Search

Mapping the spatial variability of crops is critical for precision agriculture. In this sense, remote sensing is a key technology generally dependent on the result of vegetation indices (VIs). Therefore, investigating the sensitivity of VIs and their contribution toward explaining crop variability and assisting in predicting yield is one of the pathways scientific research needs to explore. In this study, we evaluated 12 VIs with different acquisition principles in four soybean-producing fields. Using these VIs proved to be interesting to increase the performance of yield prediction models using the Randon Forest algorithm. However, simply adding VIs to the model is not enough; these VIs must aggregate information on crop variability. Some VIs are calculated based on the variation of the scene under study, and these can be an interesting option to complement the information provided by more traditional VIs, such as NDVI, assisting in predictive models, even if their direct correlation with crop yield is low in some situations. We found that using VIs groups with the same acquisition principle in isolation did not allow reaching performance of models that contained more than one principle simultaneously. In this study, the CI and TC2 indices stood out. Thus, associating VIs with different acquisition principles and, consequently, capturing different responses to variability in vegetation vigor and canopy structure is more important than the number of predictor variables itself. [ABSTRACT FROM AUTHOR]

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze. [ABSTRACT FROM AUTHOR]

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze.

Crop yield prediction and mapping are essential for crop management and decision-making. The development of unmanned aerial vehicles (UAVs) accelerates the acquisition of high-resolution imagery for the evaluation and monitoring of crop growth and development. In this study, a cost-effective yield mapping workflow was developed in a commercial setting. Two UAVs were deployed to rapidly obtain RGB and multispectral images of spinach at different growth stages in multiple spinach fields to assess crop physiological attributes in the field environment. Based on the imagery, an image processing workflow for farm field orthoimage rotation and segmentation was proposed. Then, twelve vegetation indices (VIs) were extracted from the processed images. The most robust VIs were selected by comparing the correlations among the VIs and yields and regression tree and stepwise multiple linear regression. Excess Green Index (ExG) and Normalized Difference Vegetation Index (NDVI) were identified as two of the most robust VIs for predicting spinach yield at various stages of growth. A linear regression model was developed using 45 manually harvested calibration locations and a coefficient of determination (R2) of 0.98. The root mean squared error (RMSE) was 0.19 kg/m with a mean absolute percentage error (MAPE) of 9.0 % when using a validation dataset. The produced yield maps provided the basis for a farm harvesting decision-making process and for a general crop management strategy.