Evaluation of the Integrated Canadian Crop Yield Forecaster (ICCYF) model for in-season prediction of crop yield across the Canadian agricultural landscape

Abstract

a b s t r a c tEarly warning information on crop yield and production are very crucial for both farmers and decisionmakers. In this study, we assess the skill and the reliability of the Integrated Canadian Crop Yield Forecaster (ICCYF), a regional crop yield forecasting tool, at different temporal (i.e. 1-3 months before harvest) and spatial (i.e. census agricultural region -CAR, provincial and national) scales across Canada. A distinct feature of the ICCYF is that it generates in-season yield forecasts well before the end of the growing season and provides a probability distribution of the forecasted yields. The ICCYF integrates climate, remote sensing derived vegetation indices, soil and crop information through a physical process-based soil water budget model and statistical algorithms. The model was evaluated against yield survey data of spring wheat, barley and canola during the 1987-2012 period. Our results showed that the ICCYF performance exhibited a strong spatial pattern at both CAR and provincial scales. Model performance was better from regions with a good coverage of climate stations and a high percentage of cropped area. On average, the model coefficient of determination at CAR level was 66%, 51% and 67%, for spring wheat, barley and canola, respectively. Skilful forecasts (i.e. model efficiency index > 0) were achieved in 70% of the CARs for spring wheat and canola, and 43% for barley (low values observed in CAR with small harvested area). At the provincial scale, the mean absolute percentage errors (MAPE) of the September forecasts ranged from 7% to 16%, 7% to14%, and 6% to 14% for spring wheat, barley and canola, respectively. For forecasts at the national scale, MAPE values (i.e. 8%, 5% and 9% for the three respective crops) were considerably smaller than the corresponding historical coefficients of variation (i.e. 17%, 10% and 17% for the three crops). Overall, the ICCYF performed better for spring wheat than for canola and barley at all the three spatial scales. Skilful forecasts were achieved by mid-August, giving a lead time of about 1 month before harvest and about 3-4 months before the final release of official survey results. As such, the ICCYF could be used as a complementary tool for the traditional survey method, especially in areas where it is not practical to conduct such surveys.Crown

Corn Response to Climate Stress Detected with Satellite-Based NDVI Time Series

“…The NDVI is developed from two important wave bands: the red and near infrared, and has been widely used for agricultural mapping and yield monitoring [25][26][27][28][29]. The NDVI is calculated as:…”

Assessing the Performance of MODIS NDVI and EVI for Seasonal Crop Yield Forecasting at the Ecodistrict Scale

“…The estimated variables and the variables observed at near real time were finally used as input into the selected yield model to forecast the yield probability distribution for each ECD. The 10th percentile (worst 10%), the 50th percentile (median) and the 90th percentile (best 10%) were output as the probability measures [28,36]. A detailed description of the modeling methodology can be found in Newlands et al [28] and Chipanshi et al [36].…”

“…The main features [28,36] of the ICCYF are: (1) the integration of a physical based soil moisture model to generate climate based predictors and satellite derived information; (2) an automatic ranking and selection of best predictors using Robust Least Angle Regression Scheme (RLARS) and Leave-One-Out-Cross-Validation (LOOCV) scheme at run time, as well as a spatial correlation analysis among the neighboring spatial units; (3) a Bayesian method for sequential forecasting, i.e., estimation of the prior and posterior distributions of model predictors through a Markov Chain Monte Carlo (MCMC) scheme, and random forest-tree machine learning techniques to select the best predictors of unobserved variables at the time of forecast.…”

“…Exploring the crop yield modeling at the ECD level through the ICCYF will give more insights on how the forecast may be achieved for oriented user groups, as well as a better understanding of the forecast skill at finer scales. In addition, one future development activity of the ICCYF [36] aims to use data from moderate resolution satellites (i.e., MODIS) for assessing the crop vegetation status and to derive VIs.…”

A Framework for Large-Area Mapping of Past and Present Cropping Activity Using Seasonal Landsat Images and Time Series Metrics

“…Spatially detailed census data on cropping activities could provide essential information for managing and predicting crop production [1]. These data may form the spatially explicit basis upon which yields [2] and yield potentials can be estimated with additional sources of Earth-observation data [3,4]. Worldwide, the food supply to local and regional markets can be a driving factor for agricultural land use.…”