Abstract:The use of automated methods to estimate fractional vegetation cover (FVC) from digital photographs has increased in recent years given its potential to produce accurate, fast and inexpensive FVC measurements. Wide acceptance has been delayed because of the limitations in accuracy, speed, automation and generalization of these methods. This work introduces a novel technique, the Automated Canopy Estimator (ACE) that overcomes many of these challenges to produce accurate estimates of fractional vegetation cover using an unsupervised segmentation process. ACE is shown to outperform nine other segmentation algorithms, consisting of both threshold-based and machine learning approaches, in the segmentation of photographs of four different crops (oat, corn, rapeseed and flax) with an overall accuracy of 89.6%. ACE is similarly accurate (88.7%) when applied to remotely sensed corn, producing FVC estimates that are strongly correlated with ground truth values.
Crop production in the Caribbean is dominated by small open field holdings that are almost totally reliant on rainfall. Sweet potato (Ipomoea batatas L. Lam. [Convolvulaceae]) has been identified as an important commodity to attain food and nutrition security goals of the region, particularly in light of a changing climate. The crop has high nutritional value, innate drought‐tolerant properties, and can be grown with relatively low inputs. The routine use of crop models for yield optimization is largely absent in the Caribbean. In this study, an attempt was made to parameterize the FAO AquaCrop model for sweet potato for the first time. AquaCrop is a simulation model for crop water productivity, designed primarily for use in irrigation management. Parameters were developed using data from three sweet potato cultivars grown in two agroecological zones in Jamaica under rainfed and irrigated conditions. Digital photography was combined with an automated canopy estimator to track canopy development, and sample harvesting was done throughout the crop season. The overall simulation of biomass was good, with deviations of <28% for four out of six simulations, and season‐long performance of the model was commendable. The simulation of yield presented more challenges, especially given the nonlinear rate of tuber development. The results, however, indicate that AquaCrop could be a useful tool for Caribbean agriculture in predicting the productivity of sweet potato under varying water availability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.