Growing Season and Phenological Stages of Small Grain Crops in Response to Climate Change in Alaska

The climate change in Alaska has caused earlier spring snowmelt and the growing season expanded. However, the effect of climate change on crop phenological stages, heading (BBCH 55) and maturity (BBCH 85), is unknown. In this study, the trends of growing-season length (GSL), phenological stages of crops and climatic parameters, and the correlations between climatic parameters and the phenological stages were analyzed using the climate data and crop data over the period of 1978 to 2016. The longer GSL was found in Fairbanks (64.83˚N, 147.77˚W) and in Delta Junction (64.05˚N, 145.60˚W) but not in Palmer (61.60˚N, 149.11˚W). Sowing dates did not change significantly in three locations. The decreasing trends of heading and maturity of crops were observed but varied with location. Heading of barley and oat significantly advanced 3 and 3.1 d decade-1, respectively from 1989 to 2016 in Fairbanks while no change of heading was observed in Delta Junction and Palmer. Maturity of barley, oat and wheat significantly advanced 2.6, 3.8 and 3.9 d decade-1, respectively from 1978 to 2016 in Fairbanks (P < 0.05);maturity of oat and wheat significantly advanced 4.4 and 3.4 d decade-1 from 1978 to 2015, respectively in Delta Junction (P < 0.05). The increasing temperature trends and decreasing precipitation trends were found in Fairbanks and Delta Junction but varied with phenological stages of crops. Sowing was more important for heading than for maturity of crops. The effect of climate change on heading was less important than that on maturity. Earlier maturity of crops in Fairbanks may be attributed to increased temperatures, that in Delta Junction to both increased minimum temperature and decreased precipitation and that in Palmer to temperature and precipitation.

Impact of Management Practices on Water Extractable Organic Carbon and Nitrogen from 12-Year Poultry Litter Amended Soils

Water extractable organic carbon (WEOC) and nitrogen (WEON) are two key parameters of soil water extractable organic matter (WEOM). Proper management of manure application rate in combination with tillage and cropping management could maintain appropriate WEOC and WEON concentrations in soils while decreasing the risk of their runoff from cropland and pastures. The objective of this research was to determine the effect of poultry litter (PL) application on WEOC and WEON in soils under different crops, tillage regimes, and grazing strategies. From 2001 to 2012, PL was applied at multiple rates to cultivated fields in a corn-oat/wheat-hay rotation or to pastures grazed by cattle or ungrazed. Soil samples (0 - 15 cm) were analyzed for KCl-extractable mineral N, and WEOC, and WEON contents. In addition, Ultraviolet-visible (UV-vis) and fluorescence spectroscopies were used to characterize WEOC stability. Organic N levels were higher at the high PL application rates. The soil C:N ratio narrowed as the PL application rate increased. However, the soil from pastures which received PL tended to have a wider range of C:N ratios than soil from the cultivated fields, despite identical PL application rates. The spectral analyses indicated that WEOC properties were responsive to management and PL application rate;therefore, this parameter may be used as a guide to provide best management strategy for manure application.

Forecasting Flowering and Maturity Times of Barley Using Six Machine Learning Algorithms

Interior Alaska has a short growing season of 110 d.The knowledge of timings of crop flowering and maturity will provide the information for the agricultural decision making.In this study,six machine learning algorithms,namely Linear Discriminant Analysis(LDA),Support Vector Machines(SVMs),k-nearest neighbor(kNN),Naïve Bayes(NB),Recursive Partitioning and Regression Trees(RPART),and Random Forest(RF),were selected to forecast the timings of barley flowering and maturity based on the Alaska Crop Datasets and climate data from 1991 to 2016 in Fairbanks,Alaska.Among 32 models fit to forecast flowering time,two from LDA,12 from SVMs,four from NB,three from RF outperformed models from other algorithms with the highest accuracy.Models from kNN performed worst to forecast flowering time.Among 32 models fit to forecast maturity time,two models from LDA outperformed the models from other algorithms.Models from kNN and RPART performed worst to forecast maturity time.Models from machine learning methods also provided a variable importance explanation.In this study,four out of six algorithms gave the same variable importance order.Sowing date was the most important variable to forecast flowering but less important variable to forecast maturity.The daily maximum temperature may be more important than daily minimum temperature to fit flowering models while daily minimum temperature may be more important than daily maximum temperature to fit maturity models.The results indicate that models from machine learning provide a promising technique in forecasting the timings of flowering and maturity of barley.