A review of methods to evaluate crop model performance at multiple and changing spatial scales

Abstract

Crop models are useful tools because they can help understand many complex processes by simulating them. They are mainly designed at a specific spatial scale, the field. But with the new spatial data being made available in modern agriculture, they are being more and more applied at multiple and changing scales. These applications range from typically at broader scales, to perform regional or national studies, or at finer scales to develop modern site-specific management approaches. These new approaches to the application of crop models raise new questions concerning the evaluation of their performance, particularly for downscaled applications. This article first reviews the reasons why practitioners decide to spatialize crop models and the main methods they have used to do this, which questions the best place of the spatialization process in the modelling framework. A strong focus is then given to the evaluation of these spatialized crop models. Evaluation metrics, including the consideration of dedicated sensitivity indices are reviewed from the published studies. Using a simple example of a spatialized crop model being used to define management zones in precision viticulture, it is shown that classical model evaluation involving aspatial indices (e.g. the RMSE) is not sufficient to characterize the model performance in this context. A focus is made at the end of the review on potentialities that a complementary evaluation could bring in a precision agriculture context.

Unsupervised Graph Spectral Feature Denoising for Crop Yield Prediction

“…First, we computed the optimum weight parameter µ for both EVI_June and EVI_July, which was µ = 2.2. Table I shows the crop yield prediction performance using noisy features versus denoised features with different weight parameters, under three metrics in the yield prediction literature: root-mean-square error (RMSE), Mean Absolute Error (MAE) and R2 score (larger the better) [17]. Results in Table I demonstrate that our optimal weight parameter (i.e., 2.2) has the best results among other µ values.…”

“…Further, according to (17), for µ 1 ≥ σ 2 λ i α 2 i > 0, (µ 2 − µ 1 ) ≥ 0 → (MSE(µ 2 ) − MSE(µ 1 )) ≥ 0, (18) and for 0 < µ 1 < σ 2 λ i α 2 i , (µ 2 − µ 1 ) < 0 → (MSE(µ 2 ) − MSE(µ 1 )) ≥ 0.…”

“…Using USDA corn data from 10 states in the corn belt (Iowa, Illinois, Indiana, Ohio, Nebraska, Minnesota, Wisconsin, Michigan, Missouri, and Kentucky) containing 938 counties, experimental results show that using our GLR-regularized denoiser with optimized µ to denoise two important EVI features led to improved performance in an DL model [16]: reduction of root mean square error (RMSE) [17] by 0.434% in crop yield prediction compared to the baseline when the features were not pre-denoised.…”

Bayesian multi-level calibration of a process-based maize phenology model

“…While assessing prediction quality of the models is important, this is beyond the current scope of gaining a better understanding of the phenology model and identifying model deficits in its application to regional studies. The BMM approach can also be applied to process-based crop models, wherein these point-based models can be spatialized [65]. Additionally, gene-based models can be integrated with crop models to determine more representative genotype-specific parameters [66, 67].…”

Daily Estimation of Global Solar Irradiation and Temperatures Using Artificial Neural Networks through the Virtual Weather Station Concept in Castilla and León, Spain

“…This is a key concept in both precision agriculture and agricultural modelling. Several authors have studied the different techniques applied in precision agriculture and in the modelling of crop production where they involve meteorological variables, with the objective of improving quality, profitability, resource use efficiency and sustainability [ 1 , 2 , 3 ]. Among these techniques, the application of variable doses of water, fertilizers and agrochemicals (while considering agrometeorological conditions), as well as the estimation of production (based on the evolution of meteorological variables and the physiological response of crops), are the most frequently used and are currently adopted by many farmers.…”