense, a new approach is proposed, which we call Hybrid OK-Means Fuzzy C-Means (HOFCM), and it optimizes the values of the membership matrix parameter. This approach consists of three steps: (a) generate a set of n solutions of an x dataset, applying a variant of the K-Means algorithm; (b) select the best solution as the basis for generating the optimized membership matrix; (c) resolve the x dataset with Fuzzy C-Means. The experimental results with four real datasets and one synthetic dataset show that HOFCM reduces the time by up to 93.94% compared to the average time of the standard Fuzzy C-Means. It is highlighted that the quality of the solution was reduced by 2.51% in the worst case.