Estimating the impact of environmental management on strawberry yield using publicly available agricultural data in South Korea

Abstract

Advanced information and communication technologies (ICTs) have made data collection more efficient for agricultural studies. Using publicly available database in South Korea, we estimated the relationship between the management of air temperature and relative humidity and the strawberry yield during two harvest seasons. Longitudinal data of multiple greenhouses were merged and processed, and mixed-effects models were applied to account both observed and unobserved factors across the greenhouses. The averages of air temperature and relative humidity inside each greenhouse do not take volatility of the time-varying variables into consideration, so we assessed the management of each greenhouse by the percent of time that air temperature between 15 °C and 20 °C (denoted as T_%) and the percent of time that relative humidity between 0% and 50% (denoted by H_%). The statistical models estimated that the strawberry yield decreases with respect to the number of days since harvest began and the rate of decrease is slower when T_% and H_% are higher. This study used large-scale multilocation data to provide the practical suggestion that air temperature and relative humidity should be maintained within the optimal ranges to mitigate the loss of strawberry yield especially at the later phase of a harvest season.

Keywords: Air temperature; Mixed-effects model; Open API; Relative humidity.

Figure 1. Distribution of the strawberry farms from which data were collected (yellow: primary dataset; pink: pilot dataset; red: both).

Figure 2. Observed data (left) and estimated linear trend (right) for each of the 78 farms.

Figure 3. Percent of time (%) that the temperature was below 15 °C, between 15 °C and 20 °C, and above 20 °C (top panel), and humidity was at 50% or below and above 50% (bottom panel), for each of the 78 farms.

Figure 4. Estimated average of the logarithmic number of fruit per plant, for the six scenarios: (T_%, H_%) = (10, 10), (10, 20), and (10, 30) on the left and (T_%, H_%) = (30, 10), (30, 20), and (30, 30) on the right.