Conditioning machine learning models to adjust lowbush blueberry crop management to the local agroecosystem
Parent, S.É., Lafond, J., Paré, M.C., Parent, L.E., Ziadi, N. (2020). Conditioning machine learning models to adjust lowbush blueberry crop management to the local agroecosystem. Plants, [online] 9(10), 1-21. http://dx.doi.org/10.3390/plants9101401
Plain language summary
The specific conditions of agro-ecosystems can limit the productivity of lowbush blueberry (Vaccinium angustifolium Ait.). The objectives of the project were to assess the effects of agro-ecosystems and management methods on fruit production and to subsequently develop recommendations for adjusting soil fertility according to local weather conditions. Our models revealed that weather conditions had the greatest impact on productivity. For example, high mean temperatures measured at flower bud burst and after fruit maturation, and total precipitation at flowering had positive effects. However, low mean temperatures and low precipitation before bud burst, at flowering and at harvest, as well as the number of freezing days before flower bud burst had negative effects. On the other hand, soil and blueberry leaf tissue analyses and fertilizer application rates showed limited effects on productivity. The first statistical approach successfully predicted fruit yields based on historical weather data, soil and leaf tissue analyses and fertilizer application rates. Thus, it was possible to optimize potential yields, which will allow more targeted and localized management of fertilizer.
Agroecosystem conditions limit the productivity of lowbush blueberry. Our objectives were to investigate the effects on berry yield of agroecosystem and crop management variables, then to develop a recommendation system to adjust nutrient and soil management of lowbush blueberry to given local meteorological conditions. We collected 1504 observations from N-P-K fertilizer trials conducted in Quebec, Canada. The data set, that comprised soil, tissue, and meteorological data, was processed by Bayesian mixed models, machine learning, compositional data analysis, and Markov chains. Our investigative statistical models showed that meteorological indices had the greatest impact on yield. High mean temperature at flower bud opening and after fruit maturation, and total precipitation at flowering stage showed positive effects. Low mean temperature and low total precipitation before bud opening, at flowering, and by fruit maturity, as well as number of freezing days (<−5◦C) before flower bud opening, showed negative effects. Soil and tissue tests, and N-P-K fertilization showed smaller effects. Gaussian processes predicted yields from historical weather data, soil test, fertilizer dosage, and tissue test with a root-mean-square-error of 1447 kg ha−1 . An in-house Markov chain algorithm optimized yields modelled by Gaussian processes from tissue test, soil test, and fertilizer dosage as conditioned to specified historical meteorological features, potentially increasing yield by a median factor of 1.5. Machine learning, compositional data analysis, and Markov chains allowed customizing nutrient management of lowbush blueberry at local scale.