Search

This study analyzed meteorological constraints on winter wheat yield in the northern Japanese island, Hokkaido, and developed a machine learning model to predict municipality-level yields from meteorological data. Compared to most wheat producing areas, this island is characterized by wet climate owing to greater annual precipitation and abundant snowmelt water supply in spring. Based on yield statistics collected from 119 municipalities for 14 years (N = 1,516) and high-resolution surface meteorological data, correlation analyses showed that precipitation, daily minimum air temperature, and irradiance during the grain-filling period had significant effects on the yield throughout the island while the effect of snow depth in early winter and spring was dependent on sites. Using 10-d mean meteorological data within a certain period between seeding and harvest as predictor variables and one-year-leave-out cross-validation procedure, performance of machine learning models based on neural network (NN), random forest (RF), support vector machine regression (SVR), partial least squares regression (PLS), and cubist regression (CB) were compared to a multiple linear regression model (MLR) and a null model that returns an average yield of the municipality. The root mean square errors of PLS, SVR, and RF were 872, 982, and 1,024 kg ha-1 and were smaller than those of MLR (1,068 kg ha-1) and null model (1,035 kg ha-1). These models outperformed the controls in other metrics including Pearson's correlation coefficient and Nash-Sutcliffe efficiency. Variable importance analysis on PLS indicated that minimum air temperature and precipitation during the grain-filling period had major roles in the prediction and excluding predictors in this period (i.e. yield forecast with a longer lead-time) decreased forecast performance of the models. These results were consistent with our understanding of meteorological impacts on wheat yield, suggesting usefulness of explainable machine learning in meteorological crop yield prediction under wet climate., Competing Interests: The authors have declared that no competing interests exist.

Background: The Rock Ptarmigan Lagopus muta japonica lives in the alpine zones of central Japan, which is the southern limit of the global distribution for this species. This species is highly dependent on alpine habitats, which are considered vulnerable to rapid climate change. This study aimed to assess the impact of climate change on potential L. muta japonica habitat based on predicted changes to alpine vegetation, to identify population vulnerability under future climatic conditions for conservation planning. We developed species distribution models, which considered the structure of the alpine ecosystem by incorporating spatial hierarchy on specific environmental factors to assess the potential habitats for L. muta japonica under current and future climates. We used 24 general circulation models (GCMs) for 2081-2100 as future climate conditions., Results: The predicted potential habitat for L. muta japonica was similar to the actual distribution of the territories in the study area of Japan's northern Alps (36.25-36.5°N, 137.5-137.7°E). Future potential habitat for L. muta japonica was projected to decrease to 0.4% of the current potential habitat in the median of occurrence probabilities under 24 GCMs, due to a decrease in alpine vegetation communities. Some potential habitats in the central and northwestern part of the study area were predicted to be sustained in the future, depending on the GCMs., Conclusions: Our model results predicted that the potential habitats for L. muta japonica in Japan's northern Alps, which provides core habitat for this subspecies, would be vulnerable by 2081-2100. Small sustainable habitats may serve as refugia, facilitating the survival of L. muta japonica populations under future climatic conditions. Impact assessment studies of the effect of climate change on L. muta japonica habitats at a nationwide scale are urgently required to establish effective conservation planning for this species, which includes identifying candidate areas for assisted migration as an adaptive strategy.

Goals: To evaluate the usefulness of a newly devised computer system for use with laser-based endoscopy in differentiating between early gastric cancer, reddened lesions, and surrounding tissue., Background: Narrow-band imaging based on laser light illumination has come into recent use. We devised a support vector machine (SVM)-based analysis system to be used with the newly devised endoscopy system to quantitatively identify gastric cancer on images obtained by magnifying endoscopy with blue-laser imaging (BLI). We evaluated the usefulness of the computer system in combination with the new endoscopy system., Study: We evaluated the system as applied to 100 consecutive early gastric cancers in 95 patients examined by BLI magnification at Hiroshima University Hospital. We produced a set of images from the 100 early gastric cancers; 40 flat or slightly depressed, small, reddened lesions; and surrounding tissues, and we attempted to identify gastric cancer, reddened lesions, and surrounding tissue quantitatively., Results: The average SVM output value was 0.846 ± 0.220 for cancerous lesions, 0.381 ± 0.349 for reddened lesions, and 0.219 ± 0.277 for surrounding tissue, with the SVM output value for cancerous lesions being significantly greater than that for reddened lesions or surrounding tissue. The average SVM output value for differentiated-type cancer was 0.840 ± 0.207 and for undifferentiated-type cancer was 0.865 ± 0.259., Conclusions: Although further development is needed, we conclude that our computer-based analysis system used with BLI will identify gastric cancers quantitatively.

This study quantitatively clarifies the life history of a shrub, Sambucus racemosa ssp. sieboldiana, in an old-growth forest, the Ogawa Forest Reserve, Japan, by a demographic approach using a projection matrix model that incorporates interactions between demographic parameters and canopy height dynamics. S. racemosa is a common deciduous shrub in central Japan and is known to grow predominantly at forest edges or roadsides. This indicates that it is a highly light-demanding species, and occurrence in gaps in old-growth stands suggests its "fugitive," gap-dependent life history in old-growth forests. We found that one distinctive feature of this species was that its seedlings can survive well in shaded conditions by alternating stems every year like perennial herb species. Matrix model analyses demonstrated that S. racemosa can continuously regenerate under the present disturbance regime of this forest and is highly adaptable to the structural dynamics of the old-growth forest. The maturity of S. racemosa shrubs depends on their size, and nearly all (>90%) of the mature (reproducing) individuals were found in gaps or near gaps. But wide seed dispersal by birds and the ability to form both seed banks and seedling banks, the latter of which has been regarded as a common characteristic of shade-tolerant climax species, probably increase the species' chances to encounter canopy gaps. Dynamic-canopied matrix models showed that the greatest elasticity is with shaded seedling survival. The frequent stem alternation of shaded seedlings often makes the growth rate negative, but the survival rate of seedlings in low light awaiting new gap creation is remarkably high (0.93 yr(-1)). The lower survival rate of the larger individuals and smaller minimum size to start reproduction than other canopy or subcanopy shade-tolerant species indicate that S. racemosa has the potential to reproduce before the closure of the encountered gaps and to complete its life history rapidly.