Machine Learning Undercounts Reproductive Organs on Herbarium Specimens but Accurately Derives Their Quantitative Phenological Status: A Case Study of Streptanthus tortuosus

Machine learning (ML) can accelerate the extraction of phenological data from herbarium specimens; however, no studies have assessed whether ML-derived phenological data can be used reliably to evaluate ecological patterns. In this study, 709 herbarium specimens representing a widespread annual herb, Streptanthus tortuosus, were scored both manually by human observers and by a mask R-CNN object detection model to (1) evaluate the concordance between ML and manually-derived phenological data and (2) determine whether ML-derived data can be used to reliably assess phenological patterns. The ML model generally underestimated the number of reproductive structures present on each specimen; however, when these counts were used to provide a quantitative estimate of the phenological stage of plants on a given sheet (i.e., the phenological index or PI), the ML and manually-derived PI’s were highly concordant. Moreover, herbarium specimen age had no effect on the estimated PI of a given sheet. Finally, including ML-derived PIs as predictor variables in phenological models produced estimates of the phenological sensitivity of this species to climate, temporal shifts in flowering time, and the rate of phenological progression that are indistinguishable from those produced by models based on data provided by human observers. This study demonstrates that phenological data extracted using machine learning can be used reliably to estimate the phenological stage of herbarium specimens and to detect phenological patterns.

Bird populations most exposed to climate change are less responsive to climatic variation

The phenology of many species shows strong sensitivity to climate change; however, with few large scale intra-specific studies it is unclear how such sensitivity varies over a species’ range. We document large intra-specific variation in phenological sensitivity to temperature using laying date information from 67 populations of two European songbirds covering a large part of their breeding range. Populations inhabiting deciduous habitats showed stronger phenological sensitivity compared with those in evergreen and mixed habitats. Strikingly, however, the lowest sensitivity was seen in populations that had experienced the greatest change in climate. Therefore, we predict that the strongest phenological advancement will not occur in those populations with the highest sensitivity. Our results show that to effectively assess the impact of climate change on phenology across a species range it will be necessary to account for intra-specific variation in phenological sensitivity, climate change exposure, and the ecological characteristics of a population.

Sweet Corn Ontogeny in Response to Irrigation and Nitrogen Fertilization

To achieve optimum quality, sweet corn should be harvested at the milking stage, therefore understanding of plant phenology could be the most important aspects for economic return in this crop. Phenological sensitivity to the environment could be especially important in the management of water and nitrogen. In the current research, sweet corn ontogeny in two years was monitored in response to irrigation and nitrogen fertility: three water regimes and five nitrogen levels. The results showed that nitrogen and water application significantly affected duration in sweet corn between emergence and silking. As nitrogen and water level was increased, the days and cumulative temperature units (TU, °C) from sowing to silking significantly increased. In 2014, sowing to silking ranged from 66 days equal to 1035 TU with deficit water and nitrogen treatment to 72 days equal to 1140 TU at full irrigation and highest nitrogen treatment. In 2015, the range of sowing to silking was from 67 days equal to 1090 TU, to 73 days equal to 1180 TU. In contrast, neither nitrogen nor water treatments had a large influence on the duration of the silking to milking period. Across the two years the duration of silking to milking was approximately 506 TU. Therefore, once silking date had been resolved harvest date of sweet corn could be readily predicted independent of water or nitrogen treatment as occurring about 506 TU following silking.

Phenological Sensitivity of Two Maize Cultivars to Trinexapac-Ethyl

ABSTRACT: In Brazilian agriculture there are few reports on trinexapac-ethyl (TE) effects on maize plant lodging management. This study aimed to evaluate the effects of sequential application of TE sprayed on different plant growth stages of maize using the simple hybrid P30F53HR and the variety SCS 154 Fortuna. Experiments were carried out in a greenhouse in the 2013 and 2014 harvests. Plants were grown singly in 5L pots filled with 75% soil and 25% substrate. The experimental design was a randomized complete block with four replications. The following treatments were performed: (T1) control (no application of growth retardant); (T2) application at V2 (100 g a.i. ha-1); (T3) sequential application of 100 g a.i. ha-1 at V2 plus V3; (T4) sequential application of 100 g a.i. ha-1 at V2+V3+V4; (T5) single application of 300 g a.i. ha-1 at V4; (T6) sequential application of 100 g a.i. ha-1 at V2+V3+V4+V5; (T7) sequential application of 100 g a.i. ha-1 at V2+V3+V4+V5+V6 and (T8) sequential application of 100 g a.i. ha-1 at V2+V3+V4+V5+V6+V7. The some morphological characteristics of the two maize genotypes changed in response to TE treatment. From stage V4 onwards, maize plant height showed signs of sensitivity to the growth retardant. Plants in T8 (TE applied over V2 to V7) were more sensitive to TE with over 45% reduction in plant height compared with application T7 (applied from V2 to V6). This response was similar in both maize genotypes, thus indicating that plants are highly sensitive to TE after the V6 stage.