Irineo Lorenzo López Cruz

Parameter estimation for crop growth model using evolutionary and bio-inspired algorithms

All dynamic crop models for growth and development have several parameters whose values are usually determined by using measurements coming from the real system. The parameter estimation problem is raised as an optimization problem and optimization algorithms are used to solve it. However, because the model generally is nonlinear the optimization problem likely is multimodal and therefore classical local search methods fail in locating the global minimum and as a consequence the model parameters could be inaccurate estimated. This paper presents a comparison of several evolutionary (EAs) and bio-inspired (BIAs) algorithms, considered as global optimization methods, such as Differential Evolution (DE), Covariance Matrix Adaptation Evolution Strategy (CMA-ES), Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) on parameter estimation of crop growth SUCROS (a Simple and Universal CROp Growth Simulator) model. Subsequently, the SUCROS model for potential growth was applied to a husk tomato crop (Physalis ixocarpa Brot. ex Horm.) using data coming from an experiment carried out in Chapingo, Mexico. The objective was to determine which algorithm generates parameter values that give the best prediction of the model. An analysis of variance (ANOVA) was carried out to statistically evaluate the efficiency and effectiveness of the studied algorithms. Algorithms efficiency was evaluated by counting the number of times the objective function was required to approximate an optimum. On the other hand, the effectiveness was evaluated by counting the number of times that the algorithm converged to an optimum. Simulation results showed that standard DE/rand/1/bin got the best result.

Artificial Neural Network as a Prediction Tool in Agricultural Variables

Artificial Neural Network (ANN) technology is a form of artificial intelligence that learns by processing representative data patterns through its internal architecture. ANN technology often offers a superior alternative to traditional physical-based models, and excel at uncovering patterns or relationships in data. It is also a powerful non-linear estimator which is recommended when the functional form between input-output is unknown or it is not well understood but it is believed could be nonlinear. This paper show two applications of ANN for forecasting solar radiation and available dam storage. In the first case ANN provided a good accurate forecasts for all period with an average square error of 0.05% in the prediction. For the second case, ANN provide relatively accurate estimates of water availability one month into the future in the Purisima dam located in the state of Guanajuato. The results suggest that additional input variables such as runoff, cropping patterns and groundwater extractions may be necessary to increase ANN forecasting accuracy. This feasibility study demonstrates that ANN technology has the potential to serve as a highly accurate forecasting tool. Moreover, ANN technology can continuously be updated, as new data become available, increasing its forecasting ability.