Potato is the largest non-cereal food crop in the world. Timely estimation of end-of-season tuber production using in-season information can inform sustainable agricultural management decisions that increase productivity while reducing impacts on the environment. Recently, unmanned aerial vehicles (UAVs) have become increasingly popular in precision agriculture due to their flexibility in data acquisition and improved spatial and spectral resolutions. In addition, compared with natural color and multispectral imagery, hyperspectral data can provide higher spectral fidelity which is important for modelling crop traits. In this study, we conducted end-of-season potato tuber yield and tuber set predictions using in-season UAV-based hyperspectral images and machine learning. Specifically, six mainstream machine learning models, i.e., ordinary least square (OLS), ridge regression, partial least square regression (PLSR), support vector regression (SVR), random forest (RF), and adaptive boosting (AdaBoost), were developed and compared across potato research plots with different irrigation rates at the University of Wisconsin Hancock Agricultural Research Station. Our results showed that the tuber set could be better predicted than the tuber yield, and using the multi-temporal hyperspectral data improved the model performance. Ridge achieved the best performance for predicting tuber yield (R2 = 0.63) while Ridge and PLSR had similar performance for predicting tuber set (R2 = 0.69). Our study demonstrated that hyperspectral imagery and machine learning have good potential to help potato growers efficiently manage their irrigation practices.
A critical step in profitable post-harvest potato storage management is to cure tubers at appropriate temperatures long enough for rapid wound-healing to prevent disease and defect development, but not too long to jeopardize storage quality. A two-year storage study was conducted in macro-storage totes at the University of Wisconsin Hancock storage research facility to evaluate the effects of higher wound-healing temperatures (15.6 °C, 18.3 °C) imposed for different durations, and compare them to the U.S. potato industry’s standard practice (12.8 °C), on weight loss and frying quality of multiple processing potato varieties during long-term storage. It was found that in the experimental setting of this study, warmer wound-healing temperatures resulted in (1) less weight loss, particularly during the early storage season across varieties; (2) ameliorated senescent sweetening of the Snowden variety; (3) improved fry quality of the Russet Burbank variety; (4) and no apparent disease spread during long-term storage if tubers were harvested healthy out of fields. Overall, no significant difference was found between 15.6 °C and 18.3 °C regarding their treatment effects. Our conclusion is that compared to the current standard practice, higher wound-healing temperatures may have the potential benefits of improving potato storage quality while reducing the economic penalty associated with weight loss for specific varieties, but tubers should be healthy at harvest in order to gain the benefits. Further research is needed to test if those benefits of higher wound-healing temperatures hold true in large-scale commercial storage facilities.
Uncertainty exists regarding the depth and extent to which agricultural practices affect soil properties, in particular soil organic C (SOC). In this study we examined the impact of 53 yr of continuous corn (Zea mays L.) receiving varying rates of inorganic N fertilizer with complete stover return on soil properties including SOC, total N, and bulk density (BD) to a depth of 1 m. In the treatment receiving virtually no applied N there was a significant reduction in soil N content at 0 to 30 cm over the study period, while the treatment receiving N in excess of recommended application levels was similar to the treatment receiving recommended rates of N fertilizer. Trends in SOC content were similar to those for total N, but a significant treatment effect was detectable throughout the entire 1-m soil profile sampled. Over the course of the study, all experimental fields appeared to have lost approximately 6 cm of topsoil through erosion, with the lowest N rate plots subsiding a further 2 cm due to compaction. Despite using disruptive management practices (moldboard plowing and application of anhydrous ammonia), declines in soil C and N content were not apparent for this soil type under conditions of low slope and the linear gains in productivity realized under the two higher N rate treatments. Thus N fertilizer was a benefit to this cropping system, rather than a detriment, and was sufficient to allow maintenancebut not building-of SOC.
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.